Ackermann, F. (1999). Airborne laser scanning - present status and future expectations. Isprs Journal of Photogrammetry and Remote Sensing, V54, (N2-3): 64-67.
Keywords: airborne laser scanning
Synopsis: This article describes present applications, makes comparisons to photogrammetry, and discusses future prospects for Airborne Laser Scanning (ALS).
 
 

Adams, J., (1999). Space Imagery and GIS in Oklahoma State Transportation Planning (power point file). A National Forum on Remote Sensing Applications to Transportation, May 11-12, Washington DC
http://scitech.dot.gov/reeng/sensmsrm/rmtsense/sbrsagnd.html,

Ahmed, F.; M. A. Karim; M. S. Alam (1995). Wavelet transform-based correlator for the recognition of rotationally distorted images. Optical Engineering, 34, (11): 3187-92.
Keywords: Adaptive filters; Feature extraction; Fourier transform optics; Image recognition; Optical correlation; Optical signal detection; Remote sensing; Wavelet transforms; Wavelet-based joint transform correlator; Rotation-invariant pattern recognition; Optical image processing; Rotationally distorted images recognition; Optimal filter parameters set; Mother wavelet filter; Composite reference feature; Noiseless environments; Noisy environments; Filter modulations; Discrimination improvement; Optical target detection ; Thresholding
Original Abstract: A novel wavelet-based joint transform correlator (WJTC) for rotation-invariant pattern recognition and applications in optical image processing and remote sensing is investigated. First an optimal set of filter parameters and a mother wavelet filter are selected. These are used to extract features at different resolution from a set of rotationally distorted training images. Then a composite reference feature is formulated from these features for use in the WJTC. Simulation results for both noisy and noiseless environments are presented to verify the effectiveness of this technique.
 

Aizenberg, I. N., (1996). Extraction of the small details on the noisy images and their sharpening: implementation on the CNN. 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) (Cat. No.96TH8180) 1996 (CNNA-96) Seville, Spain 24-26 June 1996
New York, NY, USA IEEE, pp.31-6.
Keywords: Cellular neural nets; Computer vision; Edge detection; Feature extraction; Filtering theory; Image enhancement; Remote sensing; Noisy images; Impulse noise filtering; Frequency amplification; Satellite images; Cellular neural network ; Gray scale images
Original abstract: Applications of the algorithms of impulse noise filtering, edge detection, high and medium frequencies amplification to improve the quality of gray-scale images, especially of satellite images, are considered. All the algorithms presented are implemented on the cellular neural network (the classical CNN type or based on universal binary neurons). The strategy of processing small-detailed images using the noise filtering without smoothing, edge detection and extraction of the small or other important details on the complex image background, has been carried out.
 

Al-Nuaimy, W.; Y. Huang; A. Eriksen; V. T. Nguyen (2000). Automatic feature selection for unsupervised image segmentation. Applied Physics Letters, 77, (8): 1230-2.
Keywords: Feature extraction; Image classification; Image segmentation; Image sequences; Image texture; Radar imaging; Radar theory; Automatic feature selection; Unsupervised image segmentation; Computational bottleneck; Image data; Remote sensing; Medical imaging; Automatic analysis; Automatic interpretation; Classification tasks; Segmentation tasks; Multivariate data; Dimensionality; General-purpose unsupervised image segmentation system; Automatic detection; Image regions; Visual texture properties; Suboptimal feature selection procedure; Automatic selection; Texture features; Segmentation; Ground-penetrating radar images; Automatic subsurface reports; Feature set ; Computation time
Original Abstract: A computational bottleneck is often imposed by the volume of image data generated in disciplines such as remote sensing and medical imaging, especially in situations where automatic analysis or interpretation is required. Segmentation and classification tasks that utilize multivariate data can be impeded by this dimensionality. A general-purpose unsupervised image segmentation system is presented here for the automatic detection of image regions exhibiting different visual texture properties. A suboptimal feature selection procedure is proposed to automatically select the set of texture features best suited for the particular application. Results are presented for the segmentation of ground-penetrating radar images for generating automatic subsurface reports. The reduction in the size of the feature set both reduces the computation time and improves the accuracy.
 

Aloisi, R.; Y. Grabit, (1996). Multispectral image resolution enhancement to improve efficiency of spectral analysis algorithms. Algorithms for Multispectral and Hyperspectral Imagery II Orlando, FL, USA 9-11 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.160-7.
Keywords: Correlation methods; Feature extraction; Geophysics computing; Image enhancement; Image resolution; Remote sensing; Sensor fusion; Spectral analysis; Wavelet transforms; Multispectral image; ARSIS method; Wavelet transform; Spatial resolution; Structure extraction; Spatial correlation; SPOT data; Panchromatic aerial imagery ; 10 m
Original abstract: The ARSIS method (ARSIS: French acronym for "spatial resolution enhancement by injection of structures") is based on multiresolution analysis techniques, especially on the wavelet transform. Its goal is to increase the spatial resolution of an image using the geometric structures extracted from a higher resolution image, given a sufficient level of spatial correlation between these two images. The method was developed on SPOT data for the processing of 10 meter resolution multispectral images. This paper presents the studies conducted for the adaptation of ARSIS to allow the fusion of SPOT XS data with high-resolution panchromatic aerial imagery. The models used in the original method were revealed to be ineffective for important resolution differences between the images and various methods were tested to obtain acceptable results.
 

Alquier, L.; P. Montesinos, (1996). Perceptual grouping and active contour functions for the extraction of roads in satellite pictures. Image and Signal Processing for Remote Sensing III Taormina, Italy 23-25 Sept. 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.153-63.
Keywords: Dynamic programming; Edge detection; Feature extraction; Image segmentation; Interactive systems; Noise; Remote sensing; Perceptual grouping; Active contour functions; Road extraction; Satellite pictures; Crest lines detection; Visual properties; Quality function; Curvature; Grey levels; Co-circularity; Noisy environments; High level interpretation process ; Interactive decision system
Original abstract: We present a, new method for perceptual grouping of pixels into roads after crest lines detection in satellite pictures. First the visual properties expected from the groupings are modelled as a quality function similar to active contour functions. They involve curvature, grey levels and co-circularity. This function is computed recursively and optimized from a local to global level with an algorithm related to dynamic programming. The final groupings are then selected according to their global quality. Applied to satellite images, the method proved its adaptability and its robustness to noisy environments. The results showed how the use of visual properties can provide an effective segmentation with no prior knowledge of the scene. This segmentation can be used to initialize a high level interpretation process or give a first description of the scene to an interactive decision system.
 

Ambrico, P. F.; A. Amodeo; P. Di Girolamo; N. Spinelli (2000). Sensitivity analysis of differential absorption lidar measurements in the mid-infrared region. Applied Optics, 39, (36): 6847-65.
Keywords: Air pollution measurement; Atmospheric optics; Atmospheric techniques; Optical radar; Remote sensing by laser beam; Sensitivity analysis; Differential absorption lidar measurements; Mid-infrared region; Laser sources; Tunable laser sources; IR spectral region; Differential absorption lidar; Atmospheric pollutants; Absorption lines; Emissions; Industrial plants; Urban areas; DIAL measurements; Interference; Absorption cross section; Optical depth; HCl; co; CO/sub 2/; NO/sub 2/; H/sub 2/O; O/sub 2/; Methane; Sensitivity study; Clean air; Urban polluted air; Emission ; Incinerator stack
Original Abstract: The availability of new laser sources that are tunable in the IR spectral region opens new perspectives for differential absorption lidar (DIAL) measurements. A region of particular interest is located in the near IR, where some of the atmospheric pollutants have absorption lines that permit monitoring of emissions from industrial plants and in urban areas. In DIAL measurements, the absorption lines for the species to be measured must be carefully chosen to prevent interference from other molecules, to minimize the dependence of the absorption cross section on temperature, and to optimize the measurements with respect to the optical depth. We analyze the influence of these factors and discuss a set of criteria for selecting the best pairs of wavelengths ( lambda /sub ON/ and lambda /sub OFF/) to be used in DIAL measurements of several molecular species (HCl, CO, CO/sub 2/, NO/sub 2/, CH/sub 4/, H/sub 2/O, and O/sub 2/). Moreover, a sensitivity study has been carried out for selected lines in three different regimes: clean air, urban polluted air, and emission from an incinerator stack.
 

Ancis, M.; M. Murroni; D. D. Giusto; M. Petrou, (1999). Region-based remote-sensing image compression in the wavelet domain. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293) IGARSS'99 Hamburg, Germany 28 June-2 July 1999
Piscataway, NJ, USA IEEE, v.4, pp.2054-6.
Keywords: Data compression; Geophysical signal processing; Geophysical techniques; Image coding; Image texture; Remote sensing; Terrain mapping; Vegetation mapping; Wavelet transforms; Geophysical mesurement technique; Image processing; Land surface; Agriculture; Image compression; Wavelet domain; Region-based method; Image region; Generic algorithm; Wavelet transform; Image preprocessing; Forest ; Urban
Original abstract: This paper argues that texture regions in remotely sensed images of the Earth are often of no interest to projects for example, concerned with agricultural applications. These regions require a large number of bits to be encoded. It is proposed that they can be identified using a generic algorithm that identifies the boundaries of textured regions irrespective of their class, and removed from the encoding process. The rest of the regions which may be of interest to the specific application, may be encoded using 1D wavelet transform applied to the string of pixels created by raster scanning the region. This approach can help remove the bottleneck of image down-loading from micro-satellites in low Earth orbits, because these satellites can obtain hundreds of images in an orbit but they can only download a few of them during each pass over the tracking station. The proposed approach can be fully implemented for on-board image preprocessing before the down-loading, for cases that urban and forest regions (textured regions) in the images are of no interest.
 

Anderson, S. G. (1995). Remote Sensing - Diode-Pumped Parametric Oscillator/Laser Simplifies Lidar System. Laser Focus World, V31, (N4): 46-47.
Keywords: Optics/Acoustics
 
 

Apostolopoulou, A.; N. Sekopoulos; C. Papandreou; P. Klimis, (1997). Inventory and operation of the road and public transport networks in Attica region. Transportation Systems 1997. (TS'97). Proceedings of the 8th IFAC/IFIP/IFORS. Transportation Systems 1997 (3 vol.) Chania, Greece 16-18 June 1997
Oxford, UK Pergamon, pp.443-7 vol.1.
Keywords: Database management systems; Geographic information systems; Strategic planning; Traffic information systems; Transportation; Travel industry; Road networks; Public transport networks; Attica region; Public transportation systems; Urban subsystems; Suburban subsystems; Inter-urban subsystems; Buses; Rail; ISAP Metro; Metro Development Study; Data collection; Inventory; Long-term planning; Data processing; gis ; Geographic information system
Original abstract: The existing road network and the public transportation systems in Attica comprising urban, suburban and inter-urban subsystems (buses, rail, ISAP Metro, terminals, etc.) form the environment into which the two new Metro lines, presently under construction and their future extensions or new lines will have to merge and integrate in the best possible way. In the context of the Metro Development Study (MDS), extensive data collection and inventory of the infrastructure and operation characteristics of the transportation systems is essential for the evaluation of existing conditions and for the development of a database required in long-term planning. The paper presents in brief the data collection and processing procedures, the development of related databases and GIS applications, and finally some of the significant findings, results and conclusions regarding the operation of the transportation systems.
 

Arai, K.; Y. Terayama; T. Arata, (1995). Image classification based on beta distribution for SAR image. 1995 International Geoscience and Remote Sensing Symposium, IGARSS '95. Quantitative Remote Sensing for Science and Applications (Cat. No.95CH35770) Firenze, Italy 10-14 July 1995
New York, NY, USA IEEE, pp.1263-5 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Image texture; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Geophysical measurement technique; Land surface; Terrain mapping; Radar remote sensing; SAR imagery; Image processing; Beta distribution; SAR image; Maximum likelihood decision rule; Probability density function; Multivariate normal distribution; Local least square estimator; Sigma filter; Weighting filter ; Speckle noise reduction
Original abstract: A new method for SAR image classification is proposed. The method is based on maximum likelihood decision rule with texture features and takes into account the probability density function of texture features. The experimental results show the proposed method is superior to the existing maximum likelihood method with multivariate normal distribution. 2.28 to 5.16% of improvements are observed with real SAR image. Effects of local least square estimator, sigma and weighting filters for speckle noise reduction on classification performance are clarified. The results show that 7.1 to 12.04 % of improvements on the classification performance are observed.
 

Arentze, T. A.; H. J. P. Timmermans (2000). A spatial decision support system for retail plan generation and impact assessment. Transportation Research Part C (Emerging Technologies), 8C, (1-6): 361-80.
Keywords: Decision support systems; Geographic information systems; Retail data processing; Town and country planning; Transportation; Visual databases; Spatial decision support system; Retail plan generation; Retail plan impact assessment; Land-use planning; Transportation planning; Location Planner ; Optimization
Original Abstract: Current geographic information systems typically offer limited analytical capabilities and lack the flexibility to support spatial decision making effectively. Spatial decision support systems aim to fill this gap. Following this approach, this paper describes an operational system for integrated land-use and transportation planning called Location Planner. The system integrates a wide variety of spatial models in a flexible and easy-to-use problem solving environment. Users are able to construct a model out of available components and use the model for impact analysis and optimization. Thus, in contrast to existing spatial decision support systems, the proposed system allows users to address a wide range of problems. The paper describes the architecture of the system and an illustrative application. Furthermore, the potentials of the system for land-use and transportation planning are discussed.
 

Asano, K.; A. Hoyano, (1998). Application of a new spherical thermography technique to monitoring of outdoor long wave radiant fields. Infrared Technology and Applications XXIV San Diego, CA, USA 19-24 July 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.317-24.
Keywords: Environmental engineering; Infrared imaging; Remote sensing; Spherical thermography technique; Outdoor long wave radiant fields monitoring; Urban street spaces; Above-ground condition differences; Design characteristics; Thermal comfort; Mean radiant temperature; Vector radiant temperature ; Environment measuring system
Original abstract: This paper describes the evaluation of the long wave radiant field using the spherical thermography technique we developed in previous studies. Four urban street spaces were chosen for comparison based mainly on differences in the above-ground conditions. Evaluations were conducted during good weather on summer days. The measurement results indicate that the long wave radiant field is directly influenced by the design characteristics of the urban space. The present study confirmed the usefulness of spherical thermography for evaluating the long wave radiant field.
 

Asrar, G., (1999). NASA Earth Science Enterprise: Remote Sensing Research and Commercialization (Power Point File). A National Forum on Remote Sensing Applications to Transportation, May 11-12, 1999, Washington DC
http://scitech.dot.gov/reeng/sensmsrm/rmtsense/sbrsagnd.html,

Axelsson, P. (1999). Processing of laser scanner data - algorithms and applications. ISPRS Journal of Photogrammetry and Remote Sensing, 54, (2-3): 138-147.
Keywords: processing airborne laser scanning
Synopsis: Describes laser scanner data, processing methods, classification of buildings and electric power lines.
Original Abstract: Airborne laser scanning systems are opening new possibilities for surveys and documentation of difficult areas and objects, such as dense city areas, forest areas and electrical power lines. Laser scanner systems available on the market are presently in a fairly mature state of art while the processing of airborne laser scanner data still is in an early phase of development. To come from irregular 3D point clouds to useful representations and formats for an end-user requires continued research and development of methods and algorithms for interpretation and modelling. This paper presents some methods and algorithms concerning filtering for determining the ground surface, DEM, classification of buildings for 3D City Models and the detection of electrical power lines. The classification algorithms are based on the Minimum Description Length criterion. The use of reflectance data and multiple echoes from the laser scanner is examined and found to be useful in many applications.
 

Babey, S. K.; C. D. Anger, (1996). Potential for the application of airborne hyperspectral remote sensing techniques to industrial inspection. Three-Dimensional and Unconventional Imaging for Industrial Inspection and Metrology Philadelphia, PA, USA 23-25 Oct. 1995
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.302-7.
Keywords: Automatic optical inspection; Calibration; CCD image sensors; Feature extraction; Image resolution; Image sampling; Infrared imaging; Infrared spectrometers; Process control; Quality control; Remote sensing; Spectroscopy computing; Visible spectrometers; Airborne hyperspectral remote sensing; Industrial inspection application; Optical remote sensing; High spectral resolution imagery; Optimal selection; High speed acquisition; Radiometric calibration; Conversion to spectral reflectances; Geometric correction; Discrimination of subtle features; Scene image sampling; Datacube; 2D image sensor; Spatial mode; Spectral mode; Preprocessing; Digital elevation model; Postprocessing; Algorithms; qc; Visible ; Near infrared
Original abstract: Airborne optical remote sensing has recently seen an evolution from limited spectral discrimination into high spectral resolution imagery. Hyperspectral imagers now have the ability to sample a scene at both high spatial and high spectral resolution, permitting optimal selection from the available information to meet specific applications. Techniques have been developed which provide for high speed acquisition, radiometric calibration, conversion to spectral reflectances, geometric correction and interpretation of airborne hyperspectral data. The same technology currently in use for discrimination of subtle features in airborne scenes is available for industrial inspection applications which can benefit from combined spectral reflectance and imaging information.
 

Babic, N. C., (2000). GIS supported management information systems in road administration domain. Second International Conference on Management Information Systems Incorporating GIS and Remote Sensing. Management Information Systems 2000 Proceedings of Management Information Systems Udine, Italy May 2000
Southampton, UK WIT Press, pp.177-84.
Keywords: Civil engineering computing; Construction industry; Data visualisation; Geographic information systems; Management information systems; Transportation; gis; Road administration; Business; Data abstraction; Decision makers; Road construction; Map generation; Road maintenance ; Geographic information system
Original abstract: The main goal that should guide development of management information systems is development of tools that are useful for busy practitioners to access and use information. Practitioners need methods to answer questions and make decisions. At the same time, a trend of increasing specialisation is evident in today's business. Therefore, applications should be tailored to help the user accomplish related tasks quickly. It is important to present the user with just what he/she needs and when it is needed. Also, an appropriate level of data abstraction should be provided to decision makers. Visualisation plays a very important role in this process. In the construction industry, especially road construction, visualisation is implemented with the help of GIS tools. However, we must not restrict GIS usage to map generation. Data from different sources, like spreadsheets and databases, can be correlated through maps. This ability to get the big picture allows planners to make better decisions in a more holistic manner. To accomplish this goal, GIS has to be implemented to support existing decision-making process, and not as a separate stand-alone utility. We illustrate all these principles through an example from road maintenance.
 

Baillard, C.; O. Dissard; O. Jamet; H. Maitre, (1996). Detection of above-ground in urban areas: application to DTM generation. Image and Signal Processing for Remote Sensing III Taormina, Italy 23-25 Sept. 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.129-40.
Keywords: Feature extraction; Geographic information systems; Image matching; Image segmentation; Markov processes; Remote sensing; Stereo image processing; Above-ground detection; Urban areas; DTM generation; Stereoscopic images; Stereoscopic matching stage; Digital surface model; DSM segmentation; Sloping ground; Digital terrain models; Above-ground extraction; Aerial imagery; Markov random field ; Cartographic databases
Original abstract: A new approach to the detection of above-ground from a pair of stereoscopic images in a general urban context is proposed. It includes a stereoscopic matching stage well-adapted to our task in order to provide a digital surface model (DSM). Then a segmentation of the DSM is performed, and regions are classified as ground or above-ground. The interest of the method is its ability to manage extended above-ground with several heights and any shape, as well as the case of a sloping ground. An application to digital terrain models (DTM) generation in urban areas is discussed. Assessment of both above-ground extraction and DTM generation on difficult scenes shows the feasibility of the approach.
 

Baillard, C.; O. Dissard; H. Maitre, (1998). Segmentation of urban scenes from aerial stereo imagery. Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170) Brisbane, Qld., Australia 16-20 Aug. 1998
Los Alamitos, CA, USA IEEE Comput. Soc
Proceedings., pp.1405-7 vol.2.
Keywords: Image reconstruction; Image segmentation; Remote sensing; Stereo image processing; Urban scenes; Aerial stereo imagery; Focusing strategy; 3D reconstruction; Above-ground objects; Radiometric analyses; Adjacent objects ; Slopes
Original abstract: Presents a focusing strategy for the 3-D reconstruction of urban scenes from aerial stereo pairs. It consists in segmenting the scene into above-ground objects (buildings or vegetation), and it relies on 3-D and radiometric analyses. The classification is able to cope with extended above-ground, adjacent objects, slopes, and it is robust to image and scene variability.
 

Baltsavias, E. P. (1999). Airborne laser scanning: existing systems and firms and other resources. Isprs Journal of Photogrammetry and Remote Sensing, V54, (N2-3): 164-198.
Keywords: systems airborne laser scanning, resources
Original Abstract: This article gives an overview of resources on airborne laser scanning (ALS). The main emphasis is on existing systems and firms, especially commercial ones. Through a very time-consuming search and with the help of numerous persons from firms, organisations and other colleagues, a quite complete survey of existing commercial systems, including detailed system parameters, has been compiled. This survey is by far the most complete and up-to-date information available today on commercial ALS. Additional data on contact information, links and, in some cases, a short background is given for firms involved in ALS (manufacturers, service providers, owners). A summary of other non-commercial and research systems, mainly of NASA, and respective links is presented. Finally, some other useful WEB links are given. The developments in ALS have been very rapid the last 1¯2 years. This overview reflects these developments and describes rather completely the current situation, thus, being useful for all persons involved in ALS one way or another.
 

Baltsavias, E. P. (1999). A comparison between photogrammetry and laser scanning. Isprs Journal of Photogrammetry and Remote Sensing, V54, (N2-3): 83-94.
Keywords: photogrammetry airborne laser scanning
Synopsis: An overview paper of the differences between these two systems: describes how they can be integrated. "ALS (can) 'see' objects smaller then the footprint (small opening below vegetation, powerlines, etc…)"
Original Abstract: A comparison between data acquisition and processing from passive optical sensors and airborne laser scanning is presented. A short overview and the major differences between the two technologies are outlined. Advantages and disadvantages with respect to various aspects are discussed, like sensors, platforms, flight planning, data acquisition conditions, imaging, object reflectance, automation, accuracy, flexibility and maturity, production time and costs. A more detailed comparison is presented with respect to DTM and DSM generation. Strengths of laser scanning with respect to certain applications are outlined. Although airborne laser scanning competes to a certain extent with photogrammetry and will replace it in certain cases, the two technologies are fairly complementary and their integration can lead to more accurate and complete products, and open up new areas of application.
 

Barducci, A.; I. Pippi (2001). Analysis and rejection of systematic disturbances in hyperspectral remotely sensed images of the Earth. Applied Optics, V40, (N9): 1464-1477.
Keywords: Applied Physics/Condensed Matter/Materials Science ; Optics/Acoustics
 
 

Barnsley, M. J.; S. L. Barr (1997). Distinguishing urban land-use categories in fine spatial resolution land-cover data using a graph-based, structural pattern recognition system. Computers, Environment and Urban Systems, 21, (3-4): 209-25.
Keywords: Cartography; Geographic information systems; Graph theory; Image resolution; Pattern recognition; Remote sensing; Town and country planning; Tree searching; Visual databases; Urban land use categories; Spatial resolution; Land cover data; Graph-based structural pattern recognition system; xrag; Extended Relational Attribute Graph; Remotely-sensed images; Land use maps; Ordnance Survey digital map data; Morphological properties; Spatial relations; Graph searching; Graph similarity measures ; Land cover pattern
Original Abstract: This paper presents a preliminary test of a graph-based, structural pattern recognition system-known as XRAG (eXtended Relational Attribute Graph)-that might be used to infer broad categories of urban land-use from very fine spatial resolution, remotely-sensed images. XRAG allows the structural properties of and relations between, discrete land-cover parcels to be analyzed and interpreted. Although the eventual aim is to derive land-use maps directly from remotely-sensed images, this paper employs Ordnance Survey 1:1,250 scale digital map data to provide the initial land-cover information. These data, free from the complex effects of mixed pixels, misclassification, shadowing and occlusion associated with remotely-sensed images, are used to examine the intrinsic separability of several different categories of urban land-use based on the morphological properties of, and the spatial relations between, their component land-cover parcels. In future studies, the system will be tested on real images. The current system also needs to be extended to incorporate graph searching algorithms and graph similarity measures, so that it can be used not only to describe the structural differences between sample areas of known land use, but also to infer land use from the spatial pattern of land cover.
 

Barr, S.; M. Barnsley (2000). Reducing structural clutter in land cover classifications of high spatial resolution remotely-sensed images for urban land use mapping. Computers & Geosciences, V26, (N4): 433-449.
Keywords: land use mapping mixed pixels
Synopsis: This paper discusses a method of reducing structural clutter or "noise", i.e. mixed pixels, shadowing, and occlusion, with a reflexive mapping procedure in which noisy pixels are re-labeled. This is a "region-based" method that considers area and adjacency. This method appears to work better than "majority filtering" methods.
Original Abstract: A new generation of very high spatial resolution (1¯5 m) satellite sensors is due to be launched within the next five years. Among other things, images acquired by these sensors offer considerable potential for the derivation of information on urban land use. It has been suggested that this can be achieved via a two-stage process involving (i) a standard (per-pixel) multispectral classification algorithm to identify the principal land cover parcels present in the observed scene and (ii) the application of structural pattern-recognition techniques to infer land use from the morphological properties of these parcels and the spatial relations that exist between them. It is implicit in this approach that the initial classification is of sufficient accuracy to allow land use to be inferred from these structural properties and relations. This assumption is investigated using airborne multispectral image data with a nominal spatial resolution of 2 m. It is shown that these data allow many features of interest in urban areas to be identified and delineated, but that they contain a significant amount of unwanted spatial detail (or `scene noise'). The latter results in structural `clutter' in the initial land cover classification, which limits the potential to infer land use in the second stage of the data-processing chain. To address this issue, a simple, region-based, reflexive-mapping procedure is developed. This operates at the parcel (cf. pixel) level. The procedure is successful at removing much of the structural clutter, and performs well in comparison with traditional majority filtering; however, the inference of urban land use from the resulting data remains problematic.
 

Basoz, N.; S. A. King; A. S. Kiremidjian; K. H. Law, (1996). Utilisation of GIS and network analysis for earthquake damage assessment of transportation systems. International Conference on Information Technology in Civil and Structural Engineering Design. Information Processing in Civil and Structural Engineering Design Glasgow, UK 14-16 Aug. 1996
Edinburgh, UK Civil-Comp Press, pp.151-60.
Keywords: Civil engineering computing; Decision support systems; Earthquakes; Geographic information systems; Transportation; gis; Network analysis; Earthquake damage assessment; Transportation systems; Seismic risk; Transportation structures; Emergency operations; Computational methodology; Performance evaluation ; Network analysis methodology
Original abstract: The potential seismic risk to the infrastructure of a region and the consequences of failure have been recognized as important issues within the last few decades. Damages to transportation structures during an earthquake often result in severe disruptions to the transportation systems of the region, causing major delays and affecting emergency operations. The paper describes a computational methodology for evaluating the performance of a transportation system in an area affected by an earthquake, utilizing modern computational tools and network analysis methodology.
 

Baumgartner, A.; C. T. Steger; H. Mayer; W. Eckstein, (1997). Semantic objects and context for finding roads. Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision III Orlando, FL, USA 21-23 April 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.98-109.
Keywords: Feature extraction; Geographic information systems; Image recognition; Image texture; Object recognition; Photogrammetry; Remote sensing; Semantic objects; Multiresolution approach; Automatic road extraction; Digital aerial imagery; Network; Intersections; Rural areas; Forest areas; Urban areas; Texture analysis; Edge extraction; Line extraction; Reduced resolution; Roadsides ; Quadrilaterals
Original abstract: This paper presents a multiresolution approach for automatic extraction of roads from digital aerial imagery. Roads are modeled as a network of intersections and links between the intersections. For different context regions, i.e., rural, forest, and urban areas, the model describes different relations between background objects, e.g., buildings or trees, and semantic road objects, e.g., road-parts, road-segments, road-links, and intersections. The classification of the image into context regions is done by texture analysis. The approach to detect roads is based on the extraction of edges in a high resolution image and the extraction of lines in an image of reduced resolution. Using both resolution levels and explicit knowledge about roads, hypotheses for roadsides are generated. The roadsides are used to construct quadrilaterals representing road-parts and polygons representing intersections. Neighboring road-parts are chained to road-segments. Road-links, i.e., the roads between two intersections, are built by grouping of road-segments and closing of gaps between road-segments. Road-links are constructed using knowledge about context.
 

Bejleri, I.; A. Lyons; P. Zwick, (2000). Environmental Screening Analysis Tool for transportation projects. URISA 2000 Annual Conference and Exposition Proceedings of 37th Annual Conference of the Urban and Regional Information Systems Association Orlando, FL, USA 19-23 Aug. 2000
Park Ridge, IL, USA Urban & Regional Inf. Syst. Assoc, pp.608-17.
Keywords: Cartography; Environmental science computing; Geographic information systems; Town and country planning; Transportation; Environmental Screening Analysis Tool; Transportation planning; University of Florida; esat; Florida Department of Transportation; ArcView; Spatial analyses; html; Maps; Geographic information system ; Urban planning
Original abstract: In an effort to improve and streamline transportation planning, an inter-agency taskforce led by the Florida Governor's Office developed guidelines for a process to identify environmentally sensitive transportation projects in 1999. The objective of the methodology is to identify the major impact issues of transportation projects early enough in the planning process so that they may be discussed and resolved by the appropriate agencies before additional resources are invested into planning and implementation. Subsequently, the University of Florida Geoplan Center was asked to develop the Environmental Screening Analysis Tool (ESAT) for the Florida Department of Transportation to implement the screening guidelines. Packaged as an ArcView extension, ESAT semi-automates project screening by running a series of spatial analyses and generating HTML and written outputs which present quantitative results and maps of potential impact areas.
 

Bell, C.; W. Acevedo; J. T. Buchanan, (1995). Dynamic mapping of urban regions: growth of the San Francisco/Sacramento region. URISA Proceedings. Papers from the Annual Conference of the Urban and Regional Information Systems Association Proceedings of 33rd Annual URISA Conference San Antonio, MN, USA 16-20 July 1995
Washington, DC, USA Urban & Regional Inf. Syst. Assoc, pp.723-34.
Keywords: Computer animation; Geographic information systems; History; Time series; Town and country planning; Transportation; Visual databases; Dynamic mapping; Urban regions; San Francisco/Sacramento region; Large metropolitan regions; Geographic information system; Urbanization; Urban region; Historical records; USGS topographic maps; Aerial photographs; Landsat imagery; Urban spatial extent; Digital transportation data; Tabular census data; Time series animation; Urban growth; Urbanized region; Temporal spatial data ; Spatial patterns
Original abstract: A methodology has been developed to document the tremendous growth which large metropolitan regions have experienced over time. A geographic information system (GIS) was used to compile a database of urbanization for the San Francisco/Sacramento urban region spanning 140 years. Historical records, USGS topographic maps, aerial photographs and Landsat imagery were used to identify the urban spatial extent. Digital transportation data and tabular census data were also incorporated into the database to provide a more complete picture of changes occurring over time. A time series animation of urban growth for the urbanized region depicts the alarming growth patterns the area experienced between the mid 1800s and the 1990s. The same process is being used to document growth in other urban regions, such as the Baltimore-Washington area. This innovative use of temporal spatial data and animation focuses attention on the dramatic increases in urban development and the spatial patterns that have developed over time.
 

Bellagente, M.; P. Gamba; P. Savazzi, (1999). Fuzzy texture characterization of urban environments by SAR data. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 Hamburg, Germany 28 June-2 July 1999
Piscataway, NJ, USA IEEE, pp.1232-4 vol.2.
Keywords: Geophysical signal processing; Geophysical techniques; Image classification; Image texture; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Terrain mapping; Geophysical measurement technique; Land surface; Radar remote sensing; Fuzzy texture characterization; Urban; Town; City; sar; Texture-base approach; Co-occurrence measure; Wavelet frame decomposition; Co-occurence matrix; Polarimetric SAR image; Radar polarimetry; Los Angeles; California ; United States
Original abstract: The authors present a texture-base approach to the classification of SAR images recorded over urban environments. In particular, they explore the use of some co-occurrence measures and the wavelet frame decomposition, to investigate if there is an advantage, and where, in using these tools. They found that the correct classification rates are only partially increased by using these additional information, with a slight preference for texture analysis through the co-occurence matrix. These considerations are validated by analyzing polarimetric SAR images recorded over Los Angeles by the AIRSAR sensor.
 

Belov, M. L.; V. A. Gorodnichev; V. I. Kozintsev (1996). Remote Sensing of Oil Films on the Sea Surface Using a Satellite-Based Lidar. Earth Observation and Remote Sensing, V13, (N6): 919-927.
Keywords: Optics/Acoustics
 
 

Benedikisson, K.; H. Benedikisson; J. A. Benedikisson; J. R. Sveinsson, (1998). An extension of parametric decision boundary feature extraction (DBFE) for classification of hyperdimensional data. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE., pp.2694-6 vol.5.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Multidimensional signal processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Optical imaging; Multispectral method; Hyperspectral imagery; Parametric decision boundary feature extraction ; Hyperdimensional data
Original abstract: Decision boundary feature extraction (DBFE) estimates the decision boundary between individual classes and uses it for feature extraction. Because the DBFE relies on the estimate of the decision boundary, it fails when not enough data are available. To overcome this problem, it is suggested to increase the size of the training set by including random data based on the estimated mean vectors and covariance matrices of the classes in the original training set. In experiments, this approach shows potential when very limited training data are available for some classes.
 

Benediktsson, J. A.; K. Arnason; A. Hjartarson; D. A. Landgrebes, (1996). Classification and feature extraction with enhanced statistics. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) IGARSS '96. Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.414-16 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Infrared imaging; Optical information processing; Remote sensing; Geophysical measurement technique; Terrain mapping; Land surface; Optical imaging; IR imaging; Satellite remote sensing; Image processing; Enhanced statistics; aviris; Spatial classifier; Pixel classifier; Decision boundary feature extraction; Discriminant analysis; Geological unit; Spectral properties ; Geology
Original abstract: Classification of AVIRIS data is considered with respect to enhanced statistics. The performance of enhanced statistics is investigated in terms of feature extraction for both pixel and spatial classifiers. The feature extraction methods applied are decision boundary feature extraction and discriminant analysis. The classification results obtained by enhanced statistics are excellent and show the classifiers to be able to distinguish between several geological units with very similar spectral properties.
 

Benediktsson, J. A.; J. I. Ingimundarson; J. R. Sveinsson, (1997). Classification and feature extraction of hyperdimensional data using LOOC covariance estimation. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042). Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.913-15 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Remote sensing; Sensor fusion; Geophysical measurement technique; Land surface; Terrain mapping; Multispectral remote sensing; Hyperdimensional; looc; Image processing; Multidimensional signal processing; Leave one out covariance; Covariance estimation; Decision boundary feature extraction ; dbfe
Original abstract: New methods for processing of multisource and hyperdimensional data are discussed both in terms of feature extraction and classification. An extension to decision boundary feature extraction (DBFE) is proposed. The extension is based on a recently developed covariance estimator, the leave one out covariance (LOOC). The extended decision boundary method is tested on a multisource remote sensing and geographic data set.
 

Benediktsson, J. A.; J. Sigurdsson; J. R. Sveinsson, (1998). Feature extraction based on LOOC estimation. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.2053-5 vol.4.
Keywords: Covariance matrices; Edge detection; Estimation theory; Feature extraction; Geophysical signal processing; Image classification; Remote sensing; LOOC estimation; Decision boundary feature extraction; dbfe; Covariance estimator; Leave one out covariance; LOOC-DBFE method ; Hyperdimensional remote data set
Original abstract: An extension to decision boundary feature extraction (DBFE) is discussed. The extension is based on a covariance estimator, the leave one out covariance (LOOC). The LOOC-DBFE method is tested on a hyperdimensional remote data set and compared to original DBFE. The proposed approach compares favorably with the original DBFE method, especially in hyperdimensional cases.
 

Benediktsson, J. A.; J. R. Sveinsson, (1997). Classification of hyperdimensional data using data fusion approaches. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042) IGARSS'97. Symposium Proceedings. Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.1669-71 vol.4.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Geophysics computing; Image classification; Neural nets; Remote sensing; Sensor fusion; Geophysical measurement technique; Image processing; Terrain mapping; Multispectral remote sensing; Hyperspectral remote sensing; Hyperdimensional data; Data fusion; Statistical classification method; Consensus; Consensus theoretic methods; Weighting; Combined classification; Weights; Decision boundary theory; Preprocessing; Neural network ; Neural net
Original abstract: Statistical classification methods based on consensus from several data sources are considered with respect to classification and feature extraction of hyperdimensional data. The consensus theoretic methods need weighting mechanisms to control the influence of each data source in the combined classification. The weights are optimized in order to improve the combined classification accuracies. Decision boundary feature extraction is considered as a preprocessing method in the data fusion. Consensus theory optimized with neural networks outperforms all other methods in terms of test accuracies in the experiments.
 

Benediktsson, J. A.; J. R. Sveinsson (1997). Feature extraction for multisource data classification with artificial neural networks. International Journal of Remote Sensing, 18, (4): 727-40.
Keywords: Feature extraction; Multilayer perceptrons; Pattern classification; Remote sensing; Sensor fusion; Multisource data classification; Artificial neural networks; Remote sensing data; Geographic data; Principal component analysis; pca; Discriminant analysis; Decision boundary feature extraction method ; Multilayer neural networks
Original Abstract: Classification of multisource remote sensing and geographic data by neural networks is discussed with respect to feature extraction. Several feature extraction methods are reviewed, including principal component analysis, discriminant analysis, and the recently proposed decision boundary feature extraction method. The feature extraction methods are then applied in experiments in conjunction with classification by multilayer neural networks. The decision boundary feature extraction method shows excellent performance in the experiments.
 

Benediktsson, J. A.; J. R. Sveinsson; K. Arnason (1995). Classification and Feature Extraction of Aviris Data. Ieee Transactions on Geoscience and Remote Sensing, V33, (N5): 1194-1205.
Keywords: feature extraction AVIRIS, feature classification
 
 

Benedirk, J.; Y. Nishiwaki, (1998). A fuzzy clustering application to land use classification in satellite images. Fuzzy Logic and Intelligent Technologies for Nuclear Science and Industry. Proceedings of the 3rd International FLINS Workshop Antwerp, Belgium 14-16 Sept. 1998
Singapore World Scientific, pp.368-75.
Keywords: Fuzzy set theory; Image classification; Matrix algebra; Pattern clustering; Remote sensing; Fuzzy clustering; Land use classification; Satellite images; Nuclear safeguards; Ambiguity; Vagueness; Unsupervised clustering; LANDSAT TM image; Urban area ; Euclidean-distance-based fuzziness measure
Original abstract: In nuclear safeguards the pictures taken by satellite may be used as an important means to identify doubtful places on land. The paper describes a preliminary test for that purpose. With the advancement of satellite technology, uncertainty due to low geometrical and spectral resolution is diminishing. Different kinds of uncertainty are present, however, while obtaining information on land use classes. Both the ambiguity and the vagueness of drawing a line between two geographical regions are addressed by fuzzy sets. Unsupervised clustering is performed on a LANDSAT TM image of Vienna, Austria, the results being used as a measure of fuzziness on the data. The degree of vagueness inherent to the subjective evaluation of geographical terms, such as *urban area', is determined by a Euclidean-distance-based measure of fuzziness.
 

Benitz, G. R. (1997). High-definition vector imaging. Lincoln Laboratory Journal, 10, (2): 147-70.
Keywords: Airborne radar; Array signal processing; Feature extraction; Image reconstruction; Image resolution; Maximum likelihood detection; Millimetre wave imaging; Radar clutter; Radar imaging; Radar target recognition; Remote sensing by radar; Speckle; Synthetic aperture radar; High-definition vector imaging; Data-adaptive approach; Synthetic-aperture radar; Radar image reconstruction; Superresolution techniques; Target recognition; uhf sar; Millimeter-wave SAR; Target identification; Radar imagery; Two-dimensional minimum-variance techniques; Maximum-likelihood algorithm; Capon algorithm; Two-dimensional MUSIC algorithm; Multiple signal classification; Wideband rail SAR measurements; SAR reflector measurements; Resolution improvement; Clutter rejection; Airborne millimeter-wave SAR data; Speckle reduction; HDVI vector aspect; Nonpointlike scattering models; Feature detection; Vector image; Airborne UHF radar; Broadside flash model; Data information ; Adaptive beamforming
Original Abstract: High-definition vector imaging (HDVI) is a data-adaptive approach to synthetic-aperture radar (SAR) image reconstruction based on superresolution techniques originally developed for passive sensor arrays. The goals are to produce more informative, higher-resolution imagery for improving target recognition with UHF and millimeter-wave SAR and to aid the image analyst in identifying targets in radar imagery. Algorithms presented here include two-dimensional minimum-variance techniques based on the maximum-likelihood method (Capon) algorithm and a two-dimensional version of the MUSIC (multiple signal classification) algorithm. Simulations are used to compare processing techniques and the results of wideband rail SAR measurements of reflectors in foliage, demonstrating resolution improvement and clutter rejection are presented. Results with airborne millimeter-wave SAR data demonstrate improved resolution and speckle reduction. We also discuss the vector aspect of HDVI, i.e., the incorporation of non-pointlike scattering models to enable feature detection. An example of a vector image is presented for data from an airborne UHF radar, using the broadside flash model to reveal greater information in the data.
 

Berardino, P.; A. Borgia; G. Fornaro; R. Lanari; E. Sansosti; M. Tesauro, (2000). Anticline growing beneath the urban area of Catania (Italy) measured by SAR interferometry. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2218-20 vol.5.
Keywords: Geodesy; Geophysical techniques; Remote sensing by radar; Synthetic aperture radar; Tectonics; Topography (Earth); Volcanology; Italy; Sicily; Vertical motion; Uplift; Volcano; Anticline; Growth; Land surface; Topography; Urban area; Catania; Town; SAR interferometry; InSAR; Radar observations; Differential SAR interferometry; Rise; Basal anticline; Outward thrusting; Basal decollement; Etna; Spreading process ; Geophysical measurement technique
Original abstract: The authors applied the differential SAR interferometry technique to detect and measure the rise of a basal anticline beneath the urban area of Catania (Italy) which originates from outward thrusting above the basal decollement of Etna volcano. This phenomenon, coupled with the already documented active extension of the volcano summit area, demonstrates the occurrence of the active volcanic spreading process.
 

Bernstein, R.; V. Di Gesu (1999). A combined analysis to extract objects in remote sensing images. Pattern Recognition Letters, 20, (11-13): 1407-14.
Keywords: Feature extraction; Mathematical morphology; Object recognition; Remote sensing; Statistical analysis; Remote sensing images; Shape recognition; Resolution power ; Structural information
Original Abstract: This paper describes an object recognition system to extract shape information from remote sensing images. One of the goals is to determine if towers and power lines can be seen on one-meter imagery and how much ground conditions can influence the resolution power of the recognition algorithms. To this end, an integrated analysis system has been implemented inside the remote sensing imaging system. The methodology consists in the combination of statistical and structural information. It has been tested on real images and it can be integrated in an automatic system for the assessment of post storm damage.
 

Bernstein, R.; M. Oristaglio; D. E. Miller; J. Haldorsen (2000). Imaging radar maps underground objects in 3-D. IEEE Computer Applications in Power, 13, (3): 20-4.
Keywords: Buried object detection; Electric conduits; Radar imaging; Underground cables; Imaging radar; Underground objects mapping; Underground electric lines; Underground gas lines; Underground communication lines; Maintenance; Conduits location; Cables location; Subsurface networks mapping; Ground-penetrating imaging radar; Three-dimensional images; Schlumberger Corporation; Electric Power Research Institute; Gas Research Institute; Underground imaging system; Maintenance costs reduction; Utility operating costs reduction; New York City; San Diego; Urban areas; Mapping system; 3 m ; 10 feet
Original Abstract: City streets cover a complex array of underground electric, gas, and communication lines. Effective maintenance, expansion, and new installation of these networks require accurate information regarding the location of the conduits, cables, and other structures that lie beneath the surface. Underground maps, if they exist, are often inaccurate, incomplete, or out of date, and attempts to find underground lines or obstacles using metal locators often prove disappointing. To help companies create accurate maps of subsurface networks, researchers have developed a new ground-penetrating imaging radar (GPIR) system that creates sharp, three-dimensional (3-D) images of underground lines and objects. Schlumberger Corporation, in conjunction with the Electric Power Research Institute (EPRI) and the Gas Research Institute, has developed a GPIR system that detects, locates, and produces 3D maps of underground features. The new underground imaging system holds the potential to reduce utility operating and maintenance costs by avoiding unneeded excavation and by reducing incidences of costly damage such as ruptured gas lines. Field demonstrations in New York City, San Diego, and other utility locations have proven the ability of the new mapping system to create accurate images of objects in crowded urban areas at depths as great as 10 ft (3 m).
 

Berthelot, C.; T. Scullion; R. Gerbrandt; L. Safronetz (2001). Ground-penetrating radar for cold in-place recycled road systems. Journal of Transportation Engineering-Asce, V127, (N4): 269-274.
Keywords:
 
 

Bessettes, V.; J. Desachy, (1998). Extraction and classification of urban areas on SPOT images. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174)Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.2583-6 vol.5.
Keywords: T. I. Stein
Original abstract: The study of urban area is an important problem in image interpretation. It is interesting to be able to analyse town development, to make streets maps automatically or just, to mask urban areas in satellite images. The objective of this study is to extract urban areas from remote sensing images and to make a classification of these areas. The proposed method combines different types of operators in order to improve the final detection. At first, the authors separate urban areas from the other type of regions (vegetation, rivers...). Then these urban areas are segmented according to the thoroughfares to obtain urban districts. Finally, the authors define a measure of urban density. This study is performed by IRIT and has been partially funded by CNES agency in the frame of the CNES program on studies and research on automatic analysis and interpretation of SPOT images.
 

Bessettes, V.; J. Desachy, (1998). Using SPOT images for urban area classification. Image and Signal Processing for Remote Sensing IV Barcelona, Spain 21-23 Sept. 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.188-200.
Keywords: Feature extraction; Geography; Image classification; Mathematical operators; Remote sensing; Urban areas detection; Classification; SPOT images; Co-operative operators; Image interpretation; Town development; Satellite images; Extraction; Remote sensing images ; Urban density
Original abstract: The urban areas represent a vast subject in image interpretation. It is interesting to be able to analyze town development, to make street maps automatically or just, to mask the urban areas in satellite images. The objective of this study is to extract urban areas from remote sensing images and to make a classification of these areas. The proposed method combines different types of operators. At first, we define automatically a mask of the urban areas by combining a classification algorithm with edge extraction algorithms. Then these urban areas are segmented according to the streets, railways and rivers to obtain urban districts. Finally, we define a measure of urban density. In this paper, we focus on the urban extraction algorithm and the urban segmentation process. This study is performed by IRIT and has been partially funded by CNES agency.
 

Bessettes, V.; J. Desachy, (1997). Urban areas detection and classification on SPOT images using co-operative operators. Image Processing, Signal Processing, and Synthetic Aperture Radar for Remote Sensing London, UK 22-26 Sept. 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.320-31.
Keywords: Feature extraction; Geography; Image classification; Mathematical operators; Remote sensing; Urban areas detection; Classification; SPOT images; Co-operative operators; Image interpretation; Town development; Satellite images; Extraction; Remote sensing images ; Urban density
Original abstract: The study of urban areas is an important problem in image interpretation. It is interesting to be able to analyze town development on satellite images or to mask urban areas automatically. The method we present in this paper consists in the extraction of urban areas from remote sensing images and the classification of these areas. We separate the urban areas from the other types of regions. Then we classify them according to a measure of the urban density. The algorithms we use, combine different types of operators in order to improve the final classification.
 

Bessettes, V.; J. Desachy; E. Cubero-Castan, (1996). Applying co-operative operators for urban area detection using SPOT imagery. Image and Signal Processing for Remote Sensing III Taormina, Italy 23-25 Sept. 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.106-17.
Keywords: Feature extraction; Image classification; Image segmentation; Remote sensing; Co-operative operators; Urban area detection; SPOT imagery; Image interpretation; Town development; Satellite images; Urban areas; Remote sensing images; Detection algorithm; irit; CNES program ; Automatic analysis
Original abstract: The study of urban area is an important problem in image interpretation. It is interesting to be able to analyse town development on satellite images or to mask urban areas. The objective of this study is to extract urban areas from remote sensing images and to make a classification of these areas. The detection algorithm combines different types of operators in order to improve the final detection. We separate urban areas from the other type of regions (vegetation, rivers etc.). Then the urban areas are classified into various under-classes (dense urban areas, suburbs etc.). This study has been performed by IRIT in the frame of the CNES program on studies and research on automatic analysis and interpretation of SPOT images.
 

Bessettes, V.; J. Desachy; M. J. Lefevre, (2000). Use of directional variance for urban area analysis on simulated Spot 5 images. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2890-2 vol.7.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Image texture; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Optical imaging; Satellite remote sensing; spot 5; Urban area; Town; City; Directional variance; Urban area analysis; High resolution; Panchromatic mode; Panchromatic image; Road; Textural feature extraction; Image processing; Segmentation; Edge detection ; Detection algorithm
Original abstract: CNES is due to launch the SPOT 5 satellite during 2001. One of its particularities, compared to the previous generations of SPOT satellites, will be its high resolution in panchromatic mode (5m and Supermode 2.5m). Before launch, CNES has to validate the choices made for the sensors with the use of simulated images. The authors's study has been made as part of the use of SPOT 5 panchromatic images for urban area analysis. The aim of the study is to extract urban areas and roads from panchromatic simulated SPOT 5 images. The proposed method combines a textural feature extraction with segmentation by edge detection in order to improve the final classification. At first, they define a textural feature based on the directional variance of the image. Then they use classification algorithms on this feature, combined with an edge detection operator, to extract the urban areas and the roads from the image.
 

Betti, A.; M. Barni; A. Mecocci, (1997). Using a wavelet-based fractal feature to improve texture discrimination on SAR images. Proceedings. International Conference on Image Processing (Cat. No.97CB36144) Santa Barbara, CA, USA 26-29 Oct. 1997
Los Alamitos, CA, USA IEEE Comput. Soc
Proceedings., pp.251-4 vol.1.
Keywords: Electromagnetic wave polarisation; Feature extraction; Fractals; Fuzzy systems; Image representation; Image segmentation; Image texture; Radar applications; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Wavelet transforms; Texture discrimination; SAR images; Wavelet-based fractal feature; Cover classes discrimination; Remote sensing image segmentation; Clustering techniques; Pyramid-based methods; Performance; Global algorithms; Single polarization synthetic aperture radar; SAR data; Mono-band images; Wavelet-based fuzzy clustering algorithm; Texture image; Fractal model; Wavelet representation ; X-SAR images
Original abstract: Clustering is commonly used in remote sensing image segmentation. Among the clustering techniques, pyramid-based methods generally provide better performance in discriminating among different cover classes if compared to global algorithms. When applied to single polarization synthetic aperture radar (SAR) data, though, such algorithms suffer from misinterpretation problems due to the mono-band nature of the images produced by these sensors. In this case an important feature to improve the segmentation is texture. This paper describes a wavelet-based fuzzy clustering algorithm which receives as input both the remotely sensed image and a texture image based on a fractal model, derived from the wavelet representation itself. The algorithm has been tested on X-SAR images, and the results demonstrate its potential usefulness.
 

Bhaskar, S.; B. Datt, (2000). Sub-pixel analysis of urban surface materials. A case study of Perth, W. Australia. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120)Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.1535-7 vol.4.
Keywords: Geophysical techniques; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Multispectral remote sensing; Hyperspectral remote sensing; Visible; ir; Infrared; Town; City; Urban scene; Perth; Australia; Subpixel analysis; Urban surface material; Spectral library; Spectral unmixing; Geo-referenced map ; Surface materials
Original abstract: Hyperspectral analysis of urban areas has the potential to deliver a cost-effective alternative to urban planning and management. This paper describes the compilation of a spectral library of urban surface materials which was used for calibrating an airborne hyperspectral image of a selected area in Perth, Western Australia. Spectral unmixing was performed to decompose this image into abundance of individual surface materials. A geo-referenced map showing the distribution of surface materials was generated.
 

Bhaumik, D.; N. L. Faust; D. Estrada; J. Linares, (1997). Three-dimensional urban GIS for Atlanta. Modeling, Simulation, and Visualization of Sensory Response for Defense Applications Orlando, FL, USA 22-23 April 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.115-24.
Keywords: Cartography; Data visualisation; Geographic information systems; Image resolution; Message passing; Multimedia computing; Remote sensing; Virtual reality; Urban GIS; Virtual 3D geographic information system; GA Atlanta, USA; Prototype system; Interactive tool; Spatial data exploration; High-density urban environment; Terrain elevation; Imagery; GIS layers; Natural features; Man-made features; 1996 Olympic Games; Olympic Village; Georgia Tech; Detailed 3D databases; Downtown area; Visualization software; Query functions; Analysis functions; Productivity ; Multimedia
Original abstract: Georgia Tech has developed a prototype system for the demonstration of the concepts of a virtual 3D geographic information system (GIS) in an urban environment. The virtual GIS integrates the technologies of GIS, remote sensing and visualization to provide an interactive tool for the exploration of spatial data. A high-density urban environment with terrain elevation, imagery, GIS layers and 3D natural and man-made features is a stressing test for the integration potential of such a virtual 3D GIS. In preparation for the 1996 Olympic Games, Georgia Tech developed two highly detailed 3D databases over parts of Atlanta. A 2.5-m database was used to depict the downtown Atlanta area, with much higher resolution imagery being used for photo-texture of individual Atlanta buildings. Less than 1-m imagery data was used to show a very accurate map of Georgia Tech and the 1996 Olympic Village. The Georgia Tech-developed visualization software was integrated via message passing with a traditional GIS package so that all commonly-used GIS query and analysis functions could be applied within the 3D environment. This project demonstrates the versatility and productivity that can be accomplished by operating GIS functions within a virtual GIS and multimedia framework.
 

Bickel, D. L.; W. H. Hensley; D. A. Yocky, (1997). The effect of scattering from buildings on interferometric SAR measurements. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042) Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.1545-7 vol.4.
Keywords: Geodesy; Geophysical techniques; Height measurement; Remote sensing by radar; Synthetic aperture radar; Topography (Earth); Geophysical measurement technique; Land surface topography; Terrain mapping; Urban area; Buildings; Building; City; Town; Radar remote sensing; Spaceborne radar; Radar imaging; Interferometric SAR; ifsar; InSAR; Elevation model; Scattering mechanism ; Coherence
Original abstract: The determination of elevation models of buildings using interferometric synthetic aperture radar (IFSAR) is an important area of active research. The focus of this paper is on some of the unique scattering mechanisms that occur with buildings and how they affect the IFSAR height measurement and the coherence. The authors show by theory and examples that the various data products obtained from IFSAR can be used to aid in interpreting building height results. They also present a method that they have used successfully in mapping buildings in Washington D.C.
 

Blacknell, D.; R. J. A. Tough (1997). Clutter discrimination in polarimetric and interferometric synthetic aperture radar imagery. Journal of Physics D (Applied Physics), 30, (4): 551-66.
Keywords: Ecology; Feature extraction; Pollution measurement; Radar clutter; Radar imaging; Radar polarimetry; Remote sensing by radar; Synthetic aperture radar; Clutter discrimination; Interferometric synthetic aperture radar imagery; Polarimetric synthetic aperture radar imagery; Vegetation; Environmental effects; Damping; Sea surface; Pollutants; Maritime military targets; Land-based targets; Background clutter; Localized clutter features; Multiple-channel SAR systems ; Statistical characteristics
Original Abstract: Many synthetic aperture radar (SAR) images contain extended regions of apparently homogeneous clutter arising from areas of vegetation or uniformly driven expanses of water. These regions may contain localized clutter variations resulting from the presence of features of ecological interest, such as changes in vegetation density due to environmental effects or damping of the sea surface by pollutants. Alternatively such clutter variations may be due to the signatures of partially concealed land-based or maritime military targets. It is thus of interest to develop techniques which can discriminate localized clutter features from the background clutter. Multiple-channel SAR systems can provide several images of a scene of this type which contain complementary sets of information. These can be combined to generate a single enhanced image of the scene in which it is possible to discriminate more effectively among the features it contains. In this paper a unified discussion of multi-channel enhancement techniques, which make use of varying degrees of knowledge regarding the statistical characteristics of the image features, is presented.
 

Blonda, P.; A. Bennardo; G. Pasquariello; G. Satalino; V. la Forgia, (1996). Application of the fuzzy Kohonen clustering network to remote sensed data processing. Applications of Fuzzy Logic Technology III Orlando, FL, USA 10-12 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.119-29.
Keywords: Backpropagation; Feature extraction; Fuzzy neural nets; Image classification; Remote sensing; Self-organising feature maps; Fuzzy Kohonen clustering network; Remote sensed data processing; Classification experiments; Multi-modular neural classification system; Labelling; Unsupervised module; Supervised module; Backpropagation learning rule; Neural net performance; Kohonen self organizing map neural network ; Complex data pre-processing
Original abstract: The effectiveness of the fuzzy Kohonen clustering network (FKCN) has been explored in two classification experiments of remote sensed data. The FKCN has been introduced in a multi-modular neural classification system for feature extraction before labelling. The unsupervised module is connected in cascade with the next supervised module, based on the backpropagation learning rule. The performance of the FKCN has been evaluated in comparison with those of a conventional Kohonen self organizing map (SOM) neural network. Experimental results have proved that the fuzzy clustering network can be used for complex data pre-processing.
 

Blonda, P.; A. Bennardo; G. Satalino; G. Pasquariello (1996). Fuzzy logic and neural techniques integration: an application to remotely sensed data. Pattern Recognition Letters, 17, (13): 1343-8.
Keywords: Fuzzy logic; Fuzzy neural nets; Fuzzy set theory; Neural net architecture; Pattern classification; Remote sensing; Unsupervised learning; Remotely sensed data; Fuzzy neural networks; Fuzzification; Unsupervised fuzzy architecture; Feature extraction ; Fuzzy min-max neural networks
Original Abstract: The paper reviews the most recent proposals on the integration of fuzzy and neural networks techniques. First, it focuses on the strategies developed and employed for the fuzzification of neural network architectures. Then it applies an unsupervised fuzzy architecture to the analysis of remotely sensed data and compares the results with those obtained by means of a conventional neural model.
 

Blonda, P.; A. M. Bognani; G. Ria; G. Satalino; A. Baraldi, (1998). Neuro-fuzzy analysis of remote sensed Antarctic data. New Trends in Fuzzy Logic II. Proceedings of the Second Italian Workshop on Fuzzy Logic Proceedings of the WLF 97 - Italian Workshop on Fuzzy Logic Bari, Italy 19-20 March 1997
Singapore World Scientific, pp.284-91.
Keywords: ART neural nets; Data analysis; Feature extraction; Fuzzy neural nets; Neural net architecture; Remote sensing; Self-organising feature maps; Neuro-fuzzy architecture; Fully self-Organizing Simplified Adaptive Resonance Theory; Remote sensed Antarctic data; Classification experiment; Fuzzy set memberships; Weights updating; Disjointed subnets; fosart; Faster adaptivity; Vigilance test ; Neuron proliferation.
Original abstract: A new neuro-fuzzy architecture, the Fully self-Organizing Simplified Adaptive Resonance Theory (FOSART), has been applied to the analysis of remote sensed Antarctic data in a classification experiment. FOSART employs fuzzy set memberships in the weights updating rule; it applies an ART-based vigilance test to control neuron proliferation and takes advantage of the fact that it employs a new version of the Competitive Hebbian Rule to dynamically generate and remove synaptic links between neurons, as well as neurons. FOSART can develop disjointed subnets. The results obtained with FOSART have been compared with those obtained with Fuzzy Learning Vector Quantization (FLVQ), and Self Organizing Feature Map (SOM) networks. The finding suggests that FOSART performances are lower, at convergence, than those of FLVQ and SOM, even if it shows a faster adaptivity to the input data structure, due to its topological and on-line characteristics.
 

Blonda, P.; V. Laforgia; G. Pasquariello; G. Satalino (1996). Feature Extraction and Pattern Classification of Remote Sensing Data by a Modular Neural System. Optical Engineering, V35, (N2): 536-542.
Keywords: Applied Physics/Condensed Matter/Materials Science ; Optics/Acoustics
 
 

Bocco, G.; R. Sanchez; H. Riemann (1995). GIS affects flood planning efforts. GIS World, 8, (2): 58-60.
Keywords: Disasters; Geographic information systems; Geophysical catastrophes; Public administration; Remote sensing; Town and country planning; Flood planning efforts; gis; Natural disaster; Developing countries; Contingency planning; January 1993 floods; Tijuana; Mexico; Remote sensing technologies; Spatial issues; Environmental issues; Urban matters; Temporal resolution; Spatial resolution ; Aerial photographs
Original Abstract: Floods are the most frequent type of natural disaster, especially in developing countries. Few results have been achieved to prevent such catastrophes, emphasizing the vulnerability of the world's societies, particularly the poorer ones, to natural disasters and the urgent need to speed up contingency planning to control and reduce their impact. A GIS was established during the January 1993 floods in Tijuana, Mexico, to assess their effects and to contribute to more detailed contingency planning efforts. GIS and remote sensing technologies have been used extensively during the last five years to approach environmental and spatial issues related to urban matters. The Tijuana study was based on that approach. Because of the spatial and temporal resolutions required for this type of research, aerial photographs were used rather than satellite images.
 

Boehner, C.; M. A. Esposito, (1996). Optical and radar merge: application on Firenze's urban environment. Geographical Information from Research to Application Through Cooperation. Second Joint European Conference and Exhibition Proceedings of Joint European Conference on Geographical Information Barcelona, Spain 27-29 March 1996
Amsterdam, Netherlands IOS Press, pp.679-82 vol.1.
Keywords: Geographic information systems; History; Remote sensing by radar; Town and country planning; Visual databases; Urban environment; European towns; Firenze; Urban planning; Monuments; Ancient squares; Bridges; Remote sensing; Construction materials; Optical remotely sensed data; Resolution; Remotely sensed radar data; Ground truth control data; End-user oriented applicability; Databases ; Geographic information system
Original abstract: Historical European towns such as Firenze have a very mixed urban tissue characterised by the presence of monuments, ancient squares and bridges. The project will detect and classify by remote sensing the construction materials forming the urban environment. The available optical remotely sensed data lacks resolution and thematic information which is needed for urban scale applications. The question: is remotely sensed radar data being more precise in resolution, eventually combined with optical RS data and to ground truth control data, able to offer more satisfying results? If so, an automation methodology has to be developed in order to offer end-user oriented applicability that allows to integrate this data with already existing traditional databases.
 

Boerner, W. M.; J. S. Verdi, (1996). Recent advances in WISIP: wideband interferometric sensing and imaging polarimetry. ISAP 1996. Proceedings of the 1996 International Symposium on Antennas and Propagation Chiba, Japan 24-27 Sept. 1996
Tokyo, Japan Inst. Electron. Inf. & Commun. Eng, pp.873-6 vol.3.
Keywords: Airborne radar; Disasters; Earthquakes; Environmental factors; Feature extraction; Geophysical techniques; Global Positioning System; Radar clutter; Radar imaging; Radar polarimetry; Radar target recognition; Radiowave interferometry; Remote sensing by radar; Spaceborne radar; wisip; Wideband interferometric sensing; Imaging polarimetry; Wide area environmental monitoring; Terrestrial covers; Planetary covers; Dynamic optimal image feature extraction; Target sections; Background clutter/speckle; Target detection; Target recognition; Target identification; Vibrating target; Interferometric POL-SAR imaging techniques; Polarimetric coregistered signature sensing; Navigational electronic tools; dgps; NASA-JPL/AIR-SAR airborne radar; nawc/p3-pol-sar; dlr-oph/do-pol-sar; ers-1/2; JERS-1 satellite radar; Flood ; Earthquake
Original abstract: WISIP, wideband ( mu Hz-PHz) interferometric sensing and imaging polarimetry, has become an indispensable tool in wide area environmental monitoring of terrestrial and planetary covers. It allows dynamic optimal image feature extraction of significant characteristics of a desirable target and/or target sections with simultaneous suppression of undesirable background clutter/speckle. WISIP may be adopted for the detection, recognition and identification (DRI) of any stationary, moving or vibrating target versus arbitrary stationary, dynamically changing or moving geophysical/ecological environments. A comprehensive overview is presented on how these modern high resolution/precision completely polarimetric coregistered signature sensing and interferometric POL-SAR imaging techniques, complemented by full integration of novel navigational electronic tools, such as DGPS, will advance electromagnetic vector wave sensing and imaging towards the limits of physical realizability. Various examples utilizing NASA-JPL/AIR-SAR, NAWC/P3-POL-SAR, DLR-OPH/DO-POL-SAR airborne, ERS-1/2, JERS-1 satellite and SIR-C/X-SAR shuttle imaging data sets dealing with recent major flood and various earthquake surface deformation events as well as other geo-environmental applications will be presented for demonstrating the utility of WISIP.
 

Boesch, R., (1998). Framework for feature extraction of natural objects. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174) Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.2062-4 vol.4.
Keywords: Feature extraction; Geophysical signal processing; Image recognition; Remote sensing; Natural objects; Image processing; Aerial data; Satellite data ; Hypothesis-based approach
Original abstract: Feature extraction of natural objects is still a very difficult task with todays image processing techniques. High resolution aerial or satellite data can be acquired with reasonable effort, but accuracy and correctness of available extraction methods are lagging behind. Instead of propagating the ultimate segmentation algorithm, a hypothesis-based approach is presented, which tries to combine established and new image processing methods with each other. Similar to the varimax criteria of principal component analysis, extraction methods should be as independent as possible from each other.
 

Boile, M. P., (1998). Intermodal transportation network analysis-a GIS application. Proceedings of 10th Mediterranean Electrotechnical Conference - MELECON 2000 Lemesos, Cyprus 29-31 May 2000
Piscataway, NJ, USA IEEE, pp.660-3 vol.2.
Keywords: Geographic information systems; Planning; Rail traffic; Transportation; Intermodal transportation network analysis; GIS application; Integrated transportation system; Network equilibrium models; Transportation planning; Future network activity; Traffic volumes; Travel costs; Intermodal network representation; Geographic information system; Spatial data format; Road network ; Transit network
Original abstract: A framework is presented which may be used to analyze and evaluate intermodal networks. An intermodal network may be defined as an integrated transportation system consisting of two or more modes. Modes on intermodal networks are connected through facilities which allow travelers and/or freight to transfer from one mode to another during a trip from an origin to a destination. Network equilibrium models may be used in the transportation planning field to make predictions regarding future network activity in terms of traffic volumes and travel costs, to evaluate alternative policies and to aid the decision making process in terms of future transportation plans. To expedite and facilitate the effort of detailed intermodal network representation and analysis, a network equilibrium model is interfaced with a geographic information system (GIS). This interface takes advantage of new technologies and sources of information on the physical components of the network. It allows the user to store the results of the proposed models in a GIS environment and display them in a spatial data format.
 

Bolter, R.; F. Leberl, (2000). Detection and reconstruction of buildings from multiple view interferometric SAR data. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.749-51 vol.2.
Keywords: InSAR data feature extraction, Interferometric SAR, Airborne single pass IFSAR
Synopsis: The authors combine multiple views and multiple data sources from INSAR sensors to extract buildings and other features with height from other features in a dataset. Method works well except when a building intersects the "shadow region" of another building.
Original abstract: Geometric reconstruction of human scale features gets feasible from airborne single pass IFSAR sensors. IFSAR data is corrupted by blur, speckle noise, and other view dependent effects as e.g., layover and shadows. Especially in case of buildings, those phenomenological features may also provide valuable information about the underlying structure. Combining multiple views and multiple data types of the same scene the exploitation of this information gets feasible. The authors use information from the interferometric height and coherence data to separate regions containing buildings from other objects in the scene. Shadow information from magnitude images is then used to delimit the exact boundaries of the buildings further. Rectangles are fit to the selected points and compared to ground truth measurements manually derived from optical images.
 

Borak, J. S.; A. H. Strahler, (1996). Feature selection using decision trees-an application for the MODIS land cover algorithm. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) IGARSS Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.243-5 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Remote sensing; Geophysical measurement technique; Land surface; Terrain mapping; Feature selection; Decision trees; Decision tree; MODIS land cover algorithm; Optical imaging; Visible; ir; Global-scale land cover map; Classifier ; Proportional sampling strategy
Original abstract: One of the key issues involved in generating global-scale land cover maps from remote sensing data is the discarding of useless or redundant information. The decision tree offers a promising approach to extraction of meaningful features from large measurement spaces. This research examines the performance of several classifiers on subsets of features produced via decision trees.
 

Borges, K. A. d.; S. Sahay (2000). GIS for the public sector: experiences from the city of Belo Horizonte, Brazil. Information Infrastructure and Policy, 6, (3): 139-55.
Keywords: Geographic information systems; Public administration; Town and country planning; Traffic information systems; Transportation; Public sector GIS; Belo Horizonte; Brazil; Brazilian municipal administration; Urban geographic information system; Local government tradition; Education; Health; Sanitation; Urban planning; Traffic; Technology acquisition; Team formation phases; Geographic database; GIS technology usage; GIS implementation; India; Future GIS projects ; Developing countries
Original Abstract: Belo Horizonte was one of the first Brazilian municipal administrations to develop an urban geographic information system. Situated within the local government tradition of local government, the development and implementation of the geographic information system (GIS) commenced in 1989 and has proceeded significantly to the extent that it has become the most complete experience of its kind throughout Brazil, with applications covering areas such as education, health, sanitation, urban planning, transportation and traffic, among others. The article reflects on the experiences of this GIS project, from the technology acquisition and team formation phases, through the creation of the geographic database, to the development of applications and dissemination among users. Current perspectives for the continuing expansion of GIS technology usage in Belo Horizonte are also presented. This "successful" experience of GIS implementation is contrasted with some GIS projects in India to highlight probable areas of emphasis in future GIS projects in developing countries.
 

Boryssenko, A.; V. I. Polishchuk, (1999). Earth near-surface passive probing by natural pulsed electromagnetic field. 1999 International Conference on Computational Electromagnetics and its Applications. Proceedings (ICCEA'99) (IEEE Cat. No.99EX374) Beijing, China 1-4 Nov. 1999
Beijing, China Publising House of Electron. Ind, pp.529-32.
Keywords: Buried object detection; Remote sensing; Signal processing; Statistical analysis; Transient analysis; Earth near-surface passive probing; Natural pulsed electromagnetic field; Subsurface hidden objects; Statistical variations; Statistical signal processing technique; Subsurface pipelines; Cables; Hidden objects; Archeological objects; Passive probing technique ; Urban conditions
Original abstract: The results of experimental studies to detect and locate subsurface hidden objects by near-surface determination of statistical variations of the natural pulsed electromagnetic background field in the 0.1-50 kHz frequency range are presented. There are possibilities of passive electromagnetic probing by use of the necessary electronic equipment and statistical signal processing technique described. Some field results to locate subsurface pipelines and cables and other hidden objects including archeological ones are shown. The perspectives of this passive probing technique for variety of applications in urban conditions are discussed.
 

Boudreau, E.; R. Huguenin; M. Karaska, (1996). Nonparametric classification of subpixel materials in multispectral imagery. Algorithms for Multispectral and Hyperspectral Imagery II Orlando, FL, USA 9-11 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.31-9.
Keywords: Agriculture; Feature extraction; Forestry; Image classification; Nonparametric statistics; Remote sensing; Spectral analysis; Nonparametric classification; Subpixel materials; Multispectral imagery; Applied analysis spectral analytical process; aasap; Materials of interest; Environmental correction; Signature derivation; Subpixel classification; Factor extraction; Training set; Background estimation; Loblolly pine; Landsat TM scene; Crop signature; Soil contamination; Wetlands species ; Lines of communication
Original abstract: An effective process for the automatic classification of subpixel materials in multispectral imagery has been developed. The applied analysis spectral analytical process (AASAP) isolates the contribution of specific materials of interest (MOI) within mixed pixels. AASAP consists of a suite of algorithms that perform environmental correction, signature derivation, and subpixel classification. Atmospheric and sun angle correction factors are extracted directly from imagery, allowing signatures produced from a given image to be applied to other images. AASAP signature derivation extracts a component of the pixel spectra that is most common to the training set to produce a signature spectrum and nonparametric feature space. The subpixel classifier applies a background estimation technique to a given pixel under test to produce a residual. A detection occurs when the residual falls within the signature feature space. AASAP was employed to detect stands of Loblolly pine in a Landsat TM scene that contained a variety of species of southern yellow pine. An independent field evaluation indicated that 85% of the detections contained over 20% Loblolly, and that 91% of the known Loblolly stands were detected. For another application, a crop signature derived from a scene in Texas detected occurrences of the same crop in scenes from Kansas and Mexico. AASAP has also been used to locate subpixel occurrences of soil contamination, wetlands species, and lines of communication.
 

Brecher, A.
Transportation Strategic Planning and Analysis Office
DOT/RSPA Volpe National Transportation Systems Center
55 Broadway, Cambridge, MA 02142
brecher@volpe.dot.gov
Summary of the DOT National Forum on Remote Sensing Applications to Transportation
TS&T
http://scitech.dot.gov/reeng/sensmsrm/rmtsense/sbrsfsum.html
 
 

Brown, D. E.; J. Marin, (1995). Learning vector quantization for road extraction from digital imagery. 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century (Cat. No.95CH3576-7) Vancouver, BC, Canada 22-25 Oct. 1995
New York, NY, USA IEEE, pp.1478-81 vol.2.
Keywords: Feature extraction; Image recognition; Remote sensing; Vector quantisation; Learning vector quantization; Road extraction; Digital imagery; Topographic information; Satellite imagery; Topographic feature data; Road networks ; SPOT imagery
Original abstract: Many operations require the most accurate and complete topographic information available. Typically map products cannot maintain currency because of the rapid pace of development. Hence, there is an urgent requirement to exploit satellite imagery to provide current topographic feature data. Among the most important features needed are roads and, hence we require automated procedures to rapidly identify road networks in imagery. This paper describes the use of learning vector quantization to extract roads from digital imagery. We provide results using data from SPOT imagery.
 

Bruce, L. M.; L. Jiang, (1999). Fast wavelet-based algorithms for multiresolutional decomposition and feature extraction of hyperspectral signatures. Algorithms for Multispectral and Hyperspectral Imagery V Orlando, FL, USA 5-6 April 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.72-81.
Keywords: Computational complexity; Feature extraction; Geophysical signal processing; Image recognition; Image resolution; Remote sensing; Wavelet transforms; Fast wavelet-based algorithms; Multiresolutional decomposition; Hyperspectral signatures; Wavelet-based spectral fingerprint; Wavelet transform modulus-maximus method; Computational expense ; Computational costs
Original abstract: Spectral features are often extracted from multispectral/hyperspectral data using a multiresolutional decomposition known as the spectral fingerprint. While the spectral fingerprint method has proven to be quite powerful, it has also shown several shortcomings: (1) its implementation requires multiple convolutions with Laplacian-of-Gaussian filters which are computationally expensive, (2) it requires a truncation of the filter impulse response which can cause spurious errors, and (3) it provides information about the sizes and areas of radiance features but not the shapes. It is proposed that a wavelet-based spectral fingerprint can overcome these shortcomings while maintaining the advantages of the traditional method. In this study, we investigate the use of the wavelet transform modulus-maximus method to generate a wavelet-based spectral fingerprint. The computation of the wavelet-based fingerprint is based on fast wavelet algorithms. The analysis consists of two parts: (1) the computational expense of the new method is compared with the computational costs of current methods, and (2) the outputs of the wavelet-based methods are compared with those of current methods to determine any practical differences in the resulting spectral fingerprints.
 

Bruce, L. M.; J. Li, (1999). Enhancing hyperspectral data throughput utilizing wavelet-based fingerprints. Image and Signal Processing for Remote Sensing V Florence, Italy 22-24 Sept. 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.218-27.
Keywords: Feature extraction; Geophysical signal processing; Image enhancement; Image recognition; Remote sensing; Wavelet transforms; Hyperspectral data throughput; Wavelet-based fingerprints; Multiresolution decompositions; Spectral fingerprints; Spectral features; Multispectral hyperspectral data; Wavelet-based algorithms; Computational expense; Computational costs; Hyperspectral Digital Image Collection Experiment; HYDICE signature ; Average Euclidean distance
Original abstract: Multiresolution decompositions known as spectral fingerprints are often used to extract spectral features from multispectral hyperspectral data. In this study, we investigate the use of wavelet-based algorithms for generating spectral fingerprints. The wavelet-based algorithms are compared to the currently used method, traditional convolution with first-derivative Gaussian filters. The comparison analyses consists of two parts: (a) the computational expense of the new method is compared with the computational costs of the current method and (b) the outputs of the wavelet-based methods are compared with those of the current method to determine any practical differences in the resulting spectral fingerprints. The results show that the wavelet-based algorithms can greatly reduce the computational expense of generating spectral fingerprints, while practically no differences exist in the resulting fingerprints. The analysis is conducted on a database of hyperspectral signatures, namely, Hyperspectral Digital Image Collection Experiment (HYDICE) signatures. The reduction in computational expense is by a factor of about 30, and the average Euclidean distance between resulting fingerprints is on the order of 0.02.
 

Brumbley, C.; I. C. Chein, (1998). Unsupervised linear unmixing Kalman filtering approach to signature extraction and estimation for remotely sensed imagery. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174) Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.1590-2 vol.3.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Kalman filters; Remote sensing; Geophysical measurement technique; Land surface; Terrain mapping; Image processing; Unsupervised linear unmixing Kalman filtering; Signature extraction; Signature matrix; Linear mixture model; Unsupervised learning ; Clustering algorithm
Original abstract: Linear Unmixing Kalman Filtering (LUKF) approach was recently developed which incorporates the concept of linear unmixing into Kalman filtering so as to achieve signature abundance estimation, subpixel detection and classification for remotely sensed images. However, LUKF assumes a complete knowledge of the signature matrix used in the linear mixture model. In this paper, the LUKF is extended to an unsupervised LUKF where no knowledge about the signature matrix is required a priori. The unsupervised learning method proposed for the ULUKF is derived from a vector quantization-based clustering algorithm. It employs a nearest-neighbor rule to group potential signatures resident within an image scene into a class of distinct clusters whose centers represent different types of signatures. These clusters' centers are then used as if they were true signatures in the signature matrix LUKF. In order to evaluate the effectiveness of ULUKF, HYDICE images were used for assessment. The results produced by ULUKF show that subpixel detection and classification can be performed.
 

Brumby, S. P.; N. R. Harvey; S. J. Perkins; R. B. Porter; J. J. Szymanski; J. Theiler; J. J. Bloch, (2000). Genetic algorithm for combining new and existing image processing tools for multispectral imagery. Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VI Orlando, FL, USA 24-26 April 2000
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.480-90.
Keywords: Feature extraction; Genetic algorithms; Image processing; Remote sensing; Genetic algorithm; Multispectral imagery; Image processing tools; Image processing algorithms; Chromosomal representation ; Geospatial feature extraction
Original abstract: We describe the implementation and performance of a genetic algorithm (GA) which evolves and combines image processing tools for multispectral imagery (MSI) datasets. Existing algorithms for particular features can also be "re-tuned" and combined with the newly evolved image processing tools to rapidly produce customized feature extraction tools. First results from our software system were presented previously. We now report on work extending our system to look for a range of broad-area features in MSI datasets. These features demand an integrated spatio-spectral approach, which our system is designed to use. We describe our chromosomal representation of candidate image processing algorithms, and discuss our set of image operators. Our application has been geospatial feature extraction using publicly available MSI and hyper-spectral imagery (HSI). We demonstrate our system on NASA/Jet Propulsion Laboratory's Airborne Visible and Infrared Imaging Spectrometer (AVIRIS) HSI which has been processed to simulate MSI data from the Department of Energy's Multispectral Thermal Imager (MTI) instrument. We exhibit some of our evolved algorithms, and discuss their operation and performance.
 

Brunzell, H., (1997). Extraction of discriminant features from impulse radar data for classification of buried objects. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042)Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.1285-7 vol.3.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Military systems; Pattern classification; Radar detection; Radar imaging; Radar signal processing; Terrestrial electricity; Geophysical measurement technique; Ground penetrating radar; Military system; Mine detection; Mine detector; Buried object detection; Explosive mine; Radar remote sensing; Discriminant feature; Impulse radar; Buried landmine; Plastic mine; Ceramic mine; Nonmetallic object ; Large bandwidth
Original abstract: This paper deals with the problem of detecting and classifying buried objects. The application in mind when addressing this problem is the detection of buried landmines. Modern landmines are to a large extent made out of plastic and ceramic materials. This makes detection with traditional sensors such as metal detectors and magnetometers almost impossible. Another problem with these sensors is the high false alarm rate induced by metallic debris from exploded bomb shells. A sensor type that seems to have capability to overcome these problems is the impulse radar. The impulse radar can detect nonmetallic objects buried in the ground. The large bandwidth of the radar also gives additional information that can be used for classification purposes. The classification abilities enable discrimination between mines and stones and metallic debris, thus reducing the false alarm rate. An important step towards good classification results is to extract a set of features from measured data. The present paper elaborates on properties that an admissible feature type must possess and shows that the choice of features should be related both to the type of measurements and the type of classifier used. A number of different feature types are finally evaluated using measured data from an impulse radar system.
 

Bruzzone, L. (2000). An approach to feature selection and classification of remote sensing images based on the Bayes rule for minimum cost. IEEE Transactions on Geoscience and Remote Sensing, 38, (1, pt.2): 429-38.
Keywords: Bayes methods; Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Optical imaging; Image processing; Feature selection; Minimum cost; Bayes method; Minimizing; Overall error; Land-cover ; Bayes rule for minimum cost
Original Abstract: Classification of remote-sensing images is usually carried out by using approaches aimed at minimizing the overall error affecting land-cover maps. However, in several remote-sensing problems, it could be useful to perform classification by taking into account the different consequences (and hence the different costs) associated with each kind of error. This allows one to obtain land-cover maps in which the total classification cost involved by errors is minimized, instead of the overall classification error. To this end an approach to feature selection and classification of remote-sensing images based on the Bayes rule for minimum cost (BRMC) is proposed. In particular a feature-selection criterion function is presented that permits one to select the features to be given as input to a classifier by taking into account the different cost associated with each confused pair of land-cover classes. Moreover, a classification technique based on the BRMC and implemented by using a neural network is described. The results of experiments carried out on a multisource data set concerning the Island of Elba (Italy) point out the ability of the proposed minimum cost approach to produce land-cover maps in which the consequences of each kind of error are considered.
 

Bruzzone, L., (1998). Classification of remote-sensing images by using the Bayes rule for minimum cost. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174)Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.1778-80 vol.4.
Keywords: Bayes methods; Geophysical signal processing; Geophysical techniques; Image classification; Minimisation; Remote sensing; Geophysical measurement technique; Land surface; Terrain mapping; Bayes rule; Minimum cost; Minimization; Bayesian method; Feature selection; Feature extraction; Land-cover map ; Minimum cost approach
Original abstract: An approach based on the Bayes rule for minimum cost for feature selection and classification of remote-sensing images is proposed. This approach allows one to achieve land-cover maps in which the total cost involved by errors, instead of the total classification error, is minimized. Experiments carried out on a multisource data set of the Island of Elba (Italy) point out the effectiveness of the proposed minimum cost approach.
 

Bruzzone, L.; D. F. Prieto; G. Silvano, (1999). Extraction and selection of robust features for classification of multispectral remote-sensing images. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293) Hamburg, Germany 28 June-2 July 1999
Piscataway, NJ, USA IEEE, pp.119-21 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Image classification; Remote sensing; Extraction; Selection; Robust features; Classification; Multispectral remote-sensing images; Land-cover; Invariant behavior ; Acquisition conditions
Original abstract: In this paper, we present an approach to the extraction and selection of robust features for classification of multispectral remote-sensing images. In particular, several robust features are proposed that, given a specific land-cover class, aim to exhibit an invariant behavior versus variations in the acquisition conditions of the images considered. In addition, a technique is presented, which is able to adaptively select the most robust features for a given problem.
 

Bruzzone, L.; F. Roli; S. B. Serpico (1995). An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection. IEEE Transactions on Geoscience and Remote Sensing, 33, (6): 1318-21.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Optical information processing; Remote sensing; Geophysical measurement technique; Optical imaging; Visible; Land surface; Terrain mapping; Jeffreys-Matusita distance; Multiclass case; Feature selection; Image processing; Bhattacharyya ; Multispectral imaging
Original Abstract: The problem of extending the Jeffreys-Matusita distance to multiclass cases for feature-selection purposes is addressed and a solution equivalent to the Bhattacharyya bound is presented. This extension is compared with the widely used weighted average Jeffreys-Matusita distance both by examining the respective formulae and by experimenting on an optical remote-sensing data set.
 

Bruzzone, L.; S. B. Serpico, (1998). A new search algorithm for feature selection in high-dimensional remote-sensing images. Image and Signal Processing for Remote Sensing IV Barcelona, Spain 21-23 Sept. 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.34-41.
Keywords: Feature extraction; Geophysical signal processing; Remote sensing; Search problems; Search algorithm; Feature selection; High-dimensional remote-sensing images; Sub-optimal search strategy; Hyperspectral sensors; Constrained local extremes; Discrete binary space; Computational cost ; AVIRIS sensor
Original abstract: A new sub-optimal search strategy suitable for feature selection in high-dimensional remote-sensing images (e.g. images acquired by hyperspectral sensors) is proposed. Such a strategy is based on a search for constrained local extremes in a discrete binary space. In particular, two different algorithms are presented that achieve a different trade-off between effectiveness of selected features and computational cost. The proposed algorithms are compared with the classical sequential forward selection (SFS) and sequential forward floating selection (SFFS) sub-optimal techniques: the first one is a simple but widely used technique; the second one is considered to be very effective for high-dimensional problems. Hyperspectral remote-sensing images acquired by the AVIRIS sensor are used for such comparisons. Experimental results point out the effectiveness of the presented algorithms.
 

Buckley, M.; J. Yang (1997). Regularised shortest-path extraction. Pattern Recognition Letters, 18, (7): 621-9.
Keywords: Computer vision; Dynamic programming; Edge detection; Feature extraction; Object recognition; Remote sensing; Shortest-path extraction; Active contours; Time-delayed dynamic programming; Discretization; Pixel subdivision; Fracture detection; Borehole images; Road detection; Satellite images ; Regularization
Original Abstract: Regularization of shortest-paths and active contours has been considered and attempted by a number of workers. However, it was not until the development of the "time-delayed dynamic programming" algorithm of Amini et al. (1990) in the active contours context that a method was found which was able to apply a simple and intuitive smoothness constraint with an efficient computational scheme. We show that, when applied to the shortest-path problem, this technique, gives rise to a simple and efficient algorithm. However, we find that the method is not practically useful in some situations because of discretization effects. A modification using pixel subdivision is proposed, which to a large extent overcomes this problem. The modified method is illustrated using two examples: fracture detection in borehole images and road detection in satellite images.
 

Bullock, M. E.; S. R. Fairchild; T. J. Patterson; R. Haxton, (1996). Automated map generation and update from high-resolution multispectral imagery. Algorithms for Multispectral and Hyperspectral Imagery II Orlando, FL, USA 9-11 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.91-103.
Keywords: Cartography; Feature extraction; Geographic information systems; Image resolution; Remote sensing; Automated map generation; High-resolution multispectral imagery; LOCATE TNG system; Lines of communication; Landsat thematic mapper imagery; GIS applications; 30 m; 4 m ; 1 m
Original abstract: This paper describes the LOCATE TNG system, which generates map products directly from multispectral imagery in an automated fashion. The LOCATE TNG system uses spectral and spatial feature information to extract various types of man-made lines of communication (LOCs) from imagery and generate them in the form of digital vector maps. The generated maps may be compared against reference digital maps to automatically find new or changed LOCs. The original LOCATE (lines of communication apparent from thematic mapper evidence) system was designed and developed to use Landsat thematic mapper imagery having a resolution of 30 m. LOCATE TNG (the next generation) has been redesigned to also have the capability to use high-resolution multispectral imagery to be available from the next generation of commercial satellites. These satellites will provide multispectral and panchromatic imagery having resolutions down to 4 m and 1 m, respectively, thus dramatically improving the information available for exploitation. LOCATE TNG employs a hierarchical algorithmic approach to extracting layers of LOCs (primary roads, secondary roads, etc.) that may be used for GIS applications.
 

Burkhart, G. R.; Z. Bergen; R. Carande; W. Hensley; D. Bickel; J. R. Fellerhoff, (1996). Elevation correction and building extraction from interferometric SAR imagery. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.659-61 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image enhancement; Radar imaging; Radar target recognition; Remote sensing by radar; Synthetic aperture radar; Geophysical measurement technique; Land surface; Terrain mapping; Radar remote sensing; Urban area; Town; City; Building; Elevation correction; Interferometric SAR imagery; ifsar; High resolution; Man made structure; Industrial area; Tree; Forest; Vegetation mapping ; Artifact removal
Original abstract: The development of high (2m) resolution interferometric SAR (IFSAR) instrumentation makes extraction of man made and natural urban structures feasible. In particular, the authors consider building extraction from imagery of an urban/industrial area. IFSAR imagery are particularly well suited for this task because these data include the measured elevation as well as the coherence and intensity of the back scattered radiation. Gradients in the IFSAR elevation correspond directly to elevation edges. Coherence and intensity data can be combined to give specific information about the scattering properties of the viewed surface. The disadvantage of IFSAR imagery is that these data are typically of lower resolution and contain greater noise than other data such as optical photography, also the data contain specific artifacts that must be removed. Indeed, the motivation for building and tree extraction behind this work is the need to remove noise and artifacts from the IFSAR data. Techniques for removing artifacts that are peculiar to IFSAR data are particularly discussed.
 

Butler, J. A., (1995). A comprehensive GIS-T enterprise database design. GIS/LIS *95 Annual Conference and Exposition Proceedings of Geographic Information Systems/Land Information Systems Nashville, TN, USA 14-16 Nov. 1995
Bethesda, MD, USA American Soc. Photogrammetry & Remote Sensing & American Congress on Surveying & Mapping, pp.137-46 vol.1.
Keywords: Electronic data interchange; Geographic information systems; Government data processing; Public administration; Software standards; Systems analysis; Transportation; Visual databases; GIS-T database design; Enterprise database design; Business processes; State department of transportation; Locationally referenced data; One-dimensional linear referencing method; Information engineering principles; Multimodal agency; Spatial Data Transfer Standard; sdts; Data exchange ; Geographic information system
Original abstract: While business processes differ between state departments of transportation (DOTs), the data which they use are relatively consistent. This paper proposes an enterprise GIS-T database design that can be generally applied by all state DOTs and other agencies working with transportation data which are locationally referenced. Of particular importance is the design*s ability to work with data that utilize a one-dimensional linear referencing method, and the correlation of that method to other locating systems. The database design was developed by applying information engineering principles to the needs of a multi-modal agency. This work builds on that of the GIS-T/ISTEA Pooled-fund Study and NCHRP 20-27. It is based on the federal Spatial Data Transfer Standard (SDTS), so it also serves to illustrate how agencies could use that standard for data exchange. A set of implementation choices is used to bring out details of the database design.
 

Caelli, T.; A. McCabe; G. Briscoe (2001). Shape tracking and production using hidden Markov models. International Journal of Pattern Recognition and Artificial Intelligence, 15, (1): 197-221.
Keywords: Cartography; Edge detection; Feature extraction; Hidden Markov models; Image sequences; Maximum likelihood estimation; Pattern classification; Probability; Remote sensing; Shape classification; Probability distribution; Viterbi method; Search problem; Hamming distance; Symbol sequences; Scene understanding ; Competitive unsupervised learning
Original Abstract: This paper deals with an application of hidden Markov models (HMMs) to the generation of shape boundaries from image features. In the proposed model, shape classes are defined by sequences of "shape states" each of which has a probability distribution of expected image feature types (feature "symbols"). The tracking procedure uses a generalization of the well-known Viterbi method by replacing its search by a type of "beam-search" so allowing the procedure, at any time, to consider less likely features (symbols) as well the search for an optimal state sequences. We evaluated the model performance on a variety of image and shape types, and developed a new performance measure defined by an expected Hamming distance between predicted and observed symbol sequences. Results point to the use of this type of model for the depiction of shape boundaries when it is necessary to have accurate boundary annotations as, for example, occurs in cartography.
 

Caetano, M.; J. Santos; A. Navarro, (1997). A multi-strategic approach for land use mapping of urban areas by integrating satellite and ancillary data. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042)Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.240-2 vol.1.
Keywords: Geophysical signal processing; Geophysical techniques; Image classification; Remote sensing; Geophysical measurement technique; Land surface; Town; City; Urban area; Land use; Multi-strategic approach; Mapping; Satellite remote sensing; Ancillary data; Method; Satellite imagery; Road network; Census data; Contextual operators; Population; Habitation; Land use class; Grande Lisboa; Lisbon ; Portugal
Original abstract: A methodology for land use mapping of urban areas by using satellite imagery and ancillary data (road network and census data) was developed. The integration of ancillary data was sequentially done to allow a cost/benefit analysis. In the analysis of the satellite imagery, special emphasis was put in the development of contextual operators for (1) discriminating pixels that have different land uses but have similar spectral characteristics, and (2) identifying land use classes that cannot be identified at a pixel level. A road network map was integrated with the satellite imagery for stratifying the study area into urban and rural areas. This stratification allowed the application of different algorithms to each stratum for an effective improvement of the land use mapping accuracy. In addition, population and habitation census data were used for a refinement of land use classes discrimination. The methodology was tested with a SPOT image to generate a map with the CLUSTERS nomenclature for the Area da Grande Lisboa, Portugal. In the final map, 22 land use classes were identified with an overall accuracy of 88% (Kappa index). Most of these 22 classes were identified with user's and producer's accuracy larger than 85%.
 

Cai, T.; R.-S. Wang (2001). Am algorithm for extracting road network from multi-band remote sensing images. Journal of Software, 12, (6): 943-8.
Keywords: Feature extraction; Remote sensing; Sensor fusion; Transportation; Road network; Remote sensing images; Multiband images ; Image recognition
Original Abstract: An algorithm for extracting road network by fusion from multi-band remote sensing images is presented. First, straight lines and parallel lines are extracted from multi-band images and fused in order to overcome the uncertainty of the description of roads in the images. Next, the roads that fit well with the constraints of the model of road are recognized according to the local property of lines. Finally, the roads that can not be fit well with the constraints of the model of road are recognized by using the global connection constraints of road network. The algorithm is applied on 3-band remote sensing images, and the effectiveness is shown by the results.
 

Camiciottoli, R.; J. M. Corrifoni; A. D. Bimbo; E. Vicario; D. Lucarella (1998). 3D navigation of geographic data sets. IEEE Multimedia, 5, (2): 29-41.
Keywords: Colour graphics; Data visualisation; Geographic information systems; Transportation; User interfaces; Very large databases; 3D navigation; Three dimensional navigation; Geographic data sets; Wide area transportation networks; Large data sets; Continuous monitoring; Network links; Data types; Visualization environment; Multiple presentation modes; 3D graphics; Color; Windowing ; Three dimensional graphics
Original Abstract: Supervision and control of wide area transportation networks requires continuous monitoring of large data sets. Two factors complicate the process: data items are spread over a wide geographic area, but are reciprocally influenced through network links, and data types attached to network nodes belong to different categories. We describe a visualization environment that tests the joint use of multiple presentation modes, such as 3D graphics, color, and windowing, to address both factors.
 

Campbell, M. V.; K. R. Slocum; J. F. Moeller, (1996). Efficient extraction of vegetation attributes from high-resolution multispectral imagery. Proceedings of Eco-Informa '96. Global Networks for Environmental Information Proceedings of Meeting on Global Networks for Environmental Information: Bridging the Gap Between Knowledge and Application Lake Buena Vista, FL, USA 4-7 Nov. 1996
Ann Arbor, MI, USA Environ. Res. Inst. Michigan, pp.387-92 vol.1.
Keywords: Data acquisition; Feature extraction; Forestry; Geographic information systems; Image resolution; Interpolation; Remote sensing; Spectral analysis; Statistical analysis; Vegetation attributes; High-resolution multispectral imagery; Airborne video imagery; Forest; Georgia; Geostatistical analyses; Field data collection; Accuracy assessment; Image interpretation; gis; Stem spacing; Percent canopy closure; Species composition; Isopleth maps; Surface interpolation; Sample size allocation ; Image spectral variability
Original abstract: A technique is described for extracting vegetation attributes from high-spatial-resolution airborne multispectral video imagery acquired over a forested study site in west-central Georgia. Geostatistical analyses were used to allocate a systematic sample of the imagery and to collect field data for accuracy assessment. Image interpretation and GIS procedures produced estimates of stem spacing, percent canopy closure, and species composition within sample plots. Isopleth maps for each attribute were created using surface interpolation. Image interpretation results exhibited moderate to poor accuracy when compared to the ground truth data. The surface interpolation procedures created only moderately accurate isopleth maps for each of the forest attributes. Potential sources of error include: inadequate sample size allocation, image spectral variability associated with date of acquisition, and inappropriate surface interpolation algorithms. Possible solutions and future research areas are presented.
 

Cao, W.; Q. Qin (1998). A knowledge-based research for road extraction from digital satellite images. Acta Scientiarum Naturalium Universitatis Pekinensis, 34, (2-3): 254-63.
Keywords: Feature extraction; Geographic information systems; Image recognition; Knowledge based systems; Object recognition; Remote sensing; Road extraction; Digital satellite images; Satellite image recognition; Geographical databases; Road properties; Image processing; Artificial intelligence; Road detection; Shape index; Possible road points; Contextual information; Road segment; Knowledge-based rules; SPOT data; Expert system ; Geographical information system
Original Abstract: As basic geographical information, road extraction from satellite images is important in the practice and theory of automatic satellite image recognition, and its results can be used for updating geographical databases. Using existing approaches to automatic road extraction from satellite images for reference and considering the road properties in China, this paper presents a new road extraction method that combines image processing techniques with an artificial intelligence methodology. In this approach, an operator is applied to an image to enhance the road information, then road detection based on the shape index and other a priori knowledge is performed to find possible road points. After using more contextual information or global constraints to extend the road seeds to form road segments, the existence of a road is inferred and the gap between the road segments is connected by employing knowledge-based rules. Finally, experimental results on SPOT data are shown.
 

Caorsi, S.; P. Gamba, (1998). Neural network approach for electromagnetic inverse scattering solution. International Symposium on Electromagnetic Theory. Proceedings of 1998 International Symposium on Electromagnetic Theory (Commission B Triennial Open Symposium) Thessaloniki, Greece 25-28 May 1998, pp.524-6 vol.2.
Keywords: Backscatter; Electrical engineering computing; Electromagnetic wave scattering; Inverse problems; Multilayer perceptrons; Permittivity; Remote sensing; Neural network approach; Electromagnetic inverse scattering; Three layer perceptron; Backscattered electromagnetic field; Geometric characteristics; Electrical characteristics; Cylindrical object; Input measurements; Dielectric permittivity; Cylinder radius ; Cylinder location
Original abstract: This paper is devoted to develop a neural approach to the electromagnetic inverse scattering problem. In particular a three layer perceptron is used to retrieve from the backscattered electromagnetic field values the geometric and electrical characteristics of a cylindrical object buried inside a given investigation domain. The number of input measurements, as well as the network structure are investigated. We show that the dielectric permittivity, location and radius of the cylinder can be reliably computed from these inputs very quickly, allowing the use of this approach in real-time remote sensing applications.
 

Carande, R. E.; M. Marra; D. Cronin; P. Nagy, (1998). Automated mapping using airborne IFSAR data. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174) Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.360-2 vol.1.
Keywords: Airborne radar; Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Topography (Earth); Geophysical measurement technique; Land surface; Terrain mapping; Radar remote sensing; Automated mapping; Airborne IFSAR; sar; Two-antenna interferometric SAR; Elevation; Topography; Topographic map; Geometric rectification; Automatic map projection; Interferometric coherence; Land-use classification; Feature detection; Algorithm ; Interferometric SAR
Original abstract: Two-antenna interferometric SAR instruments acquire SAR data in such a manner that the signals may be combined and processed to extract the elevation of each pixel. In addition to providing a high resolution topographic map of the area, this allows for geometric rectification and automatic map projection of the SAR image. The interferometric coherence may be used to assist in land-use classification which can further exploited for assisting in automated feature detection and extraction. This paper describes and demonstrates algorithms suitable for automatic generation of map products from Interferometric SAR data.
 

Carlotto, M. J., (1996). Detecting man-made features in SAR imagery. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.34-6 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image matching; Image segmentation; Radar imaging; Radar signal processing; Remote sensing by radar; Synthetic aperture radar; Weibull distribution; Geophysical measurement technique; Radar remote sensing; Land surface; Terrain mapping; Urban area; Buildings; Man-made feature; SAR imagery; Local histogram; Weibull density; Median; Skewness ; Image region analysis
Original abstract: A method for detecting man-made features in synthetic aperture radar (SAR) imagery is described. The method is based on matching the local histogram against a family of Weibull densities. The Weibull density is defined by two parameters, the median and the skewness (Weibull parameter). Regions containing man-made objects have Weibull parameter values that are smaller than those containing natural features. In experiments performed with aircraft SAR imagery, man-made features are effectively discriminated from natural features using this method.
 

Carlotto, M. J., (1996). Nonlinear mean-square estimation with applications in remote sensing. Algorithms for Multispectral and Hyperspectral Imagery II Orlando, FL, USA 9-11 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.206-17.
Original abstract: An approach to image modeling based on nonlinear mean-square estimation that does not assume a functional form for the model is described. The relationship between input and output images is represented in the form of a lookup table that can be efficiently computed from, and applied to images. Three applications are presented to illustrate the utility of the technique in remote sensing. The first illustrates how the method can be used to estimate the values of physical parameters from imagery. Specifically we estimate the topographic component (i.e., the variation in brightness caused by the shape of the surface) from multispectral imagery. The second application is a nonlinear change detection algorithm which predicts one image as a nonlinear function of another. In cases where the frequency of change is large (e.g., due to atmospheric and environmental differences), the algorithm is shown to be superior in performance to linear change detection. In the last application, a technique for removing wavelength-dependent space-varying haze from multispectral imagery is presented. The technique uses the IR bands, which are not affected significantly by haze, to predict the visible bands. Results show a significant reduction in haze over the area considered. Additional application areas are also discussed.
 

Carlotto, M. J., (1996). Using maps to automate the classification of remotely-sensed imagery. Algorithms for Multispectral and Hyperspectral Imagery II Orlando, FL, USA 9-11 April 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.40-50.
Original abstract: The accurate classification of remotely-sensed imagery usually requires some form of ground truth data. Maps are potentially a valuable source of ground truth but have several problems (e.g., they are usually out-dated, features are generalized, and thematic categories in the map often do not correspond to distinct clusters or segments in the imagery). We describe several methods for using maps to automate the classification of remotely-sensed data, specifically Landsat Thematic Mapper imagery. In each, map data are coregistered to all or a part of the image to be classified. A probability model relating spectral clusters derived from the imagery to thematic categories contained in the map is then estimated. This model is computed globally and adjusted locally based on context. By computing the probability model over a large area (e.g., the full Landsat scene) general relationships between spectral categories and clusters are captured even though there are differences between the image and the map. Then, by adjusting and applying the model locally, new features can be extracted from the image that are not contained in the map and, in certain cases, different classes can be assigned to the same cluster in different parts of the image based on context. Experimental results are presented for several Landsat scenes. Several of the methods produced results that were more accurate than the map. We show that these methods are able to enhance the spatial detail of features contained in the map, identify new features not present in the map, and fill in areas in which map coverage does not exist.
 

Carr, J. R.; K. Matanawi (1999). Correspondence analysis for principal components transformation of multispectral and hyperspectral digital images. Photogrammetric Engineering and Remote Sensing, V65, (N8): 909-914.
Keywords: Optics/Acoustics
 
 

Carrere, V.; J. E. Conel (1993). Recovery of Atmospheric Water Vapor Total Column Abundance from Imaging Spectrometer Data around 940 Nm - Sensitivity Analysis and Application to Airborne Visible Infrared Imaging Spectrometer (Aviris) Data. Remote Sensing of Environment, V44, (N2-3): 179-204.
Keywords:
 
 

Cazzaniga, G.; A. Monti Guarnieri, (1996). Removing RF interferences from P-band airplane SAR data. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.1845-7 vol.3.
Keywords: Geophysical signal processing; Geophysical techniques; Interference; Interference (signal); Interference filters; Notch filters; Radar imaging; Radar interference; Remote sensing by radar; Synthetic aperture radar; Geophysical measurement technique; Land surface; Terrain mapping; UHF radar; Radar remote sensing; RF interference removal; P-band; Airplane SAR; Airborne radar; music; Notch filtering; In-phase subtraction; Urban area ; Adaptive signal processing
Original abstract: This paper approaches the problem of canceling the disturbances due to RF interferences in P-band, airborne SAR missions. Two techniques are introduced: one exploits MUSIC to estimate the interferences' frequencies, and then performs notch filtering at that frequencies; whereas the other adaptively estimate the interference contributions and cancel them by means of in-phase subtraction. Both techniques have been successfully tested on the data acquired by the DLR E-SAR sensor over urban areas.
 

Ceccarelli, M.; A. Farina; A. Petrosino, (1996). Fuzzy unsupervised terrain classification based on a multiresolution approach. Proceedings of the WILF '95. Italian Workshop on Fuzzy Logic 1995. New Trends in Fuzzy Logic Naples, Italy 21-22 Sept. 1995
Singapore World Scientific, pp.151-9.
Keywords: Feature extraction; Fuzzy logic; Geophysics computing; Image classification; Image resolution; Image texture; Radar computing; Radar imaging; Radar theory; Real-time systems; Remote sensing; Synthetic aperture radar; Unsupervised learning; Fuzzy unsupervised terrain classification; Multiresolution approach; Real-time classification; Remote-sensed data; Pattern recognition; Fuzzy clustering; Data grouping; Textural features; Log-Gabor pyramidal analysis; Image analysis ; Spectral properties
Original abstract: Real-time classification of remote-sensed data is a challenging application in the pattern recognition area, especially when the spatial and temporal resolution increase. We focus on unsupervised fuzzy clustering algorithms applied to synthetic aperture radar data grouping and categorization. Fuzzy clustering methods are used as a classification module of the textural features extracted by a log-Gabor pyramidal analysis of the original image, whereas spectral properties of the areas to be recognised are used for the choice of the feature extraction parameters.
 

Ceccarelli, M.; A. Petrosino, (1997). A generalized regularization network for remote sensing data classification. Neural Nets WIRN VIETRI-96. Proceedings of the 8th Italian Workshop on Neural Nets Salerno, Italy 23-25 May 1996
London, UK Springer-Verlag, pp.170-9.
Keywords: Feature extraction; Feedforward neural nets; Image classification; Image resolution; Image texture; Parameter estimation; Real-time systems; Remote sensing by radar; Statistical analysis; Synthetic aperture radar; Generalized regularization network; Remote sensing data classification; Real-time classification; Pattern recognition; Spatial resolution; Temporal resolution; Neural network; Statistical methodologies; RBF networks; Synthetic aperture radar data classification; Textural feature extraction; Log-Gabor pyramidal analysis; Data-dependent approach; Spectral properties ; Radial basis function neural network
Original abstract: Real-time classification of remotely sensed data is a challenging application in the pattern recognition area, especially when the spatial and temporal resolution increases. Several studies proved that the neural network approach is an interesting alternative to conventional statistical methodologies. We focus on RBF networks applied to synthetic aperture radar data classification. RBF networks are used as a classification module of the textural features extracted by a log-Gabor pyramidal analysis of the original image. The problem of fast and reliable estimation of RBF parameters is addressed and a data-dependent approach is proposed. In particular, spectral properties of the areas to be recognised are used for the choice of the feature extraction parameters, whereas the statistical properties of the features are used for the suitable design of a generalized regularization network.
 

Ceccarelli, M.; A. Petrosino; A. Farina, (1996). Recognition of terrain classes in SAR images based on fuzzy methods and multichannel texture analysis. Proceedings of the International Workshop on Soft Computing in Remote Sensing Data Analysis Milan, Italy 4-5 Dec. 1995
Singapore World Scientific, pp.59-63.
Keywords: Cartography; Feature extraction; Fuzzy neural nets; Fuzzy set theory; Image classification; Image texture; Remote sensing; Synthetic aperture radar; Terrain class recognition; SAR images; Fuzzy methods; Multichannel texture analysis; Real time classification; Remote sensed data; Pattern recognition; Temporal resolution; Neural network approach; Unsupervised fuzzy clustering algorithms; Synthetic Aperture Radar data grouping; Fuzzy clustering networks; Classification module; Textural features; Log Gabor pyramidal analysis; Network parameter estimation; Data dependent approach ; Spectral properties
Original abstract: Real time classification of remote sensed data is a challenging application in pattern recognition, especially when the spatial and temporal resolution increase. Several recent studies proved that the neural network approach is an interesting alternative to conventional statistical methodologies. We focus on unsupervised fuzzy clustering algorithms applied to Synthetic Aperture Radar data grouping and classification. Fuzzy clustering networks are used as a classification module of the textural features extracted by a log Gabor pyramidal analysis of the original image. The problem of fast and reliable estimation of the network parameters is addressed and a data dependent approach is proposed. In particular, spectral properties of the areas to be recognised are used for the choice of the feature extraction parameters.
 

Cetin, H.; T. A. Warner; D. W. Levandowski (1993). Data Classification, Visualization, and Enhancement Using N-Dimensional Probability Density Functions (Npdf) - Aviris, Tims, Tm, and Geophysical Applications. Photogrammetric Engineering and Remote Sensing, V59, (N12): 1755-1764.
Keywords: Optics/Acoustics
 
 

Chalasani, V.; P. A. Beling, (1998). Optimization based classifiers for road extraction. SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218) San Diego, CA, USA 11-14 Oct. 1998
New York, NY, USA IEEE, pp.2938-43 vol.3.
Keywords: Decision trees; Feature extraction; Geography; Image classification; Infrared imaging; Linear programming; Remote sensing; Optimization based classifiers; Road extraction; Performance; Linear programming-based decision tree; Gray scale images; AVIRIS images; Pixel classification; Discriminant lines ; Nearest neighbour
Original abstract: We investigate the performance of a linear programming-based decision tree in creating gray scale images for road extraction from AVIRIS images. We apply our method for classification of pixels from a digital image of an area near Williamsburg, Virginia, using the distance from discriminant lines as a measure to create a gray scale image. Our method effectively captures information from a large number of bands of the original image and can be a useful input to other techniques which can use only a single band.
 

Chang, C. I. (2000). An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis. Ieee Transactions on Information Theory, V46, (N5): 1927-1932.
Keywords: spectral database; library hyperspectral image analysis, spectral variability
Original Abstract: A hyperspectral image can be considered as an image cube where the third dimension is the spectral domain represented by hundreds of spectral wavelengths. As a result, a hyperspectral image pixel is actually a column vector with dimension equal to the number of spectral bands and contains valuable spectral information that can be used to account for pixel variability, similarity and discrimination. We present a new hyperspectral measure, the spectral information measure (SIM), to describe spectral variability and two criteria, spectral information divergence and spectral discriminatory probability for spectral similarity and discrimination, respectively. The spectral information measure is an information-theoretic measure which treats each pixel as a random variable using its spectral signature histogram as the desired probability distribution. Spectral information divergence (SID) compares the similarity between two pixels by measuring the probabilistic discrepancy between two corresponding spectral signatures. The spectral discriminatory probability calculates spectral probabilities of a spectral database (library) relative to a pixel to be identified so as to achieve material identification. In order to compare the discriminatory power of one spectral measure relative to another, a criterion is also introduced for performance evaluation, which is based on the power of discriminating one pixel from another relative to a reference pixel. The experimental results demonstrate that the new hyperspectral measure can characterize spectral variability more effectively than the commonly used spectral angle mapper (SAM).
--------------------------------------------------------------------------------
 

Chang, C. I.; H. Ren (2000). An experiment-based quantitative and comparative analysis of target detection and image classification algorithms for hyperspectral imagery. Ieee Transactions on Geoscience and Remote Sensing, V38, (N2 PT2): 1044-1063.
Keywords: linear spectral unmixing hyperspectral image analysis
Original Abstract: Over the past years, many algorithms have been developed for multispectral and hyperspectral image classification. A general approach to mixed pixel classification is linear spectral unmixing, which uses a linear mixture model to estimate the abundance fractions of signatures within a mixed pixel. As a result, the images generated for classification are usually gray scale images, where the gray level value of a pixel represents a combined amount of the abundance of spectral signatures residing in this pixel. Due to a lack of standardized data, these mixed pixel algorithms have not been rigorously compared using a unified framework. The authors present a comparative study of some popular classification algorithms through a standardized HYDICE data set with a custom-designed detection and classification criterion. The algorithms to be considered for this study are those developed for spectral unmixing, the orthogonal subspace projection (OSP), maximum likelihood, minimum distance, and Fisher's linear discriminant analysis (LDA). In order to compare mixed pixel classification algorithms against pure pixel classification algorithms, the mixed pixels are converted to pure ones by a designed mixed-to-pure pixel converter. The standardized HYDICE data are then used to evaluate the performance of various pure and mixed pixel classification algorithms. Since all targets in the HYDICE image scenes can be spatially located to pixel level, the experimental results can be presented by tallies of the number of targets detected and classified for quantitative analysis.
 

Chanussot, J.; G. Mauris; P. Lambert (1999). Fuzzy fusion techniques for linear features detection in multitemporal SAR images. IEEE Transactions on Geoscience and Remote Sensing, 37, (3, pt.1): 1292-305.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image sequences; Radar imaging; Remote sensing by radar; Sensor fusion; Spaceborne radar; Synthetic aperture radar; Terrain mapping; Geophysical measurement technique; Land surface; Land use; Road network; Fuzzy fusion; Data fusion; Image fusion; Radar remote sensing; Linear feature detection; Multitemporal SAR image; Automatic detection; Linear feature ; sar
Original Abstract: This paper is concerned with the automatic detection of linear features in SAR satellite data, with application to road network extraction. After a directional prefiltering step, a morphological line detector is presented. To improve the detection performances, the results obtained on multitemporal data are fused. Different fusion strategies involving different fusion operators are then presented. Since extensions of classical set union and intersection do not lead to satisfactory results (the corresponding operators are either too indulgent or too severe), the first strategy consists of fusing the data using a compromise operator. The second strategy consists of fusing the results computed with two operators that have opposite properties, in order to obtain a final intermediate result. Thanks to the wide range of properties they provide, fuzzy operators are used to test and compare these two fusion strategies on real ERS-1 multitemporal data.
 

Chanussot, J.; G. Mauris; P. Lambert, (1999). Improving road detection on SAR images using fuzzy fusion methods. IMTC/99. Proceedings of the 16th IEEE Instrumentation and Measurement Technology Conference (Cat. No.99CH36309) Measurements for the New Millennium Venice, Italy 24-26 May 1999
Piscataway, NJ, USA IEEE, pp.1807-12 vol.3.
Keywords: Cartography; Edge detection; Feature extraction; Fuzzy set theory; Radar imaging; Remote sensing by radar; Sensor fusion; Terrain mapping; SAR images; Road detection; Fuzzy fusion methods; Automatic detection; Linear features; Multi-temporal images; Data fusion; Compromise operator; Operators with opposite properties; Global intermediate result; Fuzzy operators; Real ERS-1 data; Mean operator; Order weighted averaging operator; Feature detection ; Line detection
Original abstract: This paper focuses on the use of fuzzy fusion techniques to improve the automatic detection of linear features on multi-temporal SAR images. Different fusion strategies involving different fusion operators are presented. Since T-norms and T-conorms do not lead to satisfactory results (these operators are respectively too severe and too indulgent), the first strategy consists in fusing the data using a compromise operator. The second strategy consists in fusing the results computed with two operators with opposite properties, in order to obtain a global intermediate result. Thanks to the wide range of behaviours they provide, fuzzy operators are used to test and compare these two fusion strategies on real ERS-1 data.
 

Chein, I. C.; R. Hsuan (2000). An experiment-based quantitative and comparative analysis of target detection and image classification algorithms for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 38, (2, pt.2): 1044-63.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Multidimensional signal processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Quantitative method; Target detection; Algorithm; Hyperspectral imagery; Multispectral remote sensing; Linear spectral unmixing; Linear mixture model; Gray scale image; Orthogonal subspace projection; Maximum likelihood; Minimum distance ; Fisher's linear discriminant analysis
Original Abstract: Over the past years, many algorithms have been developed for multispectral and hyperspectral image classification. A general approach to mixed pixel classification is linear spectral unmixing, which uses a linear mixture model to estimate the abundance fractions of signatures within a mixed pixel. As a result, the images generated for classification are usually gray scale images, where the gray level value of a pixel represents a combined amount of the abundance of spectral signatures residing in this pixel. Due to a lack of standardized data, these mixed pixel algorithms have not been rigorously compared using a unified framework. The authors present a comparative study of some popular classification algorithms through a standardized HYDICE data set with a custom-designed detection and classification criterion. The algorithms to be considered for this study are those developed for spectral unmixing, the orthogonal subspace projection (OSP), maximum likelihood, minimum distance, and Fisher's linear discriminant analysis (LDA). In order to compare mixed pixel classification algorithms against pure pixel classification algorithms, the mixed pixels are converted to pure ones by a designed mixed-to-pure pixel converter. The standardized HYDICE data are then used to evaluate the performance of various pure and mixed pixel classification algorithms. Since all targets in the HYDICE image scenes can be spatially located to pixel level, the experimental results can be presented by tallies of the number of targets detected and classified for quantitative analysis.
 

Chen, C. C., (1998). A GIS approach to dynamic network routing. Proceedings. Conference XXI. Enterprise-Wide Geospatial Solutions: Realizing the Benefits Proceedings of AM/FM International Annual Conference San Jose, CA, USA 26-29 April 1998
Aurora, CO, USA AM & FM Int, pp.441-9.
Keywords: Automated highways; Data handling; Geographic information systems; Network routing; Parallel algorithms; Road traffic; Spatial data structures; Transportation; gis; Dynamic network routing; Intelligent transportation systems; Dynamic traffic assignment algorithm; Data integration; Real-time traffic information; Embedding; Decomposable data structures; Parallel processing algorithms; Routing systems; Time constraints; Location referencing system ; Spatial data
Original abstract: Within the domain of intelligent transportation systems (ITS) research, models devoted to solving dynamic traffic problems are proposed by means of integrating historical data with real-time traffic information. Due to the complexity of these models and the strength of the spatial analyzing capability of GIS, a trend towards embedding these algorithms into GIS is emerging. However, bottlenecks exist because: (1) current GIS mainly deal with data that are not sensitive to temporal changes; (2) there is a need for decomposable data structures in GIS to facilitate parallel processing algorithms to meet the time constraints of dynamic (or so called real-time) routing systems; and (3) there is a need for a consistent location referencing system to integrate spatial data from various sources. This paper discusses these difficulties in detail and proposes a conceptual model by integrating GIS with a dynamic traffic assignment (or dynamic route choice) algorithm (DTA) to resolve this problem.
 

Chen, C. H., (1997). Trends on information processing for remote sensing. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042) Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.1190-2 vol.3.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image processing; Image segmentation; Neural nets; Pattern recognition; Remote sensing; Wavelet transforms; Geophysical measurement technique; Land surface; Terrain mapping; Information processing; Compression; Segmentation; Neural network ; Wavelet transform
Original abstract: There has been greatly increased activity in the last twelve years on the use of information processing techniques on remote sensing problems including signal/image processing, compression, segmentation, feature extraction, pattern recognition, neural networks, etc. The past progress is reviewed from which a trend is developed. The trend shows a further emphasis on using neural networks and wavelet transforms for remote sensing.
 

Chen, C. H.; X. Zhang, (1999). Independent component analysis for remote sensing study. Image and Signal Processing for Remote Sensing V Florence, Italy 22-24 Sept. 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.150-8.
Keywords: Airborne radar; Feature extraction; Geophysical signal processing; Image classification; Neural nets; Principal component analysis; Radar computing; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Independent component analysis; Remote sensing study; ica; Source signal separation; Neural network architecture; SAR imagery; Pixel classification; Contrast ratio; Speckle effect; ATM images; De-mixing operations ; Airborne thematic mapper images
Original abstract: There has been much interest in the independent component analysis (ICA) methods for source signal separation. ICA algorithms can be represented by a neural network architecture to decompose a signal or image into components. The potential use of ICA in remote sensing study is examined. For SAR imagery in particular, the use of ICA to enhance the images and to improve the pixel classification is considered. It is shown that ICA processed images generally have lower contrast ratio (standard deviation to mean of an image) which implies a reduced speckle effect. The features extracted by using ICA also are quite effective for pixel classification. There are five pattern classes considered. By using the 9 original SAR images plus all 6 ATM (airborne thematic mapper) images, the best overall percentage correct is 86.6% which is the same as using 3 ICA and 6 ATM image data. Also ICA is shown to be better than PCA in classification with the same data set. Although the results presented are preliminary, ICA through its de-mixing operations is potentially a useful approach in remote sensing study.
 

Chen, K. S.; Y. C. Tzeng; C. T. Chen; J. S. Lee, (1997). Filtering effects on polarimetric SAR image classification. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042) Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.1199-201 vol.3.
Keywords: Feature extraction; Forestry; Fuzzy neural nets; Geophysical signal processing; Geophysical techniques; Geophysics computing; Image classification; Radar imaging; Radar polarimetry; Remote sensing by radar; Synthetic aperture radar; Geophysical measurement technique; Land surface; Terrain mapping; Remote sensing; Filtering effects; Polarimetric SAR; Radar remote sensing; Polarimetric filter; Supervised fuzzy dynamic learning; Neural network; Fuzzy neural net; Kalman filter; Training; P-band; Tree age classification; Vegetation mapping; Flevoland; Netherlands ; Land cover boundary
Original abstract: Feature extraction from SAR images is usually impeded by the presence of speckle noise. This becomes more serious in the case of polarimetric SAR system. A polarimetric filter recently proposed by Lee et al. [1997] emphasizes not introducing additional cross-talk and statistical correlation between channels, preserving polarimetric information and not degrading the image quality. This paper exams its effects on the image classification by a supervised fuzzy dynamic learning neural network trained by a Kalman filter technique. Based on the available ground truth, the classification performance were evaluated using the original and filtered SAR images. Two independent test sites are selected for this purpose. The first case is a P-band JPL polarimetric SAR data over Les Landes for tree age classification. A total of 12 classes between 5 to 44 years of age were to be classified, along with a bare soil type. The second test site is over Flevoland of the Netherlands. This agricultural site consists of 11 landcover types. Again, the polarimetric SAR data were acquired with JPL P, L, C bands airsar system. For the first case, it was found that the overall classification accuracy was able to improve from 69% to about 86% with kappa coefficient up from 0.46 to 0.76. Substantial improvement was also confirmed for the second case. In particular, when classification was performed using only single frequency. This shows that the polarimetric information are well preserved. By visual inspection from classified map, the land cover boundaries were also delineated more clearly. As for fuzzy neural network performance, among the tested cases, the fuzzy index equal to 2 gets the best results.
 

Chen, K. S.; S. K. Yen; D. W. Tsay (1997). Neural classification of SPOT imagery through integration of intensity and fractal information. International Journal of Remote Sensing, 18, (4): 763-83.
Keywords: Filtering theory; Fractals; Image classification; Kalman filters; Learning (artificial intelligence); Multilayer perceptrons; Optimisation; Remote sensing; Wavelet transforms; Neural classification; Information integration; Intensity information; Fractal information; High-dimensional information; Remotely sensed image classification; Land cover classification; SPOT-HRV imagery; Multispectral intensity; Texture information; Fractal dimension extraction; Wavelet transform; Image texture; Modified multilayer perceptron; Kalman filtering; Fast convergence; Built-in optimization function; Correlation analysis; Discrimination capability; Heterogeneous area; Urban regions ; Open water
Original Abstract: It is well known that higher dimensional information essentially leads to better accuracy in remotely sensed image classification. This paper is aimed at land cover classification from SPOT-HRV imagery by the integration of multispectral intensity and texture information. In particular, fractal dimensions are extracted using a wavelet transform as image texture. A neural network approach to classification is adopted in this paper. The underlying network is a modified multilayer perceptron trained by a Kalman filtering technique. The main advantages of this network are (1) its nonbackpropagation fashion of learning which leads to a fast convergence, (2) a built-in optimization function, and (3) global scale. Saving computer storage space and a fast learning capability are in particular suitable features for remote sensing applications. Correlation analysis was subsequently performed on both the intensity and fractal images. It was found that fractal information significantly improves the discrimination capability of heterogeneous area such as in urban regions, while it slightly degrades accuracy for homogeneous areas, such as open water. The overall classification performance is superior to results obtained using reflectance only. Improvements over heterogeneous areas are demonstrated.
 

Chen, S. P.; S. Zeng; C. G. Xie (2000). Remote sensing and GIS for urban growth analysis in China. Photogrammetric Engineering and Remote Sensing, V66, (N5): 593-598.
Keywords: Optics/Acoustics
Original Abstract: The progress of urban remote sensing and GIS in China since the early 1980s is reviewed. The first section introduces the early applications of remote sensing to environmental monitoring and resources investigation, and outlines its achievements. The second section focuses on further analysis of urban expansion from the point of view of spatial distribution patterns and temporal change, taking Beijing, Shanghai, and Dongguan as examples. Urban GIS is discussed in the third section. The regional differences of UGIS development in China are detailed from south to north. As remote sensing and GIS technologies develop, they will be combined for use in urban planing and management.
 

Chen, Z.; T. J. Feng; Z. Houkes, (1999). Texture segmentation based on wavelet and Kohonen network for remotely sensed images. IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028) Tokyo, Japan 12-15 Oct. 1999
Piscataway, NJ, USA IEEE, pp.816-21 vol.6.
Keywords: Feature extraction; Image segmentation; Image texture; Remote sensing; Self-organising feature maps; Wavelet transforms; Kohonen self-organizing map; 2D wavelet transform; Neural network ; Fuzzy clustering
Original abstract: In this paper, an approach based on wavelet decomposition and Kohonen's self-organizing map is developed for image segmentation. After performing the 2D wavelet transform of image, some features are extracted for texture segmentation, and the Kohonen neural network is used to accomplish feature clustering. The experimental results demonstrated the satisfactory effect of the proposed approach both for simulated textured image and multi-spectral remotely sensed images.
 

Chen, Z. K.; C. D. Elvidge; D. P. Groeneveld (1998). Monitoring seasonal dynamics of arid land vegetation using AVIRIS data. Remote Sensing of Environment, V65, (N3): 255-266.
Keywords:
Original Abstract: Seasonal changes in the density of photosynthetically active vegetation have been observed in derivative-based green vegetation index (DGVI) values derived from AVIRIS reflectance spectra of arid land shrub and saltgrass communities adjacent to Mono Lake, California. The study was conducted using AVIRIS datasets acquired in late August and early October of 1992. 2DZ_DGVI (second-order DGVI-derived in reference to zero baseline) showed a strong linear relationship (r2>0.93 for August and October) with green leaf area index (LAI) values of ten bitterbrush (Purshia tridentata) sample stands. After accounting for background errors introduced to the calculation of 1DL_DGVI (first-order DGVI-derived in reference to local rock-soil baseline), a modified 1DL_DGVI (1DL_MDGVI) exhibited a high linear correlation (r2> 0.92 for both seasons) with green LAI values of the bitterbrush stands. 2DZ_DGVI was applied to the two AVIRIS scenes acquired for the two periods to quantify and compare green vegetation cover. Areas covered by saltgrass (Distichlis spicata var. stricta) showed the largest change in 2DZ_DGVI from August to October. Shrubs, including bitterbrush and big sagebrush (Artemisia tridentata), changed less during the same period. The lowest seasonal change in 2DZ_DGVI occurred in barren areas and locations covered by Jeffrey pine (Pinus jeffreyi). The DGVI concept has potential for monitoring ecosystems in arid and semiarid lands where the influence of exposed rock¯soil backgrounds reduces the effectiveness of broadband red-vs.-NIR vegetation indices.
 

Cheng, P.; T. Toutin, (1997). Urban planning using data fusion of satellite and aerial photo images. IGARSS'97. 1997 International Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific Vision for Sustainable Development (Cat. No.97CH36042) Singapore 3-8 Aug. 1997
New York, NY, USA IEEE, pp.839-41 vol.2.
Keywords: Geophysical signal processing; Geophysical techniques; Image processing; Remote sensing; Remote sensing by radar; Sensor fusion; Town and country planning; Geophysical measurement technique; Town planning; Urban area; Optical imaging; Radar; Terrain mapping; Land use; Land surface; Data fusion; Aerial photo image; Satellite remote sensing; Multisource data; Radiometric processing; Geometric processing; spot; radarsat; irs; Photogrammetric method; Resection ; Urban planning
Original abstract: Urban planning using data fusion of different satellite and aerial photo images can be very useful. However, multisource data fusion requires geometric and radiometric processing, adapted to the nature and characteristics of the data. In this way the best information available from each image is preserved in the composite image. With the increased resolution of satellite and aerial photo images (5 m and less), the off-nadir viewing angle of the satellite sensor (greater than 20 degrees), and the multi-source data available (such as SPOT, RADARSAT, and IRS), a general and accurate photogrammetric method which can deal with different satellite images and an accurate photogrammetric method for aerial photos are needed. For satellite images, a rigorous method developed at the Canada Centre for Remote Sensing (CCRS), Natural Resources Canada, which takes into account the nature of the data can be used. For aerial photos, the method of space resection by collinearity can be used. This paper presents data fusion results using SPOT, RADARSAT, IRS satellite images and an aerial photo. The results are sharp and precise, which enables a better and easier interpretation for urban planning.
 

Chettri, S.; N. Netanyahu, (1997). Spectral unmixing of remotely sensed imagery using maximum entropy. 25th AIPR Workshop. Emerging Applications of Computer Vision Washington, DC, USA 16-18 Oct. 1996
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.55-62.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Information theory; Maximum entropy methods; Remote sensing; Remotely sensed imagery; Spectral unmixing; Maximum entropy formulation; Content extraction; Single picture element; Sub-pixel content extraction; Automatically guaranteed positive fractions; Ground cover class fractions; Combinatorial properties; Information theoretic entropy; Land surface; Terrain mapping ; Geophysical measurement technique
Original abstract: The paper addresses the importance of a maximum entropy formulation for the extraction of content from a single picture element in a remotely sensed image. Most conventional classifiers assume a winner take all procedure in assigning classes to a pixel whereas in general it is the case that there exists more than one class within the picture element. There have been attempts to perform spectral unmixing using variants of least squares techniques, but these suffer from conceptual and numerical problems which include the possibility that negative fractions of ground cover classes may be returned by the procedure. In contrast, a maximum entropy (MAXENT) based approach for sub-pixel content extraction possesses the useful information theoretic property of not assuming more information than is given, while automatically guaranteeing positive fractions. The authors apply MAXENT to obtain the fractions of ground cover classes present in a pixel and show its clear numerical superiority over conventional methods. The optimality of this method stems from the combinatorial properties of the information theoretic entropy.
 

Chiang, S. S.; C. I. Chang; I. W. Ginsberg (2001). Unsupervised target detection in hyperspectral images using projection pursuit. IEEE Transactions on Geoscience and Remote Sensing, 39, (7): 1380-91.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Image processing; Multidimensional signal processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Multispectral remote sensing; Hyperspectral remote sensing; Unsupervised target detection; Hyperspectral image; Projection pursuit; Man-made target; Skewness ; Trapping local optima
Original Abstract: The authors present a projection pursuit (PP) approach to target detection. Unlike most of developed target detection algorithms that require statistical models such as linear mixture, the proposed PP is to project a high dimensional data set into a low dimensional data space while retaining desired information of interest. It utilizes a projection index to explore projections of interestingness. For target detection applications in hyperspectral imagery, an interesting structure of an image scene is the one caused by man-made targets in a large unknown background. Such targets can be viewed as anomalies in an image scene due to the fact that their size is relatively small compared to their background surroundings. As a result, detecting small targets in an unknown image scene is reduced to finding the outliers of background distributions. It is known that "skewness," is defined by normalized third moment of the sample distribution, measures the asymmetry of the distribution and "kurtosis" is defined by normalized fourth moment of the sample distribution measures the flatness of the distribution. They both are susceptible to outliers. So, using skewness and kurtosis as a base to design a projection index may be effective for target detection. In order to find an optimal projection index, an evolutionary algorithm is also developed to avoid trapping local optima. The hyperspectral image experiments show that the proposed PP method provides an effective means for target detection.
 

Chibani, Y.; A. Houacine, (2000). On the use of the redundant wavelet transform for multisensor image fusion. ICECS 2000. 7th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.00EX445)Jounieh, Lebanon 17-20 Dec. 2000
Piscataway, NJ, USA IEEE, pp.442-5 vol.1.
Keywords: Feature extraction; Image reconstruction; Redundancy; Sensor fusion; Wavelength division multiplexing; Redundant wavelet transform; Multisensor image fusion; Feature duplication; Scales ; Remote sensing images
Original abstract: This paper describes a multisensor image fusion scheme based on the use of the redundant wavelet transform. This transform duplicates features through scales when they are significantly dominant. In order to ensure that a fused image contains all significant features coming from multisensor images, we exploit the property of redundancy to develop a fusion rule applied in the wavelet domain. Simulated and remote sensing images are used to evaluate the fusion results and compare the performances for various rules.
 

Chih-Cheng, H.; A. Fahsi; W. Tadesse; T. Coleman, (1997). A comparative study of remotely sensed data classification using principal components analysis and divergence. 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation (Cat. No.97CH36088-5) Orlando, FL, USA 12-15 Oct. 1997
New York, NY, USA IEEE, pp.2444-9 vol.3.
Keywords: Feature extraction; Image classification; Remote sensing; Statistical analysis; Data bands; Principal components analysis; Divergence; Multispectral image classification; Statistical separability; Feature selection; Aerial photographs ; Landsat Thematic Mapper data
Original abstract: This paper investigates the principal components analysis (PCA) and divergence for transforming and selecting data bands for multispectral image classification. As the principal components are independent of one another, a color combination of the first three components can be useful in providing maximum visual separability of image features. Therefore, principal components analysis is used to generate a new set of data. Divergence, a measurement of statistical separability, is employed as a method of feature selection to choose the optimal m-band subset from the n-band data for use in the automated classification process. Classification accuracy assessment is carried out using large scale aerial photographs. Classification results on the Landsat Thematic Mapper (TM) data show that PCA is a more effective approach than divergence.
 

Chitroub, S.; B. Sansal, (1997). Feature reduction in terms of higher statistical separability for enhancement of multispectral image classification. Proceedings of the Fourth IEEE International Conference on Electronics, Circuits and Systems (ICECS'97) Cairo, Egypt 15-18 Dec. 1997, pp.1209-13 vol.3.
Keywords: Feature extraction; Image classification; Image representation; Remote sensing; Feature reduction; Statistical separability; Multispectral image classification ; Pattern recognition
Original abstract: In remote sensing pattern recognition application, establishing an optimal multispectral image representation is important for a better discrimination of scene targets. In fact, the spectral bands that constitute the original multispectral image are not all interesting for the problem of classification. A feature reduction consists to transform the original pixel vector into a new of coordinates in which the new features to be retained and those can be removed are made more evident. In this paper, a method of feature reduction for the purpose of improving the accurate and the speed of classification of remote sensing imagery is presented. The method transforms the original space to the new subspace in which class separation is optimized. Only the few first new images that exhibit a higher statistical separability between classes are used for classification. The method is tested and evaluated on TM images. The results are given in interesting images forms.
 

Choi, K.; W. Jang (2000). Development of a transit network from a street map database with spatial analysis and dynamic segmentation. Transportation Research Part C-Emerging Technologies, V8, (N1-6): 129-146.
Keywords: Transit network development; GIS; Digital map; Spatial analysis; Dynamic segmentation
Original Abstract: This paper presents an integrated transit-oriented travel demand modeling procedure within the framework of geographic information systems (GIS). Focusing on transit network development, this paper presents both the procedure and algorithm for automatically generating both link and line data for transit demand modeling from the conventional street network data using spatial analysis and dynamic segmentation. For this purpose, transit stop digitizing, topology and route system building, and the conversion of route and stop data into link and line data sets are performed. Using spatial analysis, such as the functionality to search arcs nearest from a given node, the nearest stops are identified along the associated links of the transit line, while the topological relation between links and line data sets can also be computed using dynamic segmentation. The advantage of this approach is that street map databases represented by a centerline can be directly used along with the existing legacy urban transportation planning systems (UTPS) type travel modeling packages and existing GIS without incurring the additional cost of purchasing a full-blown transportation GIS package. A small test network is adopted to demonstrate the process and the results. The authors anticipate that the procedure set forth in this paper will be useful to many cities and regional transit agencies in their transit demand modeling process within the integrated GIS-based computing environment.
 

Choi, K.; T. J. Kim (1996). A hybrid travel demand model with GIS and expert systems. Computers, Environment and Urban Systems, 20, (4-5): 247-59.
Keywords: Expert systems; fortran; Geographic information systems; Human factors; Interactive systems; Planning; Transportation; User interfaces; Hybrid travel demand model; gis; Transportation planning; Geographic information system; Interactive system; TranDASS; User-unfriendliness; Labor-intensiveness; Topology conversion algorithm ; User-friendly interface
Original Abstract: The purpose of this paper is to combine a traditional transportation planning model with a geographic information system (GIS) and an expert system (ES) in order to demonstrate the feasibility of integrating a transportation planning model with GIS and ES technology. Hence an interactive desktop transportation planning system called TranDASS was developed. By combining the three systems, it is hoped that the inherent problems of transportation planning models, such as user-unfriendliness, labor-intensiveness, and theoretical limitations, can be alleviated. Yet combining GIS with a traditional transportation planning model always means that one has to overcome the topological incompatibility between the two. Therefore, a FORTRAN-based topology conversion algorithm is developed that establishes a communication channel between them. The expert system facilitates the generation of input to the transportation planning model by providing a user-friendly interface. Using an expert system, even in this limited sense, sheds light on how to resolve judgmental issues in the transportation planning process.
 

Chung-Sheng, L.; V. Castelli, (1997). Deriving texture feature set for content-based retrieval of satellite image database. International Conference on Image Processing (Cat. No.97CB36144) Santa Barbara, CA, USA 26-29 Oct. 1997
Los Alamitos, CA, USA IEEE Comput. Soc
Proceedings., pp.576-9 vol.1.
Keywords: Feature extraction; Image texture; Remote sensing; Visual databases; Deriving texture feature set; Content-based retrieval; Satellite image database; Performance; Transformed-based texture features; Spatial-based texture features; Benchmark; Brodatz set; Normalized Euclidean distance; Gabor filter; Transformed-based feature sets ; Quadrature mirror filter
Original abstract: In this paper, the performance of similarity retrieval from satellite image databases by using different sets of spatial and transformed-based texture features is evaluated and compared. A benchmark consisting of 37 satellite image clips from various satellite instruments is devised for the experiments. We show that although the proposed feature set perform only slightly better with the Brodatz set, its performance is far superior for the satellite images. The result indicates that more than 25% of the benchmark patterns can be retrieved with more than 80% accuracy by using normalized Euclidean distance. In contrast, less than 10% of the patterns are retrieved with more than 80% accuracy by using transformed-based feature sets (such as those based on Gabor filter or quadrature mirror filter (QMF)).
 

Ciochetto, G.; R. Polidoro (1998). Site investigation and output of utilities map using GPR. CSELT Technical Reports, 26, (2): 177-84.
Keywords: Cartography; Object detection; Public utilities; Radar imaging; Soil; Telecommunication cables; Telecommunication networks; Underground cables; Site investigation; Utilities map; Subsoil; Underground network infrastructures; Ground penetrating radar; 2D images; cselt; Torino; Digital cartography ; Urban area
Original Abstract: An exhaustive knowledge of the subsoil right from the first design phases of the construction of underground network infrastructures is essential, both to limit possible damage to pre-existing utilities and to reduce the number of failures especially if new trenchless techniques are used. The most popular method for locating underground utilities is definitely ground penetrating radar (GPR), due to its rapidity of execution, good-quality results, and capacity to supply 2D images of the subsoil. The paper presents the experimental results obtained by CSELT from some field tests performed in the city of Torino using GPR and reports the data obtained from the investigations of a digital cartography of the urban area.
 

Clark, G. A.; S. K. Sengupta; W. D. Aimonetti; F. Roeske; J. G. Donetti (2000). Multispectral image feature selection for land mine detection. IEEE Transactions on Geoscience and Remote Sensing, 38, (1, pt.1): 304-11.
Keywords: Buried object detection; Feature extraction; Geophysical signal processing; Geophysical techniques; Image processing; Military systems; Multidimensional signal processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Landmine; Military system; Multispectral remote sensing; Optical imaging; Visible region; Infrared imaging; IR method; Image feature selection; Land mine detection; Camera; Registered image; Supervised-learning algorithm; Metal; Plastic land mine; Detection performance ; Land surface
Original Abstract: The authors' system uses a camera that acquires registered images in six spectral bands and a supervised-learning algorithm to detect metal and plastic land mines. Results show that even with a small sample size, the detection performance is good and holds promise for future work with larger data sets.
 

Clausi, D. A.; M. E. Jernigan (1998). A fast method to determine co-occurrence texture features. IEEE Transactions on Geoscience and Remote Sensing, 36, (1): 298-300.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image texture; Remote sensing; Geophysical measurement technique; Land surface; Terrain mapping; Image processing; Image feature; Fast method; Co-occurrence texture feature; Grey-level co-occurrence matrices; Occurrence matrix; Linked-list algorithm ; Grey-level quantization
Original Abstract: A critical shortcoming of determining texture features derived from grey-level co-occurrence matrices (GLCM's) is the excessive computational burden. This paper describes the implementation of a linked-list algorithm to determine co-occurrence texture features far more efficiently. Behavior of common co-occurrence texture features across difference grey-level quantizations is investigated.
 

Collischonn, W.; J. V. Pilar (2000). A direction dependent least-cost-path algorithm for roads and canals. International Journal of Geographical Information Science, 14, (4): 397-406.
Keywords: Dynamic programming; Geographic information systems; Transportation; Visual databases; Direction dependent least-cost-path algorithm; Route planning; Roads; Canals; Topography; Grid structure; Raster structure; Geographical information systems ; Cost functions
Original Abstract: In planning routes for roads and canals, topography is often a significant constraint. Among the infinite number of possible trajectories between two points, the selected path should be a good approximation to the one with the least cost, and should avoid extremes of slopes. In the case of a canal, the number of uphill reaches of the trajectory should be minimised. This paper presents a least-cost-path algorithm developed to find the best path given the topography, the start and end-points of the linear feature (canal or road) and a function relating slope, distance and cost. The algorithm is based on dynamic programming techniques adapted to solve problems on the grid, or raster structure usually used in geographical information systems. The algorithm was programmed and used to solve hypothetical problems. Although real cost functions were not used, the results were coherent and showed the algorithm's capabilities.
 

Cometti, E.; E. Mozzi; R. Bardoscia; G. Parma; L. Ratti, (1996). GIS as support for transport planning in Lombardia. Geographical Information from Research to Application Through Cooperation. Second Joint European Conference and Exhibition Proceedings of Joint European Conference on Geographical Information Barcelona, Spain 27-29 March 1996
Amsterdam, Netherlands IOS Press, pp.933-43 vol.2.
Keywords: Cartography; Environmental factors; Geographic information systems; Public administration; Town and country planning; Transportation; Geographic information system; Transport planning; Transportation Department; Territorial and Cartographic Information Office; Italy Regione Lombardia; Territorial information system; System development project; Road network; Rail network; Model assignment; Public transport; Private transport; Infrastructural graph; Regional technical map; Regional officer ; Environmental analysis
Original abstract: The Transportation Department and the Territorial and Cartographic Information Office of Regione Lombardia (Italy), within a territorial information system (TIS) development project, carried out the integration of the road and rail networks (as defined by the Transportation Department) for model assignment of public and private transport, and produced the infrastructural graph of the TIS, based on a regional technical map with a 1:10,000 scale. This fundamental experience is a foundation for supporting the regional officer for transport planning and programming based on territorial and environmental analyses.
 

Console, E.; M. C. Mouchot, (1996). Fuzzy classification techniques in the urban area recognition. IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium. Remote Sensing for a Sustainable Future (Cat. No.96CH35875) Lincoln, NE, USA 27-31 May 1996
New York, NY, USA IEEE, pp.1373-5 vol.2.
Keywords: Fuzzy logic; Geophysical signal processing; Geophysical techniques; Image classification; Image recognition; Image segmentation; Remote sensing; Geophysical measurement technique; Land surface; Terrain mapping; Multispectral remote sensing; Optical imaging; Visible; Infrared; Satellite remote sensing; Fuzzy image classification; Urban area recognition; Town; City; Fuzzy logic method; Landsat TM; Catanzaro; Calabria; Italy; Fuzzy parallelepiped classifier ; Membership value
Original abstract: Determination of scattered urban areas in a very heterogeneous environment can prove to be quite difficult using conventional classification techniques of remotely sensed images. On the other hand, fuzzy logic methods enable this difficulty to be overcome by assigning one pixel to more than one class according to a membership grade, determined using a pre-defined function. In this study, urban areas have been classified using fuzzy logic methods. The analysis was performed on a Landsat TM sub-scene (800*600 pixels) acquired over the province of Catanzaro (Calabria, Italy). The intrinsic characteristics of the ground coverage, as well as the rough topography, contribute to make this area a very heterogeneous one. The image was classified using a fuzzy parallelepiped classifier and membership values, associated to each pixel, were calculated. For each pixel, the classes, which contributed the most, were kept for the determination of the final pixel assignment. Global accuracy of fuzzy classification, estimated on mixed test area (chosen during a 2/sup nd/ ground truth campaign) reached a level of 0.75 Urban areas were identified analysing the images that represent the combinations of "Urban" class with the other classes. The fuzzy classification results were compared to image classified using the traditional techniques, minimum distance and maximum likelihood. In terms of global accuracy, fuzzy technique appeared to be more accurate than conventional techniques.
 

Console, E.; B. Solaiman, (2000). Problems and perspectives in the high resolution data fusion. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2605-7 vol.6.
Keywords: Edge detection; Geophysical signal processing; Geophysical techniques; Image processing; Image resolution; Multidimensional signal processing; Remote sensing; Sensor fusion; Terrain mapping; Geophysical measurement technique; Multispectral remote sensing; Data fusion; Land surface; Optical imaging; Visible; ir; Infrared; High resolution; Multispectral data; Standard merging method; Transformation; rgb; ihs; Algorithm ; Fuzzy theory
Original abstract: The authors' attention has been focused on the prospects held by the introduction of high resolution. They have particularly tried to point out the difficulties and the advantages met in the fusion of high resolution and multispectral data through a simple application carried out in two phases. The first was aimed at the fusion of the data by means of a standard merging method based on the transformation RGB-IHS and the second was aimed at edge detection on the merged data by means of an algorithm based on fuzzy theory.
 

Coombs, J.; M. Shasko, (1995). The integration of highway data into the transportation centreline network. Ninth Annual Symposium on Geographic Information Systems in Natural Resources Management. Symposium Proceedings Proceedings Ninth Annual Symposium on Geographic Information Systems Vancouver, BC, Canada 27-30 March 1995
Fort Collins, CO, USA GIS World, pp.277-8 vol.1.
Keywords: Cartography; Data handling; Geographic information systems; Government data processing; Public administration; Transportation; Highway data integration; Transportation centreline network; Planning Services Branch; Ministry of Transportation and Highways; Road data; Transportation data; Geographic information system; Digital map base; Disparate data sets; Databases; Spatial based applications; Business needs; Rapidly evolving service organization ; Testing
Original abstract: The Planning Services Branch of the Ministry of Transportation and Highways has been actively developing strategies to integrate road and transportation data into a geographic information system. The efforts to date have included the construction of a digital map base and the migration of several disparate data sets onto the map base. The remaining task and challenge for the Branch is to move beyond the presentation of data to the development of tools and mechanisms to evaluate, use, and maintain these data bases for their clients. Increasing demands on the Branch to provide and assimilate data in a timely manner has been the motivating force behind these efforts to streamline data handling. It is anticipated that through efforts to provide data in a unified system, the development of spatial based applications is better served. The primary focus of the presentation is to report on the development and testing of mapping applications that meet the business needs of a rapidly evolving service organization.
 

Cord, M.; D. Declercq (2001). Three-dimensional building detection and modeling using a statistical approach. IEEE Transactions on Image Processing, 10, (5): 715-23.
Keywords: Bayes methods; Cartography; Feature extraction; Image recognition; Image reconstruction; Image resolution; Image segmentation; Monte Carlo methods; Parameter estimation; Remote sensing; Statistical analysis; Stereo image processing; Stochastic processes; Three-dimensional building detection; Statistical approach; High-resolution stereoscopic aerial imagery; Hierarchical strategy; Urban sites; Global focusing; Local modeling; Depth information; Adaptive correlation stereo matching; Multiplane model; Mixture model; Bayesian approach; Augmentation; Stochastic algorithms ; Monte Carlo study
Original Abstract: In this paper, we address the problem of building reconstruction in high-resolution stereoscopic aerial imagery. We present a hierarchical strategy to detect and model buildings in urban sites, based on a global focusing process, followed by a local modeling. During the first step, we extract the building regions by exploiting to the full extent the depth information obtained with a new adaptive correlation stereo matching. In the modeling step, we propose a statistical approach, which is competitive to the sequential methods using segmentation and modeling. This parametric method is based on a multiplane model of the data, interpreted as a mixture model. From a Bayesian point of view the so-called augmentation of the model with indicator variables allows using stochastic algorithms to achieve both model parameter estimation and plane segmentation. We then report a Monte Carlo study of the performance of the stochastic algorithm on synthetic data, before displaying results on real data.
 

Corr, D. G., (1997). Coherent change detection for urban development monitoring. IEE Colloquium on Radar Interferometry (Ref. No.1997/153) London, UK 11 April 1997, pp.6/1-6.
Keywords: Image resolution; Radar imaging; Remote sensing by radar; Spaceborne radar; Synthetic aperture radar; Coherent change detection; Urban development monitoring; Missed events; Descending orbits; Ascending orbits; Ionospheric effects; Resolution ; Coherence measurement window
Original abstract: Coherence measurements provide a tool with significant potential for detecting change. To reduce the likelihood of missed events data from both ascending and descending orbits should be used. Data from ascending orbits (which is acquired at 22.00 hrs GMT) lead to higher coherence values than that from the descending orbits (at 11.00 hrs GMT); possibly as a result of ionospheric effects: however the data available were over a restricted period. The resolution of ERS data imposes a fundamental limit to the sensitivity of the change measurements through the size of the coherence measurement window.
 

Couloigner, I.; T. Ranchin (2000). Mapping of Urban Areas: A Multiresolution Modeling Approach for Semi-Automatic Extraction of Streets. Photogrammetric Engineering and Remote Sensing, V66, (N7): 867-874.
Keywords: automatic feature extraction
Synopsis: A paper discussing an automated method for extracting roads from high resolution (2m and higher) satellite imagery. Strips of streets are divided into substructures (of varying scale) which can be modeled using a wavelet transform.
Original Abstract: A new method to hierarchically extract urban road networks from very high spatial resolution space-borne imagery (spatial resolution of 2 m and higher) is presented. An explicit and generic model of "streets" was developed according to a multiresolution analysis of images associated with a wavelet transform. The method consists of two processing steps the multiresolution extraction of edges of streets, and, if existing, the multiresolution extraction of strips of streets. The extraction of sides is achieved by the use of a multiscale representation of images, and the extraction of strips is done by a modeling of distinct substructures of streets at different characteristic scales achieved by the application of the associated wavelet transform. The method would help cartographers in their cartographic works in urban areas by a partial automation of tasks.
 

Couloigner, I.; T. Ranchin, (1998). Extraction of urban network from high spatial resolution imagery using multiresolution analysis and wavelet transform. Wavelet Applications in Signal and Imaging Processing VI San Diego, CA, USA 22-23 July 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.103-12.
Keywords: Cartography; Edge detection; Feature extraction; Image resolution; Remote sensing; Wavelet transforms; Urban network; High spatial resolution imagery; Multiresolution analysis; Wavelet transform; Quadrangular urban road network; Streets; Hierarchical system; Characteristic scales; A trous algorithm; Semi-automatic multiresolution processing; Photo-interpreters ; Airborne thematic mapper images
Original abstract: This paper presents a new method to extract, semi-automatically, a quadrangular urban road network from high spatial resolution imagery. A quadrangular network is generally composed of different classes of streets in a hierarchical system. The developed method is based both on multiresolution analysis and on the wavelet transform. The multiresolution analysis allows a multiscale analysis of images and thus the extraction of the streets in a class-by-class way. The wavelet transform enables the modeling of information at different characteristic scales. In the problem, it allows the extraction of the topography of streets. These two mathematical tools are combined in the "a trous" algorithm. The application of this algorithm to images of urban areas has been used to develop semi-automatic multiresolution processing. This method will help photo-interpreters in their cartographic work by a partial automation of tasks.
 

Couloigner, I.; T. Ranchin; V. P. Valtonen; L. Wald (1998). Benefit of the future SPOT-5 and of data fusion to urban roads mapping. International Journal of Remote Sensing, V19, (N8): 1519-1532.
Keywords:
Original Abstract: This article deals with the contribution of both the future SPOT-5 (which will produce images with the same bands as the existing SPOT 1-3 ones but with an improved spatial resolution) and a sensor fusion method to urban mapping. The ARSIS concept (in French: Amelioration de la Resolution Spatiale par Injection de Structures ) is used for sensor fusion. It allows the improvement of spatial resolution of the multi-band images, while preserving spectral information, by use of the high frequencies of panchromatic images. A well-proven method for urban mapping is then applied to all multi-spectral images available in the context of the study. A photo-interpretation of the latter confirms the benefit of fine image resolutions to urban roads mapping, in the limit of the sensor studied here. Then, when comparing the roads surface at all resolutions with reference extracted from accurate maps of the city, we demonstrate quantitatively that the finer the resolution, the more accurate the cartography.
 

Coulter, L.; D. Stow; B. Kiracofe; C. Langevin; D. M. Chen; S. Daeschner; D. Service; J. Kaiser (1999). Deriving current land-use information for metropolitan transportation planning through integration of remotely sensed data and GIS. Photogrammetric Engineering and Remote Sensing, V65, (N11): 1293-1300.
Keywords: Optics/Acoustics
 
 

Cowdery, J. M.; J. L. Kurtz, (1999). Ground penetrating radar signal processing techniques for road subsurface measurements. Radar Sensor Technology IV Orlando, FL, USA 8 April 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.86-94.
Keywords: Graphical user interfaces; Radar computing; Radar signal processing; Radar tracking; Road vehicle radar; Signal classification; Road subsurface measurements; Time domain data; Road subsurface characterization; Florida Department of Transportation; High-resolution ground penetrating radar; Test van; Road surface thickness; Subsurface layer thickness; Voids; Road layer interfaces; University of Florida; Road subsurface layer interface detection; Road subsurface layer interface tracking; Road subsurface layer interface joining; Subsurface layer classification; Computational fast layer tracking processing; Research; Road subsurface conditions; Road design; Road improvement ; Graphical user interface
Original abstract: Ground penetrating radar (GPR) has become a recognized tool for road subsurface characterization. The Florida Department of Transportation (FDOT) performs road subsurface measurements throughout Florida with a high-resolution ground penetrating radar mounted on a test van traveling at speeds up to 55 MPH. The time domain data collected by the GPR allow the determination of thickness of the road surface and subsurface layers. With appropriate signal processing, the data can provide some insights about voids and other anomalies near road layer interfaces. The University of Florida, as part of a project for the FDOT, has developed a signal processing technique for detecting, tracking and joining, and analyzing road subsurface layer interfaces. This paper describes the novel techniques and results of the current project to employ advanced signal processing techniques to detect and classify subsurface layers. In particular, a computational fast layer tracking processing technique is described along with results of the algorithm. It is expected that the ground penetrating radar and the results of current research will assist the FDOT in determining more accurate road layer thickness profiles, assessing road subsurface conditions with less coring, and rehabilitating roads with less manpower than is now required. Such capabilities will allow potentially serious problems to be corrected before they become costly and will also provide a useful tool for future road design and improvement.
 

Croteau, K.; D. Skiles; B. Faber (1997). Custom GIS revamps Denver's former airport. GIS World, 10, (6): 50-2.
Keywords: Geographic information systems; Public administration; Custom GIS; Denver Stapleton International Airport, CO, USA; Site redevelopment; Sustainability; Commercial areas; Residential areas; Natural areas; Stapleton Redevelopment Foundation; Land-use plan; Planning expertise; Cost; Land-use balance; Water use; Solid waste generation; Wastewater generation; Transportation; Energy consumption; Denver Smart Places Project; GIS-based land-use decision support system; smart places; ESRI Inc.; ArcView; Consortium for International Earth Science Information Network; Active Response GIS; Interactive land-use design ; Interactive infrastructure specification
Original Abstract: The site of the former Stapleton International Airport at Denver, CO, USA contains wildlife habitat and buildings destined for demolition. Redevelopment efforts focus on sustainability and better integration of commercial, residential and natural areas. The Stapleton Redevelopment Foundation (SRF) was formed to consider an array of development ideas and to define a final comprehensive land-use plan. SRF had access to two important resources: planning expertise and the use of an extensive GIS database covering the Stapleton site, but SRF didn't have a methodology for combining its expertise and GIS data into an efficient system for creating, modifying and comparing alternative land-use plans in terms of cost, land-use balance, water use, solid waste and wastewater generation, transportation and energy consumption. The need for a comprehensive methodology engendered the nonprofit Denver Smart Places Project and a GIS-based land-use decision support system called SMART PLACES. The system, built on ESRI Inc.'s ArcView platform and the Consortium for International Earth Science Information Network's Active Response GIS, emphasizes interactive land-use design and infrastructure specification using a hands-on, what-if approach.
 

Curran, P. J.; J. L. Dungan (1990). An Image Recorded by the Airborne Visible Infrared Imaging Spectrometer (Aviris). International Journal of Remote Sensing, V11, (N6): 929-931.
Keywords:
 
 

Curran, P. J.; J. L. Dungan (1989). Estimation of Signal-to-Noise - a New Procedure Applied to Aviris Data. Ieee Transactions on Geoscience and Remote Sensing, V27, (N5): 620-628.
Keywords: AVIRIS , signal to noise ratio, intrapixel variability
Original Abstract: To make the best use of narrowband Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data, an investigator needs to know the signal-to-noise ratio (SNR). The signal is land cover dependent and varies with both wavelength and atmospheric absorption, and random noise comprises sensor noise and intrapixel variability (i.e. variability within a pixel). The three existing methods for estimating the SNR are inadequate, since typical laboratory methods inflate, while typical dark-current and image methods deflate the SNR value. The authors propose a procedure called the geostatistical method that is based on the removal of periodic noise by notch filtering in the frequency domain and the isolation of sensor noise and intrapixel variability using the semivariogram. This procedure was applied easily and successfully to five sets of AVIRIS data from the 1987 flying season and could be applied to remotely sensed data from broadband sensors.
 

Czerniak, R. J.; J. P. Reilly; National Cooperative Highway Research Program; National Research Council (U.S.). Transportation Research Board; American Association of State Highway and Transportation Officials; United States. Federal Highway Administration (1998). Applications of GPS for surveying and other positioning needs in departments of transportation. Washington D.C., National Academy Press.
 

Dabis, H.; P. Palmer; J. Kittler, (1995). An interest operator based on perceptual grouping. Theory and Applications of Image Analysis II. Selected Paper from the 9th Scandinavian Conference on Image Analysis Uppsala, Sweden June 1995
Singapore World Scientific, pp.211-24.
Keywords: Computer vision; Feature extraction; Object recognition; Remote sensing; Interest operator; Perceptual grouping; Aerial scenes; Nonaccidentalness; Region information ; Focus of attention
Original abstract: In this paper, perceptual grouping is used to assign interest levels to complex structures in images of aerial scenes. The interest operator increases exponentially as more features belonging to the structure are detected. We apply the theory of non-accidentalness to focus our attention on events which are least likely to occur anywhere in the image except for the structure we are detecting. Region information obtained in the first sweep is fed back to the earlier levels of processing to improve the performance of feature extraction. We use the approach to detect bridges and runways although the ideas developed could be applied to any other complex structures. Only a small number of hypotheses are generated and results presented show that, in most cases, the interest levels for regions containing the structures are much higher than those for other regions. It is also shown that using the focus of attention improves the performance of feature extraction.
 

Dammert, P. B. G.; J. I. H. Askne; S. Kuhlmann, (1999). Unsupervised segmentation of multitemporal interferometric SAR images. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings Seattle, WA, USA 6-10 July 1998, pp.2259-71.
Keywords: Adaptive signal processing; Feature extraction; Geophysical signal processing; Geophysical techniques; Image classification; Image segmentation; Image sequences; Radar imaging; Remote sensing by radar; Synthetic aperture radar; Terrain mapping; Geophysical measurement technique; Land surface; Radar remote sensing; Unsupervised segmentation; Multitemporal image; Image sequence; Interferometric SAR image; InSAR; Fuzzy clustering method; Adaptive feature extraction; Principal component transformation; Fuzzy clustering; Iteration; Urban area; Forest; Farmland; Dominant land-cover ; Rule-based method
Original abstract: This paper shows how to segment large data sets of multitemporal and interferometric SAR images using an unsupervised, fuzzy clustering method. An adaptive feature extraction (principal component transformation) is employed which may drastically reduce the number of images and improves the final results. This also speeds up the fuzzy clustering iteration part considerably. The method is applied to data over two areas in Sweden: one typical urban area with forest and farmland surroundings and a forested area. The best classification accuracy is obtained when classifying the data into two classes, agreeing with the predictions of the cluster validity parameters used in this study. The method always finds the dominating land-covers in the images first. These are then subdivided as more clusters (classes) are identified, indicating that the segmentation is moderately hierarchical. The final classification results, between 65% and 75%, are comparable to those obtained in other studies. Analyzing the final cluster signatures reveals that the current unsupervised method has several similarities with rule-based methods.
 

Dantas, A.; K. Yamamoto; M. V. Lamar; Y. Yamashita, (2000). Neural network for travel demand forecast using GIS and remote sensing. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium Como, Italy 24-27 July 2000
Los Alamitos, CA, USA IEEE Comput. Soc, pp.435-40 vol.4.
Keywords: Feedforward neural nets; Geographic information systems; Multilayer perceptrons; Town and country planning; Transportation; Travel demand forecast; gis; Transportation planning; Urban area; Land use-transportation system interaction; Remote sensing images; Geographical information system ; Boston metropolitan area
Original abstract: Describes an application of neural networks in the development of a travel forecast model for transportation planning. The model intends to quantify trips within the urban area through the representation of the land use-transportation system interaction. The data to express such a complex interaction is mainly obtained from remote sensing images that are processed in a geographical information system. We present the model's basic formulation and the results of a case study conducted in the Boston metropolitan area.
 

Dare, P. M.; I. J. Dowman, (2000). Automatic registration of SAR and SPOT imagery based on multiple feature extraction and matching. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2896-8 vol.7.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image registration; Radar imaging; Remote sensing; Remote sensing by radar; Sensor fusion; Spaceborne radar; Synthetic aperture radar; Terrain mapping; Geophysical measurement technique; Land surface; Optical imaging; Radar remote sensing; sar; Automatic registration; SPOT imagery; Multiple feature extraction; Feature matching ; Satellite remote sensing
Original abstract: Many different models have been developed in the past to automatically register SAR and optical images. The vast majority of these models rely on feature based matching, due to the very different backscattering properties of the terrain in the optical and microwave regions of the electromagnetic spectrum. Even so, the difficulties associated with extracting similar features from radiometrically very different images have always hindered this approach to automatic registration. The model proposed in this paper uses feature based matching, but rather than relying on just one method of feature extraction, many different feature extraction algorithms are employed. This methodology ensures there is a large set of features extracted from each image to be matched. Consequently the chances of locating pairs of correctly matched points, which can be used in either a polynomial or a photogrammetric rectification model, are greatly increased. Application of the proposed algorithm to pairs of both small and large images showed that a substantial number of tie points could be accurately located in each pair of images. More importantly, the approach to feature based registration using multiple feature extraction techniques clearly improved the quality and quantity of the tie points compared to traditional feature based registration techniques which rely on only one feature extraction algorithm.
 

Dare, P. M.; C. S. Fraser, (2000). Linear infrastructure mapping using airborne video imagery and subsequent integration into a GIS. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2299-301 vol.5.
Keywords: Feature extraction; Geographic information systems; Image segmentation; Image sequences; Power distribution lines; Remote sensing; Video signal processing; Linear infrastructure mapping; Airborne video imagery; GIS integration; Spatial data; Helicopter based digital video sensors; High resolution colour imagery; Australia; Powerlines; Vector data; Ground measurements; Spatial information database; Power distribution network; Downward looking video sequences; Feature based matching; Image mosaics; Pylons; Ground control points; Georeferenced strip maps; Powerline network; Digital topographic data; Terrain ; Video image mosaicing
Original abstract: Airborne video imagery is an ideal tool for acquiring the spatial data needed for mapping linear infrastructure features. The flexibility offered by helicopter based digital video sensors means that high resolution colour imagery can be acquired of long linear features quickly and cheaply. This paper describes how airborne video has been implemented in Australia to map powerlines, and subsequently how the map products have been integrated with vector data and ground measurements to create a detailed spatial information database of the power distribution network. Strip maps are created from downward looking video sequences by mosaicing captured images using a combination of ephemeris data with area and feature based matching. Absolute orientation of the image mosaics is carried out interactively using the locations of the pylons as ground control points. An assessment of the resulting mosaics showed that the accuracy of the rectification of the image sequences was acceptable for purposes of this project. The georeferenced strip maps were imported into a GIS, the design of which allows the operator to view an image map of any part of the entire powerline network with digital topographic data overlaid. Selecting particular points on the image map provides access to information such as tower type, location and height. In addition, the operator is able to view a movie clip of any part of the powerline and surrounding terrain, from either a downward or forward looking perspective.
 

de Oliveira, M. G. S.; P. C. M. Ribeiro (2001). Production and analysis of coordination plans using a geographic information system. Transportation Research Part C (Emerging Technologies), 9C, (1): 53-68.
Keywords: Geographic information systems; Road traffic; Timing; Traffic control; Transportation; TRANSYT program; Signal coordination plans; SIGTRAF system; GIS-T technology; Topological information; Thematic mapping capabilities ; Timing plans
Original Abstract: The TRANSYT program is one of the most extensively used programs for the production of signal coordination plans. The impediments to the development of signal coordination plans are associated with data collection and data input. GIS offers a natural solution to these problems. The paper presents the SIGTRAF system, which uses GIS-T technology for the production of coordination plans using TRANSYT. This system is able to extract topological information from the GIS-T, thus simplifying the process of coding TRANSYT models. A case study was performed, providing insight on how the GIS-T's thematic mapping capabilities can be used to visually compare different timing plans.
 

De Vore, R. A.; W. Shao; J. F. Pierce; E. Kaymaz; B. T. Lerner; W. J. Campbell, (1997). Using nonlinear wavelet compression to enhance image registration. Wavelet Applications OV Orlando, FL, USA 22-24 April 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.539-51.
Keywords: Data compression; Feature extraction; Image coding; Image enhancement; Image matching; Image registration; Remote sensing; Transform coding; Wavelet transforms; Nonlinear wavelet compression; Complexity analysis; High-level compression; Control point extraction; Control point matching; Point alignment technique ; Landsat TM image
Original abstract: We present a method for automatically registering images based on nonlinear compression. The method involves three steps: (i) analysis of the complexity of the images; (ii) high-level compression for extracting control points in the images; (iii) registration of the images by matching control points. The first step analyzes the complexity of the given images. It numerically computes from any image a complexity index which determines the efficiency at which the image can be compressed. This index is used in the second step of the algorithm to select coefficients in the wavelet representation of the image to produce a highly compressed image. The wavelet coefficients of the highly compressed image are then transformed to pixel values. Only a few pixel values (called control points) are nontrivial. The third stage of the algorithm uses a point alignment technique to identify matching control points and to erect the registering transformations. The algorithm is tested on two quite different scenes: a portrait, representing an uncomplicated scene, and a Landsat TM image of the Pacific Northwest. In both cases, images are tested which differ by a rotation and which differ by a rigid transformation. The algorithm allows a choice of different metrics in which to do the compression and selection of control points.
 

Del Frate, F.; J. Lichtenegger; D. Solimini, (1999). Monitoring urban areas by using ERS-SAR data and neural networks algorithms. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293) Hamburg, Germany 28 June-2 July 1999
Piscataway, NJ, USA IEEE, pp.2696-8 vol.5.
Keywords: Geography; Image classification; Image texture; Neural nets; Radar imaging; Remote sensing by radar; Spaceborne radar; Synthetic aperture radar; Urban areas; ERS-SAR data; Neural networks algorithms; Multitemporal SAR data; Classification; Rome; Italy; Coherence; Textural features; SAR images; Winter; Spring; Summer; ERS tandem mission; Water surfaces; Woodland; Parks; Residential areas ; Decision-making process
Original abstract: This contribution discusses the kind of information contained in multitemporal SAR data and shows how it can be exploited for classifying the urban area of Rome, Italy. Multitemporal, coherence and textural features are obtained from a set of SAR images taken in winter, spring and summer by the ERS tandem mission. These features are used to identify areas belonging to various urban classes, including water surfaces, woodland and parks, and continuous high/low density residential areas. The decision-making process is performed by a classifier based on a neural network algorithm.
 

Del Frate, F.; A. Petrocchi; J. Lichtenegger; G. Calabresi, (2000). Neural networks for oil spill detection using ERS-SAR data. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 Hamburg, Germany 28 June-2 July 1999
Ieee
IEEE Trans. Geosci. Remote Sens. (USA), pp.2282-7.
Keywords: Feature extraction; Geophysical signal processing; Geophysics computing; Image classification; Neural nets; Oceanographic techniques; Radar imaging; Remote sensing by radar; Water pollution measurement; Water pollution; Marine pollution; Oil spill; Oil slick; Radar remote sensing; Measurement technique; Neural network; Neural net; ers; sar; Spaceborne radar; Semi-automatic detection; Algorithm; Extended pruning procedure ; Image processing
Original abstract: A neural network approach for semi-automatic detection of oil spills in European remote sensing satellite-synthetic aperture radar (ERS-SAR) imagery is presented. The network input is a vector containing the values of a set of features characterizing an oil spill candidate. The classification performance of the algorithm has been evaluated on a data set containing verified examples of oil spill and look-alike. A direct analysis of the information content of the calculated features has been also carried out through an extended pruning procedure of the net.
 

Dell'Acqua, F.; P. Gamba (2001). Detection of urban structures in SAR images by robust fuzzy clustering algorithms: The example of street tracking. Ieee Transactions on Geoscience and Remote Sensing, V39, (N10): 2287-2297.
Keywords: street extraction Fuzzy clustering, urban remote sensing.
Original Abstract: In this work, we present a fuzzy approach to the analysis of airborne synthetic aperture radar (SAR) images of urban environments. In particular, we want to show how to implement structure extraction algorithms based on fuzzy clustering unsupervised approaches.To this aim, the idea is to segment first the sensed data and recognizen very basic urban classes (vegetation, roads, and built areas). Then, from these classes, we extract structures and infrastructures of interest. The initial clustering step is obtained by means of fuzzy logic concepts and the successive analyses are able to exploit the corresponding fuzzy partition. As a possible complete procedure for urban SAR images, in this paper, we focus on the street tracking and extraction problem. Three road extraction algorithms available in literature (namely, the connectivity weighted Hough transform (CWHT), the rotation Hough transform, and the shortest path extraction) have been modified to be consistent with the previously computed fuzzy clustering results. Their different capabilities are applied for the characterization of streets with different width and shape. The whole approach is validated by the analysis of AIRSAR images of Los Angeles, CA.
 

Dell'Acqua, F.; P. Gamba (2001). Query-by-shape in meteorological image archives using the point diffusion technique. IEEE Transactions on Geoscience and Remote Sensing, 39, (9): 1834-43.
Keywords: Atmospheric techniques; Clouds; Feature extraction; Geophysical signal processing; Geophysics computing; Image retrieval; Meteorology; Query formulation; Cloud; Image archive; Image processing; Query-by-shape; Point diffusion; Point diffusion technique; Remote sensing; Measurement technique; Shape similarity evaluation; Querying; Database query; Retrieval speed; Precision; Shape feature; Image feature ; Searching
Original Abstract: The authors work on meteorological satellite image archives and provide a novel and useful query-by-shape tool. To this aim, they first present the point diffusion technique (PDT), a fast and efficient method for shape similarity evaluation. Thanks to its very structure, this approach is suitable to handle objects whose shape is not well defined and can be represented by a set of sparse points. PDT is thus suitable for application to similarity-based retrieval from remotely sensed image archives, where shapes are hardly defined but are still among the major features of interest. Moreover, they prove here that PDT is almost as effective as more standard procedures for shape-based database queries, although significantly faster. In other words, it manages to combine retrieval speed and precision, the features of greatest importance for a first remote sensing data prescreening in many applications. Archives of meteorological satellite images are typical examples of very large-sized, remote sensing-based databases with a special attention for shape features. Each meteorological satellite produces terabytes of data every day, a large part of which is not immediately analyzed and ends being stored in archives. The application of PDT to such a database is presented and discussed, and a comparison with a standard method developed for meteorological shape analysis is provided.
 

Dell'Acqua, F.; P. Gamba; B. Houshmand, (1998). Recognition of urban structures in multiband data by means of ART networks. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174) Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.400-2 vol.1.
Keywords: Adaptive signal processing; ART neural nets; Geophysical signal processing; Geophysical techniques; Geophysics computing; Image classification; Image recognition; Remote sensing; Sensor fusion; Geophysical measurement technique; Land surface; Terrain mapping; Multispectral remote sensing; Image processing; Urban structure; Multiband data; ART network; Neural net; Neural network; Multiband image; Adaptive resonance theory; Town; City; Spatial analysis; Spectral analysis; Clustering step; Class redundancy; SAR image; Santa Monica; California; usa; Los Angeles; Radar remote sensing ; Image fusion
Original abstract: Multiband images of a urban environment are analyzed and interpreted by means of a neural network approach. In particular, the advantages found by using adaptive resonance theory networks both for a spatial and spectral analysis of the data are shown and commented. Moreover, the authors simplify existing similar approaches by introducing a clustering step that automatically solves the problem of class redundancy, typical of the ART classification output. Results are given for a photo+SAR image of Santa Monica, Los Angeles.
 

Dell'Acqua, F.; P. Gamba; A. Mecocci, (1997). Image database retrieval by means of sketches and modal matching. Proceedings of 6th International Conference on Image Processing and its Applications (Conf. Publ. No.443) Dublin, Ireland 14-17 July 1997
London, UK IEE, pp.96-100 vol.1.
Keywords: Database theory; Image matching; Image sampling; Query processing; Visual databases; Image database retrieval; Modal matching; Visual search; User-defined sketch; Similarity evaluation; Scarcely sampled shapes; Sampled objects ; Similarity indexes
Original abstract: We present the application of different indexes based on the modal matching technique to visual search in an image database. The problem of efficiently retrieving the images similar to a user-defined sketch is addressed. Similarity evaluation for scarcely sampled shapes is outlined, as well as the problems related to modal matching between differently sampled objects. To these aims, four different definitions of suitable similarity indexes are introduced and discussed.
 

Deloukas, A.; I. Kokkinos; G. Kiousis; D. Zannou, (1997). GIS-based transportation planning and analysis: a practical implementation. Transportation Systems 1997. (TS'97). Proceedings volume from the 8th IFAC/IFIP/IFORS Symposium Proceedings of the 8th IFAC/IFIP/IFORS. Transportation Systems 1997 (3 vol.) Chania, Greece 16-18 June 1997
Oxford, UK Pergamon, pp.417-26 vol.1.
Keywords: Cartography; Data analysis; Entity-relationship modelling; Geographic information systems; Service industries; Strategic planning; Transportation; Visual databases; Transportation planning; Geographic information system; gis; Metro Development Study; Data management; Conceptual design; Geographical database; Public transport routes; Geocoding application; Data display; Thematic maps; Data manipulation; Map overlays ; Spatial data analysis
Original abstract: The potential of using advanced geographic information system (GIS) technology in transportation is illustrated in the context of the Metro Development Study (MDS). Data management issues related to the conceptual design of the MDS geographical database and the representation of public transport routes are discussed. A geocoding application serving the needs of the transportation model is described. Examples of data display (thematic maps) and data manipulation (map overlays) are given, and findings of spatial data analysis are presented. The overview of GIS-based transportation applications within MDS illustrates the advantages of integrating both systems.
 

Demin, X. (2000). A three-stage computational approach to network matching. Transportation Research Part C (Emerging Technologies), 8C, (1-6): 71-89.
Keywords: Geographic information systems; Image matching; Marine systems; Traffic information systems; Transportation; Visual databases; Three-stage computational approach; Network matching; Data integration; Manual manipulation; Three-stage matching algorithm; Node matching; Segment matching; Edge matching; Top-down procedures; Matching computation; Sensitive matching measures; Waterway networks; Matching rate; Computational efficiency; Linear alignment; Aspatial matching; Higher-level matching; gis ; Transportation networks
Original Abstract: Network matching is frequently needed for integrating data that come from different sources. Traditional ways of finding correspondences between transportation networks are time-consuming and require considerable manual manipulation. The paper describes a three-stage matching algorithm (node matching, segment matching, and edge matching) that combines bottom-up and top-down procedures to carry out the matching computation. As it uses sensitive matching measures, the proposed algorithm promises good improvement to existing algorithms. An experiment of matching two waterway networks is reported in the paper. The results of this experiment demonstrate that a reasonable matching rate and good computational efficiency can be achieved with this algorithm. The paper also briefly discusses necessary improvements in areas of linear alignment, aspatial matching and higher-level matching.
 

Demirbilek, A.; H. Pastaci, (2000). The planning of solution to Istanbul's transportation problem with the coordination of transportation subsystems by the aid of GPS. SICE 2000. Proceedings of the 39th SICE Annual Conference. International Session Papers (IEEE Cat. No.00TH8545) Proceedings of 39th Annual Conference of the Society of Instrument and Control Engineers - Japan (SICE 2000) Iizuka, Japan 26-28 July 2000
Tokyo, Japan Soc. Instrum. & Control Eng
SICE 2000. Proceedings of the 39th SICE Annual Conference. International Session Papers (IEEE Cat. No.00TH8545)
Access restricted., pp.297-300.
Original abstract: The Istanbul Transportation Information System has been established for the purpose of processing and storing data in a computer environment to arrange, in its most general sense, management service, coordination and planning activities related to transportation. The information system for this objective is one that is composed of a series of hardware and software components including data storage, data processing, data analysis and representation functions. A database called the transportation information system for evaluating the graphical and non-graphical data for the city of Istanbul has been formed. Moreover, some analyses are performed toward design and optimization based on a single intersection. Up-to-date data are accessed with an appropriate interrogation easily and efficiently.
 

Deschenes, F.; D. Ziou, (2000). Extracting line junctions from curvilinear structures. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.1672-4 vol.4.
Keywords: Feature extraction; Geophysical signal processing; Geophysical techniques; Image processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Line junction; Curvilinear structure; Gray-level image; Algorithm; Local line curvature; Orientation vector; Localization ; Road intersection
Original abstract: Describes an efficient approach for the detection of line junctions in gray-level images. The algorithm is divided into two steps. First, given the lines extracted from the original image, local line curvature is estimated. For this purpose, two different measures of curvature are proposed: The rate of change of direction of the orientation vector along the line and the mean of the dot products of orientation vectors within a given neighborhood. The second step involves the localization of junctions. Examples are provided based on experiments with remotely sensed images containing road intersections.
 

Descombes, X.; M. Sigelle; F. Preteux (1999). Estimating Gaussian Markov random field parameters in a nonstationary framework: application to remote sensing imaging. IEEE Transactions on Image Processing, 8, (4): 490-503.
Keywords: Feature extraction; Gaussian processes; Geophysical signal processing; Image segmentation; Image texture; Least squares approximations; Markov processes; Parameter estimation; Random processes; Remote sensing; Gaussian Markov random field parameters; Nonstationary framework; Remote sensing imaging; Textural parameters; Textural features; Nonstationarities; Estimation methods; Conditional probabilities; Least square approximation; Piecewise constant local mean; Blurring effect; Renormalization theory; Cramer-Rao estimators; Sampling; Texture discrimination; Urban areas; SPOT image ; Delineation
Original Abstract: In this paper, we tackle the problem of estimating textural parameters. We do not consider the problem of texture synthesis, but the problem of extracting textural features for tasks such as image segmentation. We take into account nonstationarities occurring in the local mean. We focus on Gaussian Markov random fields for which two estimation methods are proposed, and applied in a nonstationary framework. The first one consists of extracting conditional probabilities and performing a least square approximation. This method is applied to a nonstationary framework, dealing with the piecewise constant local mean. This framework is adapted to practical tasks when discriminating several textures on a single image. The blurring effect affecting edges between two different textures is thus reduced. The second proposed method is based on renormalization theory. Statistics involved only concern variances of Gaussian laws, leading to Cramer-Rao estimators. This method is thus especially robust with respect to the size of sampling. Moreover, nonstationarities of the local mean do not affect results. We then demonstrate that the estimated parameters allow texture discrimination for remote sensing data. The first proposed estimation method is applied to extract urban areas from SPOT images. Since discontinuities of the local mean are taken into account, we obtain an accurate urban areas delineation. Finally, we apply the renormalization based on method to segment ice in polar regions from AVHRR data.
 

Dherete, P.; J. Desachy, (2000). Cooperation and fusion of operators: Application to automatic matching of cartographic objects. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) IGARSS 2000. Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.2626-8 vol.6.
Keywords: Cartography; Feature extraction; Fuzzy logic; Geophysical signal processing; Geophysical techniques; Image matching; Image processing; Pattern matching; Remote sensing; Sensor fusion; Terrain mapping; Geophysical measurement technique; Land surface; Data fusion; Operators; Automatic matching; Cartographic object; SPOT image; Geographic database; Linear feature; Geographic feature; Complex image; Context; Complexity; Scene understanding; Diversity; Imprecision ; Fuzzy logic theory
Original abstract: The aim of this study is to provide a system able to identify and to match linear cartographic objects on SPOT images using geographic databases, and to update the databases. Automatic matching of geographic features in complex remote sensing images faces different problems, such as diversity of context or complexity of information. In order to simplify identification and to limit the search space, the authors use databases as a priori knowledge to help the scene understanding. But, diversity and imprecision of information sources to process generate new problems. The fuzzy logic theory has proved in the last years its ability to solve a large range of problems concerning imprecision.
 

Dherete, P.; J. Desachy, (1998). Extraction of geographic features using multi-operator fusion. Image and Signal Processing for Remote Sensing IV Barcelona, Spain 21-23 Sept. 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.418-28.
Keywords: Dynamic programming; Feature extraction; Fuzzy logic; Geography; Geophysical signal processing; Image recognition; Remote sensing; Sensor fusion; Geographic features; Multi-operator fusion; Remote sensing images; Automatic analysis; Context diversity; Complexity of information; Scene understanding; Fuzzy logic theory; Imprecision; Extraction algorithms; Radiometry; Color; Linearity; Wrong detections; Generic models; Optimal path; Linear feature; Snake-like technique ; Erratic parts
Original abstract: Automatic analysis of remote sensing images faces different problems: context diversity, complexity of information. To simplify identification and to limit the search space, we use extra data and knowledge to help the scene understanding. Diversity and imprecision of information sources generate new problems. The fuzzy logic theory is used to solve the problem of imprecision. Many extraction algorithms are used to provide a more reliable result. Extraction may be performed either globally on the whole image or locally using information of data bases. Each extractor produces a map of certainty factors for a given type of geographic features according to their characteristics: radiometry, color, linearity, etc. Maps contain wrong detections due to imperfections of the detectors or non-completeness of generic models. So, we generate a new map using fusion to have a best credibility used to compute a dynamic programming. It finds an optimal path even if the linear feature is partially occluded. But the path is generally erratic due to noise. Then a snake-like technique to smooth the path to clean the erratic parts and to tune the level of detail required to represent the geographic features on a map of a given scale is given. The result is used to update data bases.
 

Di Carlo, W.; G. G. Wilkinson, (1996). Dominant linear feature detection in satellite images using a self-organizing neural network. Proceedings of the International Workshop on Soft Computing in Remote Sensing Data Analysis Milan, Italy 4-5 Dec. 1995
Singapore World Scientific, pp.73-9.
Keywords: Feature extraction; Image segmentation; Remote sensing; Self-organising feature maps; Dominant linear feature detection; Satellite images; Self-organizing neural network; Automatic geometrical feature detection; Geometrical rectification; Meaningful structure identification; Landscape; Mapping; Kohonen maps; Dominant linear segment detection ; Segmented binary images
Original abstract: The automatic detection of geometrical features in satellite images is an important requirement in remote sensing both for carrying out geometrical rectification and for identifying meaningful structures on the landscape in mapping studies. The paper describes an experimental study carried out at the Joint Research Centre to explore the use of Kohonen maps to detect dominant linear segments in binary images segmented from satellite images. This procedure forms part of a wider activity concerned with carrying out geometrical rectification of images.
 

Ding, C. (1998). The GIS-based human-interactive TAZ design algorithm: examining the impacts of data aggregation on transportation-planning analysis. Environment and Planning B-Planning & Design, V25, (N4): 601-616.
Keywords:
Original Abstract: An aggregate approach (traffic analysis zones, TAZs) has been used to conduct conventional transportation-planning analysis. The impact of a TAZ (sizes and boundaries) on traffic demand estimates and evaluation of transportation systems, however, has not been addressed adequately in the literature. In this paper I will attempt to examine the impact of spatial data aggregation on transportation by generating TAZ alternatives and building linkages among land use, transportation, and GIS. This paper consists of two major components. In the first, attention is focused on the discussion of the GIS-based interface system which links land use, transportation, and GIS. The GIS-based interface system also includes a GIS-based human-interactive TAZ design algorithm that generates TAZ alternatives. In the second, I concentrate on the examination of the impact of TAZs on transportation. This is conducted by simulations, which create TAZ alternatives and report final estimates of traffic demand and evaluation of transportation systems. It is concluded that spatial data aggregation affects the outcomes of transportation-planning models significantly, particularly when the number of TAZs is small.
 

dos Santos Mendonca, P. R.; A. C. Frery, (1998). Genetic-annealing parameter estimation for intensity SAR data. Second Latino-American Seminar on Radar Remote Sensing. Image Processing Techniques (ESA SP-434) Santos, Brazil 11-12 Sept. 1998
Noordwijk, Netherlands ESA, pp.37-43.
Keywords: Genetic algorithms; Maximum likelihood estimation; Radar imaging; Remote sensing by radar; Simulated annealing; Synthetic aperture radar; Genetic-annealing parameter estimation; Intensity SAR data; Maximum likelihood estimator; Distributional parameters; Optimisation problem; Objective function; Numerical instabilities; Stochastic optimisation ; Urban areas
Original abstract: Finding the maximum likelihood estimators for some distributional parameters of intensity data in synthetic aperture radar (SAR) images is a very difficult optimisation problem due to, among other reason, the presence of several local maxima in the objective function, the analytical intractability of the expressions involved and numerical instabilities. A possible approach to this problem is the use of stochastic optimisation techniques, such as simulated annealing and genetic algorithms, that do not get trapped into local maxima hills and, thus, make it possible to deal with very general distributions. This work shows the results of such approach in real situations, with images obtained from urban areas.
 

Doucelte, P.; P. Agouris; M. Musavi; A. Stefanidis, (1999). Automated extraction of linear features from aerial imagery using Kohonen learning and GIS data. Integrated Spatial Databases. Digital Images and GIS. International Workshop ISD'99. Selected Papers (Lecture Notes in Computer Science Vol.1737) Portland, ME, USA 14-16 June 1999
Berlin, Germany Springer-Verlag, pp.20-33.
Keywords: Feature extraction; Geographic information systems; Image classification; Image resolution; Network topology; Remote sensing; Self-organising feature maps; Unsupervised learning; Semi-automated linear feature extraction; Aerial imagery; Kohonen learning; Geographic information system; Coarse-resolution GIS vector data; Kohonen self-organizing map algorithm; Neural network; Competitive unsupervised learning; Radiometrically classified image pixels; Network topology initialization; Spatial structures; Network weight initialization; Synaptic weight vector updating; Winning neural units; 2D vector shape vertices; High-resolution hyperspectral imagery ; Center-line information extraction
Original abstract: An approach to semi-automated linear feature extraction from aerial imagery is introduced in which Kohonen's (1982) self-organizing map (SOM) algorithm is integrated with existing GIS data. The SOM belongs to a distinct class of neural networks which is characterized by competitive and unsupervised learning. Using radiometrically classified image pixels as input, appropriate SOM network topologies are modeled to extract underlying spatial structures contained in the input patterns. Coarse-resolution GIS vector data is used for network weight and topology initialization when extracting specific feature components. The Kohonen learning rule updates the synaptic weight vectors of winning neural units that represent 2D vector shape vertices. Experiments with high-resolution hyperspectral imagery demonstrate a robust ability to extract center-line information when presented with coarse input.
 

Dousset, B., (1995). Synthetic aperture radar imaging of urban surfaces: a case study. 1995 International Geoscience and Remote Sensing Symposium, IGARSS '95. Quantitative Remote Sensing for Science and Applications (Cat. No.95CH35770) Firenze, Italy 10-14 July 1995
New York, NY, USA IEEE, pp.2092-6 vol.3.
Keywords: Backscatter; Geophysical techniques; Hydrological techniques; Moisture measurement; Radar cross-sections; Radar imaging; Remote sensing by radar; Soil; Synthetic aperture radar; Geophysical measurement technique; Radar remote sensing; Hydrology; Land surface; Terrain mapping; Soil moisture; Water content; Urban area; California; United States; usa; SAR imaging; Urban surface; SAR image; Los Angeles basin; Backscatter intensity; Radar scattering; Smooth pavement; Asphalt; Road; Commercial area ; Azimuth dependence
Original abstract: A set of SAR images of the Los Angeles basin was analyzed to assess their potential to derive soil moisture, an important component of the surface energy balance in urban areas. Large variations of backscatter intensities were observed for different land uses and different SAR images. Low intensities were found over smooth pavement and asphalt. High intensities were found over industrial and commercial areas, with a marked illumination azimuth dependence for the latter; and maximum intensities were found when the flight direction was parallel to building alignments. A similar anisotropy occurred over residential areas, albeit at lower intensities. These contaminations mask the backscatter variations resulting from other processes, and may limit the estimation of soil moisture to undeveloped blocks and parks, unless a correction is applied.
 

Dow, J. W.; R. H. Stokes, (1995). AM/FM/GIS database population using integrated airborne remote sensing techniques. Proceedings AM/FM International. Conference XVIII AM/FM International Conference XVIII Baltimore, MD, USA 20-23 March 1995
Aurora, CO, USA AM & FM Int, pp.297-308.
Keywords: Altimeters; Costing; Geographic information systems; Global Positioning System; Remote sensing; Town and country planning; Visual databases; am/fm/gis; Visual database; Airborne remote sensing; Mapping; Facilities data; Decision processes; Cost; Data collection; Map data; Integrated sensor; Automated mapping facilities management; Steerable scanning laser altimeter; Differential Global Positioning System; Three-dimensional vector map data ; 3D vector map data
Original abstract: The AM/FM/GIS systems currently being employed by industry provide for the storage of mapping and facilities data which can be rapidly accessed and analyzed in support of decision processes. Currently this data is obtained using methods that often result in inaccuracies and increased cost. In addition, the data must constantly be updated to reflect changes in the physical environment. Therefore, a need has arisen to convert to an automated data collection procedure whereby accurate map data can be collected in a cost effective, timely, and reoccurring manner. A current method for conversion employs an airborne platform populated with an integrated sensor package specifically designed to obtain and record imagery and three-dimensional (i.e., height and location) map data. The types of imagery obtainable extend from the visible through the infrared range. The mapping system is a steerable, scanning laser altimeter coupled with a differential GPS to provide accurate three-dimensional vector map data. This data is the digital elevation and location of items scanned and is directly loadable into AM/FM/GIS systems for immediate database population and maintenance.
 

Dowman, I.; A. Holmes; V. Vohra, (1995). Developments in automated object-image registration. Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision II Orlando, FL, USA 19-21 April 1995
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.85-92.
Keywords: Feature extraction; Forestry; Image registration; Photogrammetry; Remote sensing; Automated object-image registration; Knowledge based approach; Features identification; Polygons; Distinctive shape; Raster data; Forest areas; Image to map registration ; High resolution satellite imagery
Original abstract: There is considerable activity at present in feature extraction using a knowledge based approach. Much of this work is concerned with identifying the features. In the work described in this paper the main interest is in extracting features which can be matched on an image and a map. The emphasis is on polygons which have a distinctive shape and can be extracted from vector as well as raster data. An algorithm has been developed and tested which automatically matches forest areas on a map with forest areas on and image in two dimensions. This algorithm is being developed for more general use so that the problem of image to map registration can be automated in a general way. Results are given on the use of the algorithm to identify changes in forestry from Landsat Thematic Mapper data and developments which can match buildings on high resolution satellite imagery are reported. An overall strategy for full automation is presented and discussed and future developments considered.
 

Drake, N. A.; S. Mackin; J. J. Settle (1999). Mapping vegetation, soils, and geology in semiarid shrublands using spectral matching and mixture modeling of SWIR AVIRIS imagery. Remote Sensing of Environment, V68, (N1): 12-25.
Keywords: AVIRIS , spectral matching, linear mixture modeling techniques
Original Abstract: Spectral matching and linear mixture modeling techniques have been applied to synthetic imagery and AVIRIS SWIR imagery of a semiarid rangeland in order to determine their effectiveness as mapping tools, the synergism between the two methods, and their advantages, and limitations for rangeland resource exploitation and management. Spectral matching of pure library spectra was found to be an effective method of locating and identifying endmembers for mixture modeling although some problems were found with the false identification of gypsum. Mixture modeling could accurately estimate proportions for a large number of materials in synthetic imagery; however, it produced high variance estimates and high error estimates when presented with all nine AVIRIS endmembers because of high noise levels in the imagery. The problem of which endmembers to select was addressed by implementing a mixture model that allowed estimation of the errors on the proportions estimates, discarding the endmembers with the highest errors, recomputing the errors, and the proportions estimates, and iterating this process until the mixture maps were relatively free from noise. This methodology ensured that the lowest contrast materials were discarded. The inevitable confusion that followed was monitored the using the maps produced by spectral matching. Spectral matching was more effective than mixture modeling for geological mapping because it allowed identification and mapping of the relatively pure regions of all the surficial materials that exert an influence on the spectral response. The maps of the different clay minerals were of considerable value for mineral exploration purposes. Conversely, spectral matching was less useful than mixture modeling for rangeland vegetation studies because a classification of all pixels is needed and abundance estimates are required for many applications. Mixture modeling allowed identification of both nonphotosynthetic and green vegetation cover and thus total cover. Though the green vegetation mixture map appears to be very precise, the nonphotosynthetic vegetation estimates were poor.
 

Du, Q.; C. I. Chang (2001). A linear constrained distance-based discriminant analysis for hyperspectral image classification. Pattern Recognition, V34, (N2): 361-373.
Keywords: AI/Robotics/Automatic Control
 
 

Du, Q.; I. C. Chein; D. C. Heinz; M. L. G. Althouse; I. W. Ginsberg, (2000). A linear mixture analysis-based compression for hyperspectral image analysis. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.585-7 vol.2.
Keywords: Data compression; Geophysical signal processing; Geophysical techniques; Image classification; Image coding; Multidimensional signal processing; Remote sensing; Terrain mapping; Geophysical measurement technique; Land surface; Linear mixture analysis; Image compression; Hyperspectral image; Least squares linear spectral mixture analysis; Target detection; aviris; High compression ratio; Optical image ; Multispectral remote sensing
Original abstract: The authors present a fully constrained least squares linear spectral mixture analysis-based compression technique for hyperspectral image analysis, particularly, target detection and classification. Unlike most compression techniques that directly deal with image gray levels, the proposed compression approach generates the abundance fractional images of potential targets present in an image scene and then encodes these fractional images so as to achieve data compression. Since the vital information used for image analysis is generally preserved and retained in the abundance fractional images, the loss of information may have very little impact on image analysis. In some occasions, it even improves analysis performance. AVIRIS data experiments demonstrate that it can effectively detect and classify targets while achieving very high compression ratios.
 

Duan, L.; Y. Bao; W. Zhang (1998). GPS vehicle navigation system. Transactions of Nanjing University of Aeronautics & Astronautics, 15, (2): 172-8.
Keywords: Automated highways; Computerised navigation; Geographic information systems; Global Positioning System; Real-time systems; Road traffic; GPS vehicle navigation; Intelligent vehicle navigation; Urban fields; Inter-province; Inter-state transport; City geographical information system; Real-time correction ; Transportation
Original Abstract: This paper introduces the GPS intelligent vehicle navigation system (IVNS). This system can be widely applied to the urban fields, inter-province and inter-state transport which, as a part of intelligent transport systems (ITS), would contribute toward improving troublesome driving conditions on driver's benefits. The paper discuss as two key techniques; city geographical information system (GIS), real-time correction of the deviation.
 

Ducksbury, P. G.; D. M. Booth; C. J. Radford, (1995). Vehicle detection in infrared linescan imagery using belief networks. Fifth International Conference on Image Processing and its Applications (Conf. Publ. No.410) Fifth International Conference on Image Processing and its Applications (Conf. Publ. No.410) Edinburgh, UK 4-6 July 1995
London, UK IEE, pp.415-19.
Keywords: Bayes methods; Feature extraction; Image classification; Image segmentation; Infrared imaging; Object detection; Remote sensing; Tracking; Vehicle detection; Infrared linescan imagery; Belief networks; Airborne downward looking imagery; Pearl-Bayes network; Vehicle track detectors; Shadow detectors; Contextual evidence; Neighbouring detections ; Feedback loop
Original abstract: This paper describes a system for detecting vehicles in airborne downward looking infrared linescan imagery, and in particular, the use of a Pearl-Bayes Network (PBN) to combine disparate sources of evidence. Here the primary source of evidence is a vehicle detection algorithm with supporting evidence being provided by vehicle track and shadow detectors. The spatial arrangement of the vehicles also provides useful contextual evidence since vehicles often move in convoy or are clustered into small groups when encamped. This observation is the basis for allowing neighbouring detections to re-enforce one another and for incorporating a feedback loop with which to increase the sensitivity of the vehicle detection algorithm within areas of suspected activity.
 

Dueker, K. J.; J. A. Butler (2000). A geographic information system framework for transportation data sharing. Transportation Research Part C (Emerging Technologies), 8C, (1-6): 13-36.
Keywords: Data models; Geographic information systems; Traffic information systems; Transaction processing; Transportation; Geographic information system framework; Transportation data sharing; Data producers; Data integrators; Data users; Enterprise geographic information systems-transportation; GIS-T data model; Transportation data elements; Transportation features; Common data model; Graphical representations; Point events; Linear referencing; Relevant transportation features; Application-specific databases; Transactional update system; Feature-oriented enterprise GIS-T database ; Application-specific network databases
Original Abstract: The paper develops a framework and principles for sharing transportation data. The framework is intended to clarify roles among participants, data producers, data integrators, and data users. The principles are intended to provide guidance for the participants. Both the framework and the principles are based on an enterprise geographic information systems-transportation (GIS-T) data model that defines relations among transportation data elements. The data model guards against ambiguities and provides a basis for the development of the framework and principles for sharing transportation data. There are two central principles. First is the uncoupling of graphics, topology, position, and characteristics, Second is the establishment of a schema for transportation features and their identifiers. An underlying principle is the need for a common data model that holds transportation features, not their graphical representations, as the objects of interest. Attributes of transportation features are represented as linear and point events. These are located along the feature using linear referencing. Sharing of transportation data involves exchange of relevant transportation features and events, not links and nodes of application-specific databases. Strategies for sharing transportation features follow from this approach. The key strategy is to identify features in the database to facilitate a transactional update system, one that does not require rebuilding the entire database anew. This feature-oriented enterprise GIS-T database becomes the basis for building separate application-specific network databases.
 

Dueker, K. J.; J. A. Butler (1998). GIS-T enterprise data model with suggested implementation choices. URISA Journal, 10, (1): 12-36.
Keywords: Cartography; Data models; Geographic information systems; Transportation; Travel industry; Visual databases; gis-t; Enterprise data model; Digital road map databases; Organizations; User requirements; Location referencing systems; Interoperability ; Geometry
Original Abstract: Sharing of digital road map databases within and among organizations is dependent on translating user requirements to a data model that supports linear and non-linear location referencing systems. This paper examines issues of creating such a data model with the intent of sharing digital road map databases, and suggests implementation choices that can accommodate a range of applications. The proposal is best characterized as a GIS-T enterprise data model suitable for organizations responsible for any and all modes of transportation; e.g., aviation, highways, public transit, and railways. The proposed data model may be sufficiently robust to support ITS map database interoperability by maintaining independence among the geographic datum, the events that occur on the transportation system, the geometry to represent the system cartographically, and the paths through the system. Sample physical database designs are provided to show how the model might be implemented.
 

Duff, K.; M. Hyzak
TFHRC
Structural Monitoring with GPS
Turner-Fairbank Highway Research Center (TFHRC)
http://www.tfhrc.gov/pubrds/spring97/gps.htm
Keywords: structural monitoring, GPS
 
 

Duggin, M. J.; J. A. North; E. Bohling; T. Birdsall; S. Bisgrove, (1997). Contrast enhancement in natural scenes using multiband polarization methods. Polarization: Measurement, Analysis, and Remote Sensing San Diego, CA, USA 30 July-1 Aug. 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.288-95.
Keywords: CCD image sensors; Feature extraction; Focal planes; Geophysical signal processing; Image enhancement; Natural scenes; Object recognition; Polarimetry; Remote sensing; Contrast enhancement; Multiband polarization methods; Digital imaging cameras; Linear drivers; Multiband imaging polarimeter; Digital image acquisition; Quantitative method; Target discrimination; Feature recognition; Shadow penetration; Terrestrial images; Digital photography; ccd fpa ; Polarimetric mapping
Original abstract: Relatively little work has been performed to investigate the potential of polarization techniques to provide contrast enhancement in natural scenes. Largely, this is because film is less accurate radiometrically than digital CCD FPA sensing devices. Such enhancement is additional to that provided by between-band differences for multiband data. Recently, Kodak has developed several digital imaging cameras which were intended for professional photographers. However, the application of linear drivers to read the data from the camera into the computer has resulted in a device which can be used as a multiband imaging polarimeter. Here we examine the potential of digital image acquisition as a potential quantitative method to obtain new information additional to that obtained by multiband or even hyperspectral imaging methods. We present an example of an active on-going research program.
 

Duncan, G.; W. Heidbreder; C. Szpak; J. Hammack; B. Morey, (1998). A multilevel technique for image enhancement improvement using RADARSAT. Algorithms for Multispectral and Hyperspectral Imagery IV Orlando, FL, USA 13-14 April 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.86-99.
Keywords: Feature extraction; Geophysical signal processing; Image enhancement; Image recognition; Radar imaging; Remote sensing by radar; Multilevel technique; Image enhancement improvement; radarsat; Image quality improvement; Extraction; Map features; Sensor imagery; Visual metrics; Shoreline categorization ; Delineation
Original abstract: This paper presents an image quality improvement approach for extraction of map features based on single and multisensor image enhancement techniques. The approach relies upon the evaluation of sensor imagery for extraction of map features based on its sensor characteristics. The approach is illustrated by evaluation results for RADARSAT using two visual metrics. Samples of single sensor and multiband enhancement results are presented for a range of map features. Features include those essential for shoreline categorization and delineation for support of environmental applications.
 

Duncan, G.; W. H. Heidbreder; J. Hammack; C. Szpak, (1997). Map feature examination of RADARSAT for geospatial utility and imagery enhancement opportunities. Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision III Orlando, FL, USA 21-23 April 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.55-66.
Keywords: Cartography; Feature extraction; Geography; Geophysical signal processing; Image enhancement; Radar imaging; Remote sensing by radar; Map feature examination; radarsat; Geospatial utility enhancement; Geospatial imagery enhancement; Multisensor tests; Multisensor enhancement techniques; Data collection; Data analysis ; Product-source prediction capability
Original abstract: This paper discusses multisensor tests conducted to examine the geospatial information potential of RADARSAT imagery. The focus of the tests is to develop a metric for determining which map features present in optical or radar imagery could benefit from the use of multisensor enhancement techniques. Visual and geospatial differences between optical and radar imagery are studied. Data collection and analysis are based on a product-source prediction capability (PSPC) and other related modeling and analysis tools.
 

Duskunovic, I.; G. Heene; W. Philips; I. Bruyland, (2000). Urban area detection in SAR imagery using a new speckle reduction technique and Markov random field texture classification. IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120) Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, v.2, pp.636-8.
Keywords: SAR imagery Urban area detection, Speckle reduction, Markov random field,Texture classification
Synopsis: The authors introduce a speckle reduction technique to reduce the effects of scatter interference in SAR data. They then use the Markov Random Field texture classification method for urban dectection. Results show that classification is more accurate when their speckle reduction technique is used as compared to traditional speckle filters.
Original abstract: The strength of synthetic aperture radar (SAR) as a land observation tool resides in S. Gautama et al. (1998) the sensitivity of radar backscatter to the moisture content of terrain media and to the geometrical parameters of the scatterers in the media (i.e., size, shape, roughness and orientation), and (2) an all-weather, day or night imaging capability. However, SAR images are degraded by multiplicative speckle noise due to interference between individual scatterers within one resolution cell. The authors first propose a new speckle reduction method, which preserves edges and doesn't need parameters to be adjusted, based on wavelet decomposition. Comparison with standard speckle filters shows that their filter removes speckle better, while preserving the same amount of detail. Next they use the filter technique in combination with the Markov random field (MRF) texture classification as stated in by S. Gautama et al. (1998) to detect urban areas in the images. The results show that classification results are better when using their proposed filter, compared to the classification results with images filtered with standard speckle filters.
 

Dutra, L. V.; R. Huber; P. Hernandez, (1998). Primary forest and land cover contextual classification using JERS-1 data in Amazonia, Brazil. IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174) Seattle, WA, USA 6-10 July 1998
New York, NY, USA IEEE, pp.2743-5 vol.5.
Keywords: Feature extraction; Forestry; Geophysical signal processing; Geophysical techniques; Geophysics computing; Image classification; Multilayer perceptrons; Radar imaging; Remote sensing by radar; Spaceborne radar; Synthetic aperture radar; Terrain mapping; Vegetation mapping; Geophysical measurement technique; Land surface; Forest; Radar remote sensing; Land cover contextual classification; sar; L-band; jers-1; Amazonia; Amazon; Brazil; Image texture; Image feature; Neural net; Neural network; Multilayer perceptron; Contextual method; Tapajos National Forest ; Para State
Original abstract: The authors present a methodology for land cover and primary forest mapping in Amazonia using textural features derived from JERS-1 data and classified with a multilayer perceptron based contextual method. Land cover classification is an important step towards the use of radar data as a tool for land use change studies in Amazonia. Also, primary forest classification is an important issue in ecosystem studies and economical assessment of sustainable timber exploitation. The use of radar data, particularly L-band data, is justifiable as large Amazonian area is permanently cloud covered. Considering a set of primary forest and land use classes of interest in the Tapajos National Forest and adjacent regions, Para State, Brazil, it was investigated which classes could be distinguished using textural features derived by co-occurrence and matched filtering techniques. Nondiscriminating classes were grouped together to form new classes resulting in two classes of primary forest, three classes of land use, water and aquatic vegetation. The feature set with higher overall accuracy was used to classify a small mosaic of the region, using a contextual neural network based classifier with 87% overall accuracy.