El-Khattib, H. M.; N. M. El-Mowelhi; A. A. El-Salam, (1997). Desertification
and land degradation using high resolution satellite data in the Nile Delta,
Egypt. 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.197-9 vol.1.
Keywords: Agriculture; Geomorphology; Pollution; Remote sensing;
Soil; North Africa; Rural area; Land surface; Arid region; Desert; Desertification;
Land degradation; Nile Delta; Egypt; Remote sensing observations; Soil
salinity; Agricultural land; Lake Manzala; ad 1992; ad 1995; Urban area;
ad 1963; Salinization; Urbanization; Cultivated land ; Vegetation
Original abstract: Recently, recognition of the severity of the desertification
problems in Egypt began to grow. Remote sensing data of different spectral,
spatial and temporal resolutions and other ancillary data were used, including
LANDSAT and SPOT images, topographic maps, soil survey studies conducted
in 1963. Cases of land degradation and desertification in Egypt, especially
soil salinity and urban desertification, are increasingly visible. The
current investigation aims at studying desertification and soil degradation
of agricultural lands in the north eastern part of the Nile Delta, adjacent
to lake Manzala, Egypt. Modern techniques and most-up to date of satellite
data using Multitemporal image processing analysis and the data were combined
in CARIS GIS software for land degradation processes and calculations.
Pedological, physiographic features and soil profiles were carefully studied
with guidance of SPOT image for 1992 and LANDSAT TM for 1995. Soil samples
were analyzed, maps of salinity and urban areas were carried out. The obtained
results was compared with data collected on the same area in 1963 by the
soil survey research department of the Soil, Water and Environment Research
Institute (SWERI). Salinity and sodicity of soil was increased during the
1963-1992 period. Most of substantial changes in land degradation phenomenon
in both soil salinization and urbanization are expected in the north eastern
part of the Nile Delta in Egypt. Multitemporal images were processed for
12 settlements (villages and towns) for the period of 1952, 1963 and 1992,
there were considerable 1952 urban expansion of using 40 years. The magnitude
of increase in 1992 compared with 1952 was 1.1 to as high as 46 folds.
Soil degradation and urban encroachment onto cultivated land are loss of
productive lands as well as low values of NDVI are expected.
Elvidge, C. D.; Z. K. Chen; D. P. Groeneveld (1993). Detection of
Trace Quantities of Green Vegetation in 1990 Aviris Data. Remote
Sensing of Environment, V44, (N2-3): 271-279.
Keywords: AVIRIS , feature classification
Engdahl, M.; J. Hyyppa, (2000). Temporal averaging of multitemporal
ERS-1/2 Tandem INSAR 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.2224-6 vol.5.
Keywords: Geophysical techniques; Remote sensing by radar; Spaceborne
radar; Synthetic aperture radar; Terrain mapping; Geophysical measurement
technique; Land surface; Land use; Radar remote sensing; Temporal averaging;
Multitemporal; ers-2; ers-1; Tandem; insar; SAR interferometry; Classification
; Urban
Original abstract: In this study the potential of multitemporal ERS-1/2
SAR Tandem interferometry in land-use classification was investigated.
Emphasis was on classifying land-use near urban centres, where the land-use
features are typically small and high resolution is therefore desired.
A high-quality orthorectified multitemporal interferometric dataset was
created for further study. Temporal averaging, i.e. averaging over several
intensity and coherence images reduces noise and increased the amount of
discernible features without degrading the image resolution. At this stage
of the study only visual classification has been done, temporal averaging
was found to increase the number of visually discernible classes in the
imagery.
Euisun, C.; L. Chulhee (2001). Optimizing feature extraction for
multiclass problems. IEEE Transactions on Geoscience and Remote
Sensing, 39, (3): 521-8.
Keywords: Feature extraction; Optimisation; Remote sensing; Feature
extraction optimization; Multiclass problems; Pattern classification; Feature
extraction method; Classification accuracies; Remotely sensed data ; Algorithm
Original Abstract: Feature extraction has been an important research
topic in pattern classification and has been studied extensively by many
researchers. Most of the conventional feature extraction methods are performed
using a criterion function defined between two classes or a global function.
Although these methods work relatively well in most cases, it is generally
not optimal in any sense for multiclass problems. In order to address this
problem, the authors propose a method to optimize feature extraction for
multiclass problems. The authors first investigate the distribution of
classification accuracies of multiclass problems in the feature space and
find that there exist much better feature sets that the conventional feature
extraction algorithms fail to find. Then the authors propose an algorithm
that finds such features. Experiments with remotely sensed data show that
the proposed algorithm consistently provides better performances compared
with the conventional feature extraction algorithms.
Euisun, C.; L. Chulhee, (2000). Feature extraction based on the Bhattacharyya
distance. 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.2146-8 vol.5.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Remote sensing; Terrain mapping; Geophysical
measurement technique; Land surface; Image processing; Bhattacharyya distance;
Classification error; Gaussian ML classifier; Feature vector ; Multiclass
problem
Original abstract: The authors propose a feature extraction method
based on the Bhattacharyya distance. Recently, it has been reported that
an accurate estimation of classification error is possible using the Bhattacharyya
distance. In the proposed method, the authors try to find feature vectors
that minimize the estimated classification error of Gaussian ML classifier.
In order to find such feature vectors, they start with arbitrary initial
feature vectors and update them using two optimization techniques: sequential
search and global search. Since they use the error estimation equation
for updating feature vectors, the search time can be reduced significantly.
They first apply the algorithm to two class problems and extend it to multiclass
problems. Experimental results show that the proposed feature extraction
algorithm compares favorably with conventional feature extraction algorithms.
Evans, T. P.; S. J. Walsh; B. Entwisle; R. R. Rindfuss, (1995). Testing
model parameters of transportation network analyses in rural Thailand.
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.302-11 vol.1.
Keywords: Geographic information systems; Health care; Sensitivity
analysis; Statistics; Transportation; Model parameter testing; Transportation
network analyses; GIS environment; Geographic information system; Geographic
accessibility; Family planning; Remote villages; Health care facilities;
Thailand Nang Rong; Longitudinal survey data; Topographic maps; Road surface
type; Passable seasons; Network routing model peformance; Travel assumptions;
Travel speeds; Road closure; Flooding; Spatial interaction weighting schemes;
Descriptive statistics; Euclidean distance ; Skewed travel time distribution
Original abstract: Network analysis techniques implemented within a
GIS environment are used to assess the geographic accessibility of villages
to health care facilities in Nang Rong district, Thailand. Data for the
research consists of longitudinal survey data at the village level and
transportation network data digitized from topographic maps that classify
roads by surface type and seasons passable. A sensitivity analysis is used
to determine the performance of the network routing model as a consequence
of travel assumptions and scenarios. This work uses network analysis to
measure the travel times between 51 rural villages and 42 health care centers
in the study area. Various scenarios are used to test the sensitivity of
the analysis to different model parameters including variations in travel
speeds for different road types, closure of roads due to flooding, and
spatial interaction weighting schemes. Descriptive statistics are used
to evaluate the sensitivity of the network analysis to model parameters.
Sensitivity analyses showed that Euclidean distance skewed the distribution
of travel time to the closest health center, making remote villages appear
more isolated. Network analysis was used to evaluate the nature of family
planning accessibility by varying travel scenarios involving travel characteristics
and road conditions. Information on road type, seasonality and mode of
transportation are important considerations in modelling accessibility,
particularly in the rural environment of Nang Rong.
Farison, J. B.; U. Vanjara; E. Merenyi, (2000). AVIRIS image compression
with orthogonal projection and KL transforms. Proceedings of the IASTED
International Conference. Signal and Image Processing Proceedings of 2000
Conference on Signal and Image Processing Las Vegas, NV, USA 19-23 Nov.
2000
Anaheim, CA, USA IASTED/ACTA Press, pp.52-7.
Keywords: Data compression; Feature extraction; Image coding; Image
sequences; Infrared imaging; Infrared spectroscopy; Karhunen-Loeve transforms;
Remote sensing; Visible spectroscopy; AVIRIS image compression; Airborne
visible/infrared imaging spectrometer; Orthogonal projection transform;
Karhunen-Loeve transform; Hyperspectral images; Feature separation; Spatially
invariant image sequences; Linearly additive image sequences; Spatial distributions;
Imaging signatures; Spectral signatures; Spatial distribution maps ; Optimal
compression technique
Original abstract: The orthogonal projection (OP) transform has been
applied to AVIRIS (airborne visible/infrared imaging spectrometer) hyperspectral
images for feature separation. The method is based on a mathematical model
for spatially invariant, linearly additive image sequences which describes
the image sequence in terms of the spatial distributions and imaging signatures
of the distinct features present in the image scene. The OP transform uses
the spectral signatures of the image features to transform the original
image sequence into the respective spatial distribution maps of the separate
features, from which the original image sequence can be reconstructed.
The Karhunen-Loeve transform (KLT) is an optimal compression technique
based on the statistical variance of the data. The KLT is characterized
by its ability to compact the information content in an image set into
its first few principal components. However, it does not isolate the distinctive
features of the image data. The focus of this paper is to compare the results
of the two methods as applied to an AVIRIS image sequence.
Farrall, M. H.; M. Painho; L. T. Vasconcelos; M. R. Paiva, (1996). Spatial
scale analysis of landscape fragmentation due to transport corridors.
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.602-10 vol.1.
Keywords: Ecology; Geographic information systems; Sensitivity analysis;
Statistics; Town and country planning; Transportation; Spatial scale analysis;
Landscape fragmentation; Transport corridors; Environmental problems; Europe;
Linear features; Transport infrastructures; Ecosystem threats; Habitats;
Species conservation; Geographic information system; Professional decisions;
Landscape structure; Influence zone; Patch boundaries ; Natural areas
Original abstract: Landscape fragmentation has become one of the major
environmental problems in Europe. Unfortunately, when assessing the spatial
characteristics of a landscape, linear features like roads and railways
are often not included in the analysis. The investment in transport infrastructures
is now creating additional threats to existing ecosystems. Major consequences
of transport corridor implementation include direct fragmentation of habitats
and the subsequent alteration of the landscape structure. Due to differences
in the scales at which organisms perceive the environment, responses to
landscape patterns vary among species. Conservationists, ecological consultants
and planners must usually rely on intuition to make decisions that could
influence the survival of animal populations. With a GIS, it becomes easier
to provide spatial information to guide the decisions of professionals
working in the area of the environment. This study addresses the question
of how incorporating transport corridors in the analysis affects landscape
structure over a range of spatial scales. The computed landscape metrics
included edge, shape, core area and contagion statistics. Sensitivity analysis
was performed on two buffer areas-the transport corridor's influence zone
and patch boundaries. A critical analysis was made, comparing the advantages
and deficiencies of the utilized indices, due to variations inflicted by
changes of these factors. This analysis specifically targets natural areas.
A discussion of the behavior of indices according to the modification of
several factors was conducted.
Farrand, W. H.; R. B. Singer; E. Merenyi (1994). Retrieval of Apparent
Surface Reflectance from Aviris Data - a Comparison of Empirical Line,
Radiative Transfer, and Spectral Mixture Methods. Remote Sensing
of Environment, V47, (N3): 311-321.
Keywords:
Fayek, R. E.; A. K. C. Wong, (1996). Extracting buildings from aerial
topographic maps. International Conference on Image Processing (Cat.
No.96CH35919) Proceedings of 3rd IEEE International Conference on Image
Processing Lausanne, Switzerland 16-19 Sept. 1996
New York, NY, USA IEEE, pp.401-4 vol.2.
Keywords: Building; Feature extraction; Image segmentation; Inference
mechanisms; Mesh generation; Object recognition; Remote sensing; Aerial
topographic maps; 2D information recovery; Intensity images; 3D information;
Range images; 3D object recognition; Sensory data; Remote sensing aerial
images; 2D intensity images; 3D data; Symbolic information extraction;
3D triangular mesh models; Symbolic reasoning; Generic object models ;
Image regions
Original abstract: The recovery of 2D information from intensity images,
and that of 3D information from range images are the major issues in 3D
objects recognition from sensory data. The analysis and interpretation
of remote sensing aerial images have important applications. This paper
presents an efficient method for the analysis and modeling of such scenes
based on range sensory data. Unlike methods using 2D intensity images,
we exploit the rich 3D data. We extract symbolic information from the 3D
triangular mesh models. These are used to recognize buildings using symbolic
reasoning and generic object models.
Fern, A.; M. T. Musavi; J. Miranda (1998). Automatic extraction of
drainage network from digital terrain elevation data: a local network approach.
IEEE Transactions on Geoscience and Remote Sensing, 36, (3):
1007-11.
Keywords: Feature extraction; Geomorphology; Geophysical signal
processing; Geophysical techniques; Geophysics computing; Hydrological
techniques; Image processing; Rivers; Topography (Earth); Hydrology; Remote
sensing; Automatic extraction; Drainage network; River; Digital terrain
elevation data; Local network approach; Locally connected processing unit;
Global problem ; Land surface topography
Original Abstract: A local network for the automatic extraction of
drainage networks from elevation data is described. The methodology demonstrates
how a large number of locally connected processing units can solve the
global problem of drainage network extraction. The methodology has advantages
over previous methods and is able to extract lakes as well as streams and
rivers.
Ferretti, A.; F. Ferrucci; C. Prati; F. Rocca, (2000). SAR analysis
of building collapse by means of the permanent scatterers technique.
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.3219-21 vol.7.
Keywords: Geophysical techniques; Remote sensing by radar; Surveying;
Synthetic aperture radar; Terrain mapping; Geophysical measurement technique;
Land surface; Building; Buildings; Collapse; Urban area; Town; City; Radar
remote sensing; sar; Permanent scatterers technique; Deformation; DInSAR;
Differential InSAR; Terrain motion; Line of sight; Camaiore; Milano; Milan;
Paris; Precursory motion; Italy; Spain ; Precursor
Original abstract: As already shown in previous papers, detection of
stable areas make it possible to use DInSAR techniques to get local measurements
on a pixel-by-pixel basis. Reliable deformation measurements can then be
obtained on a subset of image pixels, called Permanent Scatterers (PS).
These points can be used as a "natural GPS network" to monitor terrain
motion in the direction of the line of sight (LOS), analyzing the phase
history of each one. In urban areas most of the PS correspond to single
buildings whose deformation can be measured every 35 days with an accuracy
better than one millimeter. Results obtained ERS SAR images are presented
for 3 test sites: Camaiore (40 images), Milano (62 images) and Paris (64
images). Time series analysis of collapsed buildings in Camaiore are illustrated
which show interesting precursory motions. Time series analysis of two
metallic buildings in Milano and Paris are then used to validate the technique
and to estimate its accuracy.
Ferretti, A.; C. Prati; F. Rocca, (2000). Nonlinear subsidence rate
estimation using permanent scatterers in differential SAR interferometry.
IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99
Hamburg, Germany 28 June-2 July 1999
IEEE Trans. Geosci. Remote Sens. (USA), pp.2202-12.
Keywords: Geodesy; Geophysical techniques; Remote sensing by radar;
Synthetic aperture radar; Tectonics; Terrain mapping; Uplift; Downlift;
Geophysical measurement technique; Radar remote sensing; InSAR; Nonlinear
subsidence rate estimation; Permanent scatterer; Differential SAR interferometry;
Urban area; Absidence; Subsidence; Atmospheric phase contribution; Nonlinear
motion ; Phase unwrapping
Original abstract: Discrete and temporarily stable natural reflectors
or permanent scatterers (PS) can be identified from long temporal series
of interferometric SAR images even with baselines larger than the so-called
critical baseline. This subset of image pixels can be exploited successfully
for high accuracy differential measurements. The authors discuss the use
of PS in urban areas, like Pomona, CA, showing subsidence and absidence
effects. A new approach to the estimation of the atmospheric phase contributions,
and the local displacement field is proposed based on simple statistical
assumptions. New solutions are presented in order to cope with nonlinear
motion of the targets.
Finch, J.; A. Reid; G. Roberts (1989). The Application of Remote
Sensing to Estimate Land Cover for Urban Drainage Catchment Modelling.
Journal of the Institution of Water and Environmental Management,
V3, (N6): 558-563.
Keywords:
Fischer, A.; T. H. Kolbe; F. Lang; A. B. Cremers; W. Forstner; L. Plumer;
V. Steinhage (1998). Extracting buildings from aerial images using hierarchical
aggregation in 2D and 3D. Computer Vision and Image Understanding,
72, (2): 185-203.
Keywords: Computer vision; Feature extraction; Image reconstruction;
Logic programming; Object recognition; Remote sensing; Stereo image processing;
Aerial images; Building extraction; Model-based method; 3D images; Data-driven
process; Model-driven process; Multilevel aggregation hierarchy; Multiple
image correspondence ; Constraint logic programming
Original Abstract: We propose a model-based approach to automated 3D
extraction of buildings from aerial images. We focus on a reconstruction
strategy that is not restricted to a small class of buildings. Therefore,
we employ a generic modeling approach which relies on the well-defined
combination of building part models. Building parts are classified by their
roof type. Starting from low-level image features we combine data-driven
and model-driven processes within a multilevel aggregation hierarchy, thereby
using a tight coupling of 2D image and 3D object modeling and processing,
ending up in complex 3D building estimations of shape and location. Due
to the explicit representation of well-defined processing states in terms
of model-based 2D and 3D descriptions at all levels of modeling and data
aggregation, our approach reveals a great potential for reliable building
extraction.
Fiset, R.; F. Cavayas (1997). Automatic comparison of a topographic
map with remotely sensed images in a map updating perspective: The road
network case. International Journal of Remote Sensing, V18,
(N4): 991-1006.
Keywords:
Original Abstract: A map guided procedure to automatically extract
the road network from SPOT-HRV panchromatic images is proposed in a topographic
map revision perspective. This procedure allows highly accurate results
to be obtained independently of the density and the shape of the road network.
The procedure is described in detail, along with our conclusions concerning
the optimal conditions of its application. Some preliminary results are
also shown concerning the introduction of a back-propagation neural network
to extract the road network. This approach is considered to eliminate the
problems associated with the grey level value and edge intervals. In the
proposed procedure these intervals are necessary to detect the roads and
must be specified every time to adapt to the particular radiometric content
of a new image.
Fiset, R.; F. Cavayas; M. C. Mouchot; B. Solaiman; R. Desjardins (1998).
Map-image matching using a multi-layer perceptron: the case of the road
network. Isprs Journal of Photogrammetry and Remote Sensing,
V53, (N2): 76-84.
Keywords: map updating feature extraction, satellite imagery; road
extraction; neural network; template matching; map updating
Synopsis: This article describes a method of automated map revision
(scale 1:50,000) where new roads can be added to a map database. Roads
are matched using a multi-layer perceptron (MLP) which corresponds segments
from SPOT-HRV panchromatic images to segments in a map database. New roads
can then be extracted from the images.
Original Abstract: To help automatize map revision at a scale of 1
: 50,000, a map-guided method is described to update the road network of
a map database. This paper describes the essential first step of the procedure,
which consists of matching the roads present on both the image and the
map database. This matching has to be performed precisely in order to generate
meaningful hypotheses on the location of new roads. The matching is conducted
by using a multi-layer perceptron (MLP) trained to recognize road segments
on the SPOT-HRV panchromatic image corresponding to the cartographic database
being treated. Two template matching methods using the trained MLP weight
matrix are developed. The first method locates all the road intersections
on the image, while the second method locates the segments only. Both methods
are not accurate enough to be used alone. However, combining both approaches
gives results that are reliable enough to be used in the generation of
the hypotheses needed to extract new roads.
Fiset, R.; F. Cavayas; M. C. Mouchot; B. Solaiman; R. Desjardins, (1996).
An automatic road extraction method using a map-guided approach combined
with neural networks for cartographic database validation purposes.
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.236-8 vol.1.
Keywords: Cartography; Feature extraction; Geophysical signal processing;
Geophysical techniques; Geophysics computing; Neural nets; Geophysical
measurement technique; Map-guided approach; Remote sensing; Terrain mapping;
Automatic road extraction method; Image processing; Neural network; Neural
net; Cartographic database validation; Road intersection; SPOT panchromatic
image; Optical imaging; Planimetric accuracy; Land surface; Urban area
; Town city
Original abstract: A method is proposed to extract road intersections
from a SPOT panchromatic image, using a map-guided approach combined with
the application of a neural network. The results show an average increase
of 36% of planimetric accuracy after applying the method instead of simply
superimposing the roads on the geocoded image. Also, only 8 out 42 samples
were previously correctly traced, compared to 27 after application of the
algorithm.
Fletcher, E. J.; I. Busby; D. Wheatley, (1995). Intelligent support
tools for the exploitation of a network referenced database system for
urban highways. *Steps Forward'. Proceedings of the Second World Congress
on Intelligent Transport Systems *95 Yokohama Proceedings of 2nd World
Congress on Intelligent Transport Systems Yokohama, Japan 9-11 Nov. 1995
Tokyo, Japan Vehicle, Road & Traffic Intelligence Soc, pp.1652-6
vol.4.
Keywords: Data acquisition; Expert systems; Geographic information
systems; Public administration; Traffic engineering computing; Transportation;
Visual databases; Intelligent support tools; Network referenced database
system; Urban highways; Sunderland; Highway data acquisition systems; Video
surveying; GIS developments; Road surface macro texture; Skidding resistance
assessment; Road sign detection; CityLIGHT ; CitySIGN
Original abstract: This paper reports on the experience of a local
highway authority (The City of Sunderland) in association with the local
University in developing a range of highway data acquisition systems, post
survey processing techniques and data management tools. In particular the
paper outlines work on video surveying and attempts to speed up the post
survey processing using expert systems support, experiences with in house
GIS developments, road surface macro texture and skidding resistance assessment
and early work on automated road sign detection from video data. As an
example of the management tools the CityLIGHT and CitySIGN software packages
are discussed.
Foody, G. M. (1995). Land cover classification by an artificial neural
network with ancillary information. International Journal of Geographical
Information Systems, 9, (5): 527-42.
Keywords: Cartography; Geographic information systems; Neural nets;
Remote sensing; Town and country planning; Land cover classification; Artificial
neural network; Ancillary information; gis; Remotely-sensed data; Statistical
classification; Fuzzy output; Class membership; Fuzzy classification; Mapping;
Soil type ; Geographic information system
Original Abstract: Remote sensing is an important source of land cover
data required by many GIS users. Land cover data are typically derived
from remotely-sensed data through the application of a conventional statistical
classification. Such classification techniques are not, however, always
appropriate, particularly as they may make untenable assumptions about
the data and their output is hard, comprising only the code of the most
likely class of membership. Whilst some deviation from the assumptions
may be tolerated and a fuzzy output may be derived, making more information
on class membership properties available, alternative classification procedures
are sometimes required. Artificial neural networks are an attractive alternative
to the statistical classifiers and one is used to derive a fuzzy classification
output from a remotely-sensed data set that may be post-processed with
ancillary data available in a GIS to increase the accuracy with which land
cover may be mapped. With the aid of ancillary information on soil type
and prior knowledge of class occurrence the accuracy of an artificial neural
network classification was increased by 29.93 to 77.37 per cent. An artificial
neural network can therefore be used generate a fuzzy classification output
that may be used with other data sets in a GIS, which may not have been
available to the producer of the classification, to increase the accuracy
with which land cover may be classified.
Ford, B. J.; D. K. Widner, (2000). Shared geography: building a common
street centerline resource to service state and county governments.
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
URISA Proceedings. Papers from the Annual Conference, pp.584-93.
Keywords: Cartography; Geographic information systems; Government
data processing; Town and country planning; Transportation; Visual databases;
Common street centerline resource; Government data; Roadway; Virginia Department
of Transportation; Geocoding; Mapping products; gis; Street information;
Complex data sets ; Geographic information system
Original abstract: Building and maintaining a common street centerline
file to fill the needs of a county government and a state department of
transportation is a unique and challenging task. The Virginia Department
of Transportation (VDOT) and the Fairfax County Geographic Information
Services Department have jointly decided to take on that task. Within the
borders of Fairfax County, VA there are approximately 4000 miles of roadway.
VDOT is responsible for the maintenance of over 2600 miles of this roadway.
There are 300-400 new streets added to the system each year as well as
hundreds of state and county projects each year that alter the current
network. At a county level a street centerline must support the routing
of emergency vehicles, school buses, maintenance crews, and hundreds of
other inspectors and field personnel. The street centerline layer must
be able to support other analysis applications such as geocoding. Further,
the street layer must support the cartographic production of small and
large scale mapping products. This paper should be of interest to GIS professionals
responsible for maintaining street information or other complex data sets
that could support multiple levels of government.
Ford, S. J.; D. Kalp; J. McGlone; D. M. McKeown, Jr., (1997). Preliminary
results on the analysis of HYDICE data for information fusion in cartographic
feature extraction. 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.67-86.
Keywords: Cartography; Data analysis; Feature extraction; Geophysical
signal processing; Image processing; Remote sensing; Sensor fusion; Spectral
analysis; HYDICE data analysis; Information fusion; Cartographic feature
extraction; Hyperspectral Digital Imagery Collection Experiment; Airborne
hyperspectral imagery; Surface material attribution; Fort Hood; Texas;
usa; Geopositioning; Multisensor registration; Surface material classification;
2 meter GSD; Hyperspectral dataset; Spatial resolution; Panchromatic mapping
imagery; Urban scene analysis ; Spatial database population
Original abstract: This paper discusses ongoing research in the analysis
of airborne hyperspectral imagery with application to cartographic feature
extraction and surface material attribution. Preliminary results, based
upon the processing and analysis of hyperspectral data acquired by the
Naval Research Laboratory's (NRL) Hyperspectral Digital Imagery Collection
Experiment (HYDICE) over Fort Hood, Texas in late 1995, are shown. Significant
research issues in geopositioning, multisensor registration, spectral analysis,
and surface material classification are discussed. The research goal is
to measure the utility of hyperspectral imagery acquired with high spatial
resolution (2 meter GSD) to support automated cartographic feature extraction.
Our hypothesis is that the addition of a hyperspectral dataset, with spatial
resolution comparable to panchromatic mapping imagery, enables opportunities
to exploit the inherent spectral information of the hyperspectral imagery
to aid in urban scene analysis for cartographic feature extraction and
spatial database population. Test areas selected from the Fort Hood dataset
will illustrate the process flow and serve to show current research results.
Ford, S. J.; J. C. McGlone; S. D. Cochran; J. A. Shufelt; W. A. Harvey;
D. M. McKeown, Jr., (1998). Analysis of HYDICE data for information
fusion in cartographic feature extraction. 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.2702-6 vol.5.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Image registration; Multidimensional
signal processing; Remote sensing; Sensor fusion; Terrain mapping; Geophysical
measurement technique; Land surface; Land use; Optical imaging; Multispectral
remote sensing; Hyperspectral imaging; hydice; Information fusion; Cartography;
Image processing; Hyperspectral Digital Imagery Collection Experiment;
Fort Hood; United States; usa; Texas; Geopositioning ; Photogrammetric
block adjustment
Original abstract: Late in 1995 the authors organized a hyperspectral
data acquisition using the Naval Research Laboratory's Hyperspectral Digital
Imagery Collection Experiment sensor system over Fort Hood, Texas. This
acquisition resulted in hyperspectral data with a nominal 2 meter ground
sample distance collected with 210 spectral samples per pixel. This paper
describes current quantitative classification results for man-made and
natural materials using 14 surface material classes over selected test
areas within Fort Hood. The authors discuss the issues encountered in radiometric
effects due to changing solar illumination and atmospheric conditions during
the acquisition. They also describe their approach to image registration
and geopositioning, using a full photogrammetric block adjustment solution.
Foresman, T. W.; J. E. Estes; J. J. Garegnani; D. L. Porter, (1996).
Remote sensing and core data needed to support planning and policy decision
making. 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.2243-5 vol.4.
Keywords: Geophysical techniques; Government policies; Remote sensing;
Town and country planning; Geophysical measurement technique; Land surface;
Terrain mapping; Planning; Policy decision making; Sustainable development
research; Land use; Land cover change; Environment; Satellite imagery ;
Regional Data Center
Original abstract: A variety of sustainable development research efforts
and related activities are attempting to reconcile the issues of conserving
our natural resources without limiting economic motivation while also improving
our social equity and quality of life. Land use/land cover change, occurring
on a global scale, is an aggregate of local land use decisions and profoundly
impacts our environment. It is therefore the local decision making process
that should be the eventual target of many of the ongoing data collection
and research efforts which strive toward supporting a sustainable future.
Satellite imagery data is a primary source of data upon which to build
a core data set for use by researchers in analyzing this global change.
A process is necessary to link global change research, utilizing satellite
imagery, to the local land use decision making process. One example of
this is the NASA-sponsored Regional Data Center (RDC) prototype. The RDC
approach is an attempt to integrate science and technology at the community
level. The anticipated result of this complex interaction between research
and the decision making communities will be realized in the form of long-term
benefits to the public.
Forster, B.; C. Ticehurst; Y. Dong, (1997). Analysis of radar response
from urban areas. 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.891-4 vol.2.
Keywords: Backscatter; Geophysical techniques; Radar cross-sections;
Radar imaging; Radar polarimetry; Remote sensing by radar; Synthetic aperture
radar; Geophysical measurement technique; Land surface; Terrain mapping;
Urban area; City; Town; Radar remote sensing; Buildings; Radar scattering;
Backscattering; Image classification; AirSAR quad polarised radar; sar;
Sydney; Australia ; Building orientation
Original abstract: The output from regular mapping and monitoring of
urban areas provides an important source of information for urban planners
and decision makers. The use of remotely sensed data to provide this information
has been successful in particular environments but has had only limited
success in tropical zone countries where cloud and rain often restrict
the useful acquisition of visible/infrared image data on a regular basis.
In many cases, and particularly in east Asia, these are precisely the areas
that most need the data. A number of researchers have examined the potential
of using radar images to overcome these problems, because at the wavelengths
used (X- to P-), radar is not affected by cloud or rain. Urban areas are
a spatially complex mixture of both natural and built surfaces whose spectral
and geometric properties are many and varied. Buildings for example, cause
significant backscatter when irradiated by microwave radiation, which is
dependent on wavelength, polarisation and incidence angle of the radar
beam, and roughness, dielectric properties and size, shape and orientation
of the buildings and their surface facets. To some extent all combinations
of specular and diffuse backscatter are a function of the height and width
of buildings, and thus give rise to the possibility of using backscatter
as a measure of the bulk density of the built environment. Equations for
backscattering mechanisms, often found in urban environments, are well
known. These are for example, facets, point scatterers, dihedral and trihedral
corner reflectors, cylinders and wedges. This paper examines the theoretical
relationships between urban morphology and remote sensing response at radar
wavelengths, provides some preliminary results on measures of urban classification
using AirSAR quad polarised radar data from test sites over the city of
Sydney, Australia, and proposes a solution to the problem of backscatter
variation due to building orientation.
Freeland, R.; J. Susa (1997). PennDOT deploys districtwide GIS.
GIS World, 10, (8): 52-4.
Keywords: Geographic information systems; Public administration;
Town and country planning; PennDOT; Districtwide GIS; Pennsylvania Department
of Transportation; Roadway data; Map products; Maps; GIS workstation; Local
database; Plotter ; System training
Original Abstract: The Pennsylvania Department of Transportation (PennDOT)
is laying the groundwork to boost employees' productivity at its district
offices by making it easier for them to find, format and analyze roadway
data. Until recently, all requests for maps and map products were handled
by PennDOT's central office GIS staff in Harrisburg. Following a successful
pilot project, every district office is scheduled to receive a GIS workstation,
software, local database, plotter and system training. The move positions
PennDOT as one of the nation's first transportation agencies to successfully
deploy GIS within its districts.
Freeman, A.; S. Hensley; E. Moore, (1999). Analysis of radar images
of Angkor, Cambodia. 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.2572-4 vol.5.
Keywords: Airborne radar; Archaeology; Remote sensing by radar;
Synthetic aperture radar; Terrain mapping; Angkor; Cambodia; Radar image
analysis; 1996 AIRSAR Pacific Rim Deployment data; Temples; Cities; Prehistoric
habitation; Hydraulic constructions; Urban zone; Topography; Feature identification;
Feature delineation; Circular earthworks; Circular village sites; Earthwork
dykes; Reservoirs; Canals; Temple sites ; Main temple complex
Original abstract: During the 1996 AIRSAR Pacific Rim Deployment, data
were collected over Angkor in Cambodia. The temples of Angkor date the
succession of cities to the 9th-13th century AD, but little is known of
its prehistoric habitation. A related area of archaeological debate has
been the origin, spiritual meaning and use of the hydraulic constructions
in the urban zone. The high resolution, multi-channel capability of AIRSAR,
together with the unprecedentedly accurate topography provided by TOPSAR,
offer identification and delineation of these features. Examples include
previously unrecorded circular earthworks around circular village sites,
detection of unrecorded earthwork dykes, reservoirs and canal features,
and of temple sites located some distance from the main temple complex
at Angkor.
Frere, D.; J. Vandekerckhove; T. Moons; L. Van Gool, (1998). Automatic
modelling and 3D reconstruction of urban buildings from aerial 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.2593-6 vol.5.
Keywords: Cartography; Computer graphics; Geophysical techniques;
Geophysics computing; Photogrammetry; Remote sensing; Geophysical measurement
technique; Terrain mapping; Building; Three dimensional model; Computer
model; Automatic model; Three dimensional reconstruction; Urban buildings;
Aerial image; House; Roof; Residential area; Urban site; Reasoning; Hypothesis
generation ; Verification
Original abstract: A method is presented that automatically generates
3D models of generic house roofs from aerial images of residential areas
in urban sites. Crucial to the method is the possibility of delineating
regions in the images that correspond well to actual roof structures. Restricting
the processing to relatively small regions allows at all stages of the
algorithm to use constraints that are not very tight, and, at the same
time, to keep the combinatorics under control. All modelling is done by
reasoning in 3D. By adopting a strategy of hypothesis generation and verification
the authors are not only are capable of exploiting all available image
data at every step in the algorithm, but also to treat all views equally.
Decoupling topology retrieval from metric accuracy makes it possible to
generate and test combinations which otherwise would have been ruled out
by more tight constraints. The method is implemented and tests on the correctness
and completeness of the extracted roof models have been performed.
Frery, A. C.; H. J. Muller; C. C. F. Yanasse; S. J. S. Sant'Anna (1997).
A model for extremely heterogeneous clutter. IEEE Transactions
on Geoscience and Remote Sensing, 35, (3): 648-59.
Keywords: Backscatter; Electromagnetic wave scattering; Geophysical
techniques; Radar clutter; Radar cross-sections; Radar imaging; Radar theory;
Remote sensing by radar; Geophysical measurement technique; Terrain mapping;
Land surface; Radar remote sensing; Model; Extremely heterogeneous clutter;
G distribution; Multiplicative model; Multilook intensity; Amplitude data;
Urban area ; Speckle
Original Abstract: A new class of distributions, G distributions, arising
from the multiplicative model is presented, along with their main properties
and relations. Their densities are derived for complex and multilook intensity
and amplitude data. Classical distributions, such as K, are particular
cases of this new class. A special case of this class called G/sup 0/,
that has as many parameters as K distributions, is shown able to model
extremely heterogeneous clutter, such as that of urban areas, that cannot
be properly modeled with K distributions. One of the parameters of this
special case is related to the degree of homogeneity, and a limiting case
is that of a scaled speckle. The advantage of the G/sup 0/ distribution
becomes evident through the analysis of a variety of areas (urban, primary
forest and deforested) from two sensors.
Friedl, M. A.; C. E. Brodley; A. H. Strahler (1999). Maximizing land
cover classification accuracies produced by decision trees at continental
to global scales. IEEE Transactions on Geoscience and Remote Sensing,
37, (2, pt.2): 969-77.
Keywords: Decision trees; Feature extraction; Geophysical signal
processing; Geophysical techniques; Image classification; Terrain mapping;
Geophysical measurement technique; Land surface; Remote sensing; Land cover
classification accuracy; Continental scale; Global scale; Feature selection;
Classifier performance; avhrr ; Land cover type
Original Abstract: Classification of land cover from remotely sensed
data at continental to global scales requires sophisticated algorithms
and feature selection techniques to optimize classifier performance. The
authors examine methods to maximize classification accuracies using decision
trees to map land cover from multitemporal AVHRR imagery at continental
and global scales. As part of their analysis they test the utility of "boosting",
a new technique developed to increase classification accuracy by forcing
the learning (classification) algorithm to concentrate on those training
observations that are most difficult to classify. Their results show that
boosting consistently reduces misclassification rates by 20-50% depending
on the data set in question, and that most of the benefit gained by boosting
is achieved after seven boosting iterations. They also assess the utility
of including phenological metrics and geographic position as additional
features to the classification algorithm. They find that using derived
phenological metrics produces little improvement in classification accuracy
relative to using an annual time series of NDVI data, but that geographic
position provides substantial power for predicting land cover types at
continental and global scales. However, in order to avoid generating spurious
classification accuracies using geographic position, training data must
be distributed evenly in geographic space.
Fruneau, B.; J. P. Rudant; D. Obert; D. Raymond, (1999). Small displacements
detected by SAR interferometry on the city of Paris (France). 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.1943-5 vol.4.
Keywords: Geodesy; Geophysical techniques; Groundwater; Hydrological
techniques; Remote sensing by radar; Synthetic aperture radar; Terrain
mapping; Topography (Earth); Geophysical measurement technique; Hydrology;
Land surface topography; Subsidence; InSAR; Displacement; SAR interferometry;
Paris; France; City; Urban area; Slow deformation; Tandem image; ad 1993;
ad 1994; ad 1995; ad 1996; Pumping ; Phreatic water
Original abstract: The feasibility of SAR interferometry for the detection
of slow deformations on urban areas with standard atmospheric conditions
is shown. The authors focus on the city of Paris (France), on which ten
interferograms are derived from tandem images acquired during the period
of July 28 1993, August 10 1996. The main limitation for this kind of measurements
is due to tropospheric inhomogeneities, which lead to significant phase
variations as high as one fringe. The best solution to compensate for the
artifacts introduced by these inhomogeneities in the propagating medium
appears to be the addition of interferograms. Then, a halo of subsidence,
whose extension is about 600 m by 700 m is evidenced. It is precisely straight
above an important working site: the construction of an underground station
for the new "Eole" subway. This subsidence is produced by the lowering
of the piezometric level, due to the pumping of the phreatic water.
Fuan, T.; W. Philpot (1998). Derivative analysis of hyperspectral
data. Remote Sensing of Environment, 66, (1): 41-51.
Keywords: Data analysis; Fluorescence; Remote sensing; Spectral
analysis; Vegetation mapping; Derivative spectral analysis; Hyperspectral
data; High-resolution spectrally continuous remote sensing data; Smoothing
algorithms; Spectral data sets; Interactive derivative analysis; Savitzky-Golay
smoothing; Kawata-Minami smoothing; Mean-filter smoothing; Finite divided
difference approximation algorithm; Convolution algorithm; Derivative computation
procedures; Laboratory spectral data; Soybean fluorescence spectrum; Spectral
feature extraction; Scaling effect; Band separations; Noise removal ; Sampling
interval
Original Abstract: With the goal of applying derivative spectral analysis
to analyze high-resolution, spectrally continuous remote sensing data,
several smoothing and derivative computation algorithms have been reviewed
and modified to develop a set of cross-platform spectral analysis tools.
Emphasis was placed on exploring different smoothing and derivative algorithms
to extract spectral details from spectral data sets. A modular program
was created to perform interactive derivative analysis. This module calculated
derivatives using either a convolution (Savitzky-Golay) or finite divided
difference approximation algorithm. Spectra were smoothed using one of
the three built-in smoothing algorithms (Savitzky-Golay smoothing, Kawata-Minami
smoothing, and mean-filter smoothing) prior to the derivative computation
procedures. Laboratory spectral data were used to test the performance
of the implemented derivative analysis module. An algorithm for detecting
the absorption band positions was executed on synthetic spectra and a soybean
fluorescence spectrum to demonstrate the usage of the implemented modules
in extracting spectral features. Issues related to smoothing and spectral
deviation caused by the smoothing or derivative computation algorithms
were also observed and are discussed. A scaling effect, resulting from
the migration of band separations when using the finite divided difference
approximation derivative algorithm can be used to enhance spectral features
at the scale of specified sampling interval and remove noise or features
smaller than the sampling interval.
Fujimura, S.; S. Kiyasu, (1997). A method for object-oriented feature
extraction from hyperspectral data-generation of new channels by fusion
of 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.975-7 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Object-oriented methods; Remote sensing;
Sensor fusion; Geophysical measurement technique; Land surface; Terrain
mapping; Optical imaging; Multispectral remote sensing; Hyperspectral remote
sensing; Data fusion; Image processing; Object-oriented method; New channel
generation ; Supervised classification
Original abstract: Extracting significant features is essential for
processing and transmission of a vast volume of hyperspectral data. Conventional
ways of extracting features are not always satisfactory for this kind of
data in terms of optimality and computation time. The authors present an
object-oriented feature extraction method designed for supervised classification.
After all the data are reduced and orthogonalized, a set of appropriate
features for the prescribed purpose is extracted as linear combinations
(fused channel) of the reduced components. Each dimension of hyperspectral
data is weighted and fused according to the extracted features, which means
the generation of new channels from hyperspectral data. Results of feature
extraction are applied to evaluating the performance of sensors and to
designing a new sensor.
Fujimura, S.; A. Yonenaga; S. Kiyasi, (1998). Application of an object-oriented
feature extraction method to quantitative estimation from hyper-spectral
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.1061-3 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Geophysics computing; Object-oriented methods; Remote sensing;
Geophysical measurement technique; Land surface; Terrain mapping; Optical
imaging; Multispectral remote sensing; Image processing; Object oriented
method; Quantitative estimation; Hyperspectral remote sensing ; Significant
feature
Original abstract: Extracting significant features is essential for
processing, storing and/or transmission of a vast volume of hyperspectral
data. Conventional ways of extracting features are not always satisfactory
for this kind of data in terms of optimality and computation time. The
authors have already developed an object-oriented feature extraction method
designed for supervised classification. They apply the basic idea of the
approach to feature extraction for quantitative estimation from hyperspectral
data. After the data obtained for various values of a quantity are orthogonalized
and reduced by principal component analysis, the features describing the
variation of spectra are extracted as linear combinations of the reduced
components. An experiment using pigment shows that the feature extraction
method for quantitative analysis yielded satisfactory results.
Fukuda, S.; H. Hirosawa, (1999). A wavelet-based texture feature
set applied to classification of multifrequency polarimetric 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
IEEE Trans. Geosci. Remote Sens. (USA), pp.2282-6.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Image texture; Radar imaging; Radar polarimetry;
Remote sensing by radar; Synthetic aperture radar; Terrain mapping; Wavelet
transforms; Geophysical measurement technique; Land surface; Radar remote
sensing; Wavelet-based texture feature set; Multifrequency polarimetric
SAR image; Land cover; Subimages; Wavelet decomposition; Downsampling;
Flevoland site; Agricultural area; The Netherlands; Polarization selection;
Feature reduction ; Holland
Original abstract: Texture is an essential key to the classification
of land cover in SAR images. A wavelet-based texture feature set is derived.
It consists of the energy of subimages obtained by the overcomplete wavelet
decomposition of local areas in SAR images, where the downsampling between
wavelet levels is omitted. The feature set has been successfully applied
to multifrequency polarimetric images of the Flevoland site, an agricultural
area in The Netherlands. The methods of polarization selection and feature
reduction are also discussed.
Gaddis, L. R.; L. A. Soderblom; H. H. Kieffer; K. J. Becker; J. Torson;
K. Mullins (1996). Decomposition of Aviris Spectra - Extraction of Surface-Reflectance,
Atmospheric, and Instrumental Components. Ieee Transactions on Geoscience
and Remote Sensing, V34, (N1): 163-178.
Keywords: AVIRIS , spectra decomposition, surface-reflectance
Original Abstract: Presents techniques that use only information contained
within a raw, high-spectral-resolution, hyperspectral Airborne Visible/Infrared
Imaging Spectrometer (AVIRIS) scene to estimate and remove additive components
(atmospheric scattering and instrument dark current). These techniques
allow normalization of multiplicative components (instrument gain, topography,
atmospheric transmission) and enhancement, extraction, and identification
of relative-reflectance information related to surface composition and
mineralogy. The authors' derivation of additive components from raw AVIRIS
data is based on an adaptation of Crippen's "regression intersection method
(RIM)." As does RIM, the authors use pairs of surface units that are spectrally
homogeneous, spatially extensive, and located in rugged terrain. However,
their technique utilizes the long-wavelength spectral data of AVIRIS to
derive and remove atmospheric scattering components for each unit. AVIRIS
data from the Kelso Dunes and Granite Mountain areas of southern California
served as spectrally contrasting, topographically modulated surfaces for
illustration of this technique. For a given site and wavelength pair, subtraction
of the wavelength-dependent additive component from individual bands will
remove topographic shading in both sites in band-to-band ratio images.
Normalization of all spectra in the scene to the average scene spectrum
results in cancellation of multiplicative components and produces a relative-reflectance
scene. Absorption features due to mineral absorptions that depart from
the average spectrum can be identified in the relative-reflectance AVIRIS
product. The validity of these techniques is demonstrated by comparisons
between relative-reflectance AVIRIS spectra derived from application of
this technique and those derived by using the standard calibration techniques
of JPL. Calibrated spectra were extracted from an AVIRIS scene of the Upheaval
Dome area of Canyonlands National Park, UT. Results show that surface-reflectance
information can be extracted and interpreted in terms of surface mineralogy
after application of these techniques to AVIRIS data.
Gader, P.; J. M. Keller; H. Frigui; L. Hongwu; W. Dayou, (1998). Landmine
detection using fuzzy sets with GPR images. 1998 IEEE International
Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational
Intelligence (Cat. No.98CH36228) Anchorage, AK, USA 4-9 May 1998
New York, NY, USA IEEE, pp.232-6 vol.1.
Keywords: Fuzzy set theory; Object detection; Radar applications;
Radar imaging; Landmine detection; Fuzzy sets; GPR images; Ground penetrating
radar imaging system; 3D array; Intensity values; Multiple prototypes;
Fuzzy clustering; Gradient features; Object prototypes; DARPA backgrounds
data set; Mine lanes ; Roads
Original abstract: This paper describes a fuzzy set based approach
to the detection of landmines using a novel ground penetrating radar (GPR)
imaging system. The GPR produces a three-dimensional array of intensity
values, representing a volume below the surface of the ground. Multiple
prototypes are generated from fuzzy clustering of gradient features on
training data, and a fuzzy confidence is then constructed for the test
data from the "object" prototypes. This confidence plane is used to automatically
detect objects, which are then scored by the ground truth information.
Results on the training and testing with the DARPA backgrounds data set
(open fields) and mine lanes (roads) are analyzed.
Gader, P. D.; M. Mystkowski; Z. Yunxin (2001). Landmine detection
with ground penetrating radar using hidden Markov models. IEEE Transactions
on Geoscience and Remote Sensing, 39, (6): 1231-44.
Keywords: Backscatter; Buried object detection; Geophysical techniques;
Hidden Markov models; Military systems; Radar cross-sections; Radar theory;
Remote sensing by radar; Terrain mapping; Terrestrial electricity; Geophysical
measurement technique; Military system; Geoelectric method; Landmine; Mine
detection; Unexploded ordnance; Radar remote sensing; Ground penetrating
radar; Hidden Markov model; Radar signature; Moving vehicle; Radar scattering;
Observation vector representation; Baum-Welch algorithm ; Land surface
Original Abstract: Novel, general methods for detecting landmine signatures
in ground penetrating radar (GPR) using hidden Markov models (HMMs) are
proposed and evaluated. The methods are evaluated on real data collected
by a GPR mounted on a moving vehicle at three different geographical locations.
A large library of digital GPR signatures of both landmines and clutter/background
was constructed and used for training. Simple, but effective, observation
vector representations are constructed to naturally model the time-varying
signatures produced by the interaction of the GPR and the landmines as
the vehicle moves. The number and definition of the states of the HMMs
are based on qualitative signature models. The model parameters are optimized
using the Baum-Welch algorithm. The models were trained on landmine and
background/clutter signatures from one geographical location and successfully
tested at two different locations. The data used in the test were acquired
from over 6000 m/sup 2/ of simulated dirt and gravel roads, and also off-road
conditions. These data contained approximately 300 landmine signatures,
over half of which were plastic-cased or completely nonmetal.
Gamba, P.; B. Houshmand, (2001). Characterization of C-band and X-band
InSAR data for 3D urban analysis. Proceedings of the 2001 IEEE Radar
Conference (Cat. No.01CH37200) Proceedings of the 2001 IEEE Radar Conference
Atlanta, GA, USA 1-3 May 2001
Piscataway, NJ, USA IEEE, pp.415-20.
Keywords: Microwave measurement; Radar resolution; Remote sensing
by radar; Synthetic aperture radar; C-band; X-band; InSAR data; 3D urban
analysis; SAR measurements; Los Angeles; nasa/jpl airsar; Intermap Star-3i
system; Range measurements; Bald earth topography; 3D shapes; Ground resolution;
Building analysis; Filtering ; Ad hoc algorithms
Original abstract: We compare C and X-band SAR measurements over the
same urban area to understand which kind of information they are able to
provide and which are the differences and similarities of the data sets.
In particular, we consider data recorded over Los Angeles by the C-band
NASA/JPL AIRSAR system and by the X-band Intermap Star-3i system. We analyze
for both data sets the original range measurements as reconstructed after
the phase unwrapping procedure, the bald earth topography that we were
able to retrieve, and the 3D shapes of some of the buildings in the UCLA
campus area. Our results show that, despite the lower resolution, AIRSAR
data are still able to provide interesting views of an urban environment.
The better ground resolution of the X-band system allows us to perform
slightly better building analysis and extraction. Both systems suffer from
large data drop out regions that prevent the original data from being immediately
useful. However, it is still possible to extract the terrain height to
some extent by means of a filtering procedure and to deduce built structure
characteristics if suitable ad hoc algorithms are introduced.
Gamba, P.; B. Houshmand (2001). An efficient neural classification
chain of SAR and optical urban images. International Journal of
Remote Sensing, V22, (N8): 1535-1553.
Keywords:
Original Abstract: In this paper a suitable neural classification algorithm,
based on the use of Adaptive Resonance Theory (ART) networks, is applied
to the fusion and classification of optical and SAR urban images. ART networks
provide a flexible tool for classification, but are ruled by a large number
of parameters. Therefore, the simplified ART2-A algorithm is used in this
paper, and the neural approach is integrated into a classification chain
where fuzzy clustering for merging of classes is also considered. The interaction
between the two methods leads to encouraging results in less CPU time than
classification with fuzzy clustering alone or other classical approaches
(ISODATA). Examples of classification are provided using C-band total power
AIRSAR data and optical images of Santa Monica, Los Angeles.
Gamba, P.; B. Houshmand (2001). Integration of hyperspectral and
IFSAR data for improved 3D urban profile reconstruction. Photogrammetric
Engineering and Remote Sensing, V67, (N8): 947-956.
Keywords: 3D urban profile AVIRIS
Original Abstract: In this paper hyperspectral (AVIRIS) and radar (AIRSAR)
aerial data acquired over urban environments are considered. The information
available from each sensor was extracted and merged to improve the 3D profile
reconstruction of builtup areas. Two classification schemes were evaluated
for AVIRIS data clustering, while the effect of the radar view angle was
considered in assessing the quality of the associated digital elevation
models. A detailed analysis of what is possible to extract and to what
extent these data are useful was also produced, considering precise 2D
and 3D ground truth of the UCLA campus.
Gamba, P.; B. Houshmand (2000). Digital surface models and building
extraction: a comparison of IFSAR and LIDAR data. IEEE Transactions
on Geoscience and Remote Sensing, 38, (4, pt.2): 1959-68.
Keywords: Cartography; Feature extraction; Geophysical signal processing;
Geophysical techniques; Radar imaging; Remote sensing by laser beam; Remote
sensing by radar; Synthetic aperture radar; Terrain mapping; Geophysical
measurement technique; Land surface; Image processing; Remote sensing;
Digital surface model; Building extraction; Buildings; Urban area; Town;
City; ifsar; lidar; Built structure; Interferometric SAR; Laser remote
sensing ; Radar remote sensing
Synopsis: Discusses building extraction in DSMs, comparing results
using both interferometric SAR and LIDAR data. Their automated extraction
technique detects height and shape of buildings. Results show extracted
buildings from LIDAR data show better shape characterization.
Original Abstract: The task of extracting significant built structure
in digital surface models (DSM) is analyzed. The original data are obtained
by means of interferometric SAR or LIDAR techniques and have different
resolution and noise characteristics. This work aims to make a comparison
of what (and how precisely) it is possible to detect and extract starting
from these models, taking into account their differences but applying to
them the same planar approximation approach. To this aim, data over Los
Angeles and Denver is considered and evaluated. The results show that LIDAR
data provide a better shape characterization of each building, and not
simply because of their higher resolution. Indeed, less accurate results
obtained starting from radar data are mainly due to shadowing/layover effects,
which can be only partially corrected by means of the segmentation procedures.
However, better results than those already presented in the literature
could be achieved by using the IFSAR data correlation map.
Gamba, P.; B. Houshmand, (2000). Hyperspectral and IFSAR data for
3D urban characterization. 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.2611-13 vol.6.
Keywords: Geophysical signal processing; Geophysical techniques;
Image processing; Multidimensional signal processing; Radar imaging; Remote
sensing; Remote sensing by radar; Sensor fusion; Synthetic aperture radar;
Terrain mapping; Geophysical measurement technique; Land surface; Multispectral
method; sar; Data fusion; Urban area; Town; City; Hyperspectral remote
sensing; Radar remote sensing; ifsar; Urban characterization; Three dimensional
method; aviris; airsar; Hyperspectral classification; Built zone; Best
footprint detection; Buildings; Building ; Terrain cover
Original abstract: AVIRIS and AIRSAR data over a urban environment
are evaluated. The 2D maps available from hyperspectral classification
are used to improve the detection and recognition of built zones starting
from the IFSAR DEM. The improvements are twofold: best footprint detection
provides a way to better reconstruct the 3D profile of individual buildings.
Moreover, different terrain covers (e.g. trees) are recognized and discarded.
Examples are provided over the UCLA campus in Los Angeles.
Gamba, P.; B. Houshmand, (1999). Three dimensional urban characterization
by IFSAR measurements. IEEE 1999 International Geoscience and Remote
Sensing Symposium. IGARSS'99 (Cat. No.99CH36293) IEEE 1999 International
Geoscience and Remote Sensing Symposium. IGARSS'99 Hamburg, Germany 28
June-2 July 1999
Piscataway, NJ, USA IEEE, v. vol.5, pp.2401-3.
Keywords: Synthetic aperture radar , InSAR,Three dimensional urban
characterization,ifsar,Machine vision
Synopsis: This paper proposes a building extraction algorithm for use
with IFSAR data. Their goal is to detect height and shape of buildings.
Algorithm is more effective in detecting height than detecting area.
Original abstract: In this paper a machine vision approach is applied
to IFSAR data to extract the most relevant built structures in a dense
urban environment. The algorithm tries to cluster primitives (line segments)
into more complex surfaces (planes) to approximate the 3D shape of these
objects. Very interesting results starting from TOPSAR data recorded over
S. Monica are presented.
Gamba, P.; B. Houshmand, (1999). Three-dimensional road network by
fusion of polarimetric and interferometric SAR data. 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.302-4 vol.1.
Keywords: Geophysical signal processing; Geophysical techniques;
Image classification; Radar imaging; Radar polarimetry; Remote sensing
by radar; Sensor fusion; Synthetic aperture radar; Terrain mapping; Geophysical
measurement technique; Land surface; Land use; Radar remote sensing; Polarimetric
radar; InSAR; sar; Road network; Three-dimensional method; Image processing;
Fuzzy classification; Street pixel; Dynamic programming; Fuzzy membership
function ; Urban infrastructure
Original abstract: In this paper a fuzzy classification procedure is
applied to polarimetric radar measurements, and street pixels are detected.
These data are successively grouped into consistent roads by means of a
dynamic programming approach based on the fuzzy membership function values.
Further fusion of the 2D road network extracted and 3D TOPSAR measurements
provides a powerful way to analyze urban infrastructures.
Gamba, P.; B. Houshmand; B. Mercers; S. Schnick, (2000). 3D building
profiles: comparison and fusion of LIDAR and IFSAR 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.984-6 vol.3.
Keywords: Geophysical signal processing; Geophysical techniques;
Optical radar; Radar imaging; Remote sensing by laser beam; Remote sensing
by radar; Sensor fusion; Synthetic aperture radar; Terrain mapping; Geophysical
measurement technique; Land surface; Radar remote sensing; City; Urban
area; Buildings; Building; 3D profile; Three dimensional structure; Laser
remote sensing; lidar; ifsar ; sar
Original abstract: The authors analyze a data set composed of interferometric
radar (IFSAR) and LIDAR measurements over a urban area. The data set horizontal
resolution (2.5 meters) allows to characterize the major buildings in the
studied area (Downtown Denver), and to make a comparison of the building
3D structure retrievable from the data. Furthermore, the integration of
these two sensors, even if in a very preliminary forms, shows promising
results. For instance, the problems affecting IFSAR measurements and due
to multiple bouncing of the electromagnetic field in a crowded built area
may be partially corrected by determining the building footprints by means
of LIDAR data. Moreover, less expensive IFSAR data may be corrected from
its layover and shadowing problems by exploiting LIDAR measurements on
a sample area.
Gamba, P.; B. Houshmand; M. Saccani (2000). Detection and extraction
of buildings from interferometric SAR data. IEEE Transactions on
Geoscience and Remote Sensing, 38, (1, pt.2): 611-17.
Keywords: Geophysical signal processing; Geophysical techniques;
Radar imaging; Remote sensing by radar; Synthetic aperture radar; Terrain
mapping; Geophysical measurement technique; Land surface; Land use; Radar
remote sensing; Urban scene; City; sar; Building; Feature extraction; Radar
detection; Interferometric SAR; InSAR; Terrain elevation data; Machine
vision approach; Local approximation; Three-dimensional data; Best-fitting
planes; Height; Position ; Topographic surface
Synopsis: This is a journal version of the IGARSS '99 conference paper
(Gamba, 2000). There are additional figures and description of their building
extraction algorithm.
Original Abstract: The authors present a complete procedure for the
extraction and characterization of building structures starting from the
three-dimensional (3D) terrain elevation data provided by interferometric
SAR measurements. Each building is detected and isolated from the surroundings
by means of a suitably modified machine vision approach, originally developed
for range image segmentation. The procedure is based on a local approximation
of the 3D data by means of best-fitting planes. In this way, a building
footprint, height and position, as well as its description with a simple
3D model, are recovered by a self-consistent partitioning of the topographic
surface reconstructed from interferometric radar data.
Gamba, P.; M. Lilla; A. Mecocci, (1997). Extraction of discontinuous
chains of symbols by means of perceptual grouping. 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.422-5 vol.2.
Keywords: Artificial intelligence; Feature extraction; Geographic
information systems; Image recognition; Modules; Search problems; Discontinuous
symbol chains extraction; Perceptual grouping; Algorithm; Digitized maps;
Artificial intelligence kernel; Search strategy generation module; Pixels
scanning; Symbol detection module; Cost function evaluation module; Global
quality index; Gestalt rules; Grouping procedures optimisation ; Geographic
information system
Original abstract: This paper proposes a new algorithm which applies
perceptual grouping to track discontinuous chains of symbols in digitized
maps. The procedure is based on an artificial intelligence kernel that
supervises three different auxiliary processes: the search strategy generation
module, responsible for the strategy to scan pixels; the symbol detection
module that extracts the recognized symbols; the cost function evaluation
module that assigns a global quality index to each symbol by considering
the whole course of the line. Selected Gestalt rules are used to optimize
the grouping procedures.
Gamba, P.; M. Lilla; A. Mecocci, (1997). A fast algorithm for target
shadow removal in monocular colour sequences. Proceedings. International
Conference on Image Processing (Cat. No.97CB36144) Proceedings of International
Conference on Image Processing Santa Barbara, CA, USA 26-29 Oct. 1997
Los Alamitos, CA, USA IEEE Comput. Soc
Proceedings. International Conference on Image Processing (Cat. No.97CB36144)
Access restricted., pp.436-47 vol.1.
Original abstract: We present a fast algorithm to extract a shadow
model from a monocular colour scene exploiting the hue, luminosity, saturation
(HLS) colour components. The method allows one to recover target shapes
in diurnal scene for improved identification and it is based on the definition
of a global bitmap model and a more particular strip bitmap model to identify
shadow regions. Each pixel in the image is then classified as shadow or
target by a comparison with these models.
Gamba, P.; L. Lombardi, (1999). Coding scene contents using the image
background. Proceedings IEEE International Conference on Multimedia
Computing and Systems Proceedings of ICMCS99: IEEE Multimedia Systems '99:
Florence, Italy 7-11 June 1999
Los Alamitos, CA, USA IEEE Comput. Soc, pp.860-4 vol.1.
Keywords: Boundary integral equations; Image coding; Image representation;
Visual databases; Scene content coding; Image background; Scene coding
approach; Spatial relations; Shape representation; Boundary Integral -
Resonant Mode Expansion; Shape analysis; Vibration modes; Elastic sheet;
Fixed boundary; Arbitrarily shaped object; BI-RME algorithm ; Scene background
Original abstract: We propose a scene coding approach that allows us
to maintain the spatial relations among the individual objects and between
these objects and the background by a suitable representation of their
shapes. To this aim we apply the recently introduced Boundary Integral
- Resonant Mode Expansion (BI-RME) approach for shape analysis, whose aim
is to compute the vibration modes of an elastic sheet of fixed boundary
to represent an arbitrarily shaped object. We demonstrate that the BI-RME
algorithm is suitable to give contemporary and efficiently the shape representation
for all the objects present in the original image. Moreover, it preserves
the spatial relations by the analysis of the scene background, i.e. the
part of an image left when all the meaningful objects have been extracted.
Gamba, P.; L. Lombardi (1999). Shape analysis with the *Boundary
Integral-Resonant Mode Expansion' method. Image and Vision Computing,
17, (5-6): 357-64.
Keywords: Boundary integral equations; Image recognition; bi-rme;
Shape analysis; Boundary Integral-Resonant Mode Expansion; Modal matching
algorithm; Eigenfunctions; Helmholtz equation; Dirichlet boundary condition
; Vibration modes
Original Abstract: This paper proposes the applications of the Boundary
Integral-Resonant Mode Expansion (BI-RME) method to the shape analysis
problem, an approach originally implemented for the determination of modes
of a cavity resonator. We explore its advantages for shape analysis and
recognition of a BI-RME based modal matching algorithm, where each shape
is represented with a set of eigenfunctions, and solutions of the Helmholtz
equation with Dirichlet boundary condition. These solutions correspond
to the vibration modes of an elastic sheet of arbitrary shape and fixed
boundary and show some advantages over previous approaches. It is demonstrated
that the BI-RME algorithm is particularly suitable for characterizing shapes
with multiply connected boundaries and requires small cpu times.
Gamba, P.; L. Lombardi, (1997). Shape analysis by means of the *boundary
integral-resonant mode expansion' method. Proceedings of the Third
International Workshop on Visual Form. Advances in Visual Form Analysis
Capri, Italy 28-30 May 1997
Singapore World Scientific, pp.227-36.
Keywords: Computer vision; Eigenvalues and eigenfunctions; Image
recognition; Shape analysis; Boundary integral; Resonant mode expansion;
Modal matching algorithm; Eigenfunctions; Helmholtz equation; Dirichlet
boundary condition; Vibration modes; Elastic sheet; Arbitrary shape; BI-RME
algorithm ; Multiply connected boundary
Original abstract: In this paper the application of the Boundary Integral-Resonant
Mode Expansion (BI-RME) method to the shape analysis problem is proposed.
We explore the advantages for shape analysis and recognition of a BI-RME
based modal matching algorithm, where each shape is represented by means
of a set of eigenfunctions, solutions of the Helmholtz equation with Dirichlet
boundary condition. These solutions correspond to the vibration modes of
an elastic sheet of arbitrary shape and fixed boundary and show some advantages
over the previous approaches. It is demonstrated that the BI-RME algorithm
is particularly suitable to characterize shapes with multiply connected
boundary and requires small cpu-times.
Gamba, P.; A. Marazzi; A. Mecocci; P. Savazzi, (1996). A completely
fuzzy classification chain for multispectral remote sensing images.
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.2071-3 vol.4.
Keywords: Geophysical signal processing; Geophysical techniques;
Image classification; Remote sensing; Geophysical measurement technique;
Land surface; Terrain mapping; Classification algorithm; Optical imaging;
Multidimensional signal processing; Fuzzy classification chain; Multispectral
remote sensing; fnp; Pyramidal approach; Training pixels ; Fuzzy nearest
prototype
Original abstract: In this work a new classification algorithm that
uses FNP mixed with a pyramidal approach is proposed. The prototypes of
each class are generated by means of FCM with a FNP initialization. The
aim of the work is to improve the performances of the usual non parametric
classifiers by extracting the maximum information from the training pixels
and from the pixels to be classified. This is done by using both the high
spatial-correlation between pixels and the confidence levels, given by
the fuzzy algorithm. Results are presented that show the improvement obtained
by applying the proposed method to multispectral image classification.
Gamba, P.; A. Mecocci (1999). Perceptual grouping for symbol chain
tracking in digitized topographic maps. Pattern Recognition Letters,
20, (4): 355-65.
Keywords: Cartography; Edge detection; Feature extraction; Group
theory; Search problems; Symbol manipulation; Tracking; Symbol chain tracking;
Digitized maps; Topographic maps; Artificial intelligence; Perceptual grouping;
Search strategy generation module; Symbol detection module; Cost function
evaluation module; Line detection ; Document analysis
Original Abstract: A new algorithm that applies perceptual grouping
to detect and track discontinuous chains of symbols in digitized maps is
proposed. The procedure is based on an artificial intelligence kernel that
supervises three different auxiliary processes: the search strategy generation
module that is responsible for the strategy to scan pixels; the symbol
detection module that extracts the recognized symbols; the cost function
evaluation module that assigns a global quality index to each symbol by
considering the whole course of the line. Selected Gestalt rules are used
to optimize the grouping procedures. After the algorithm discussion, the
problem of the extraction of dotted and dashed lines from digitized topographic
maps is discussed. Experimental results on many maps of the Istituto Geografico
Militare Italiano show a very good performance: 92% of the discontinuous
lines have been correctly chained, and the percentage of incorrectly classified
symbols is also very small.
Gamba, P.; P. Savazzi, (1998). Classification of urban environments
in SAR images: a fuzzy clustering perspective. 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.351-3 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Radar imaging; Remote sensing by radar;
Synthetic aperture radar; Geophysical measurement technique; Land surface;
Terrain mapping; Town; City; Urban environment; sar; Radar remote sensing;
Fuzzy clustering; Algorithm; SAR image; Pyramidal procedure; Green area;
Street; Park; Buildings ; Fuzzy Bough transform
Original abstract: Fuzzy clustering algorithms are used for the interpretation
of high resolution SAR images of urban environments. The idea is to define
a pyramidal procedure suitable for the characterization first of more different
environments (for instance, green areas, streets, and buildings). This
rough analysis is then followed by more oriented fuzzy clustering tools,
devoted to the extraction of more details: in this paper a modified fuzzy
Bough transform is introduced and used to group pixels classified as pixels
in consistent straight lines.
Gao, B. C.; K. B. Heidebrecht; A. F. H. Goetz (1993). Derivation
of Scaled Surface Reflectances from Aviris Data. Remote Sensing
of Environment, V44, (N2-3): 165-178.
Keywords:
Garro, A. J.; M. S. Vignale, (1996). Rhode Island Department of Transportation
utilizing GIS for statewide design, construction and traffic program planning.
URISA Proceedings, Annual Conference. Papers from the Annual Conference
of the Urban and Regional Information Systems Association Proceedings of
URISA 1996 Annual Meeting on Information Systems Salt Lake City, UT, USA
27 July-1 Aug. 1996
Washington, DC, USA Urban & Regional Inf. Syst. Assoc, pp.202-8.
Keywords: Geographic information systems; Scheduling; Traffic information
systems; Rhode Island Department of Transportation; Statewide design; Traffic
program planning; Transportation needs; Transportation system; GIS system;
Highway infrastructure; Construction projects; Highway network; ridot;
Rhode Island Geographic Information System ; Transportation improvement
program
Original abstract: The Intermodal Surface Transportation Efficiency
Act (ISTEA) of 1991 highlighted the importance of developing management
systems to better identify and address our transportation needs and ensure
a quality transportation system. Following this lead, the Rhode Island
Department of Transportation (RIDOT) decided to implement a GIS system
to aid in the overall management of its design, construction and traffic
programs. As the state continues to improve and reconstruct its highway
infrastructure and the number of design and construction projects increase,
it has become more difficult to determine how these projects affect each
other and the surrounding highway network. The system is designed to provide
detailed information on design and construction projects throughout the
state which allows the RIDOT to analyze and make intelligent decisions
regarding scheduling and prioritizing of current projects. The base map
selected for the project was developed by The Rhode Island Geographic Information
System (RIGIS) in a cooperative effort with other state agencies and local
groups. The database was designed to integrate relevant information available
from several sections within the RIDOT into a single unique database. The
development of the management system provides RIDOT with a valuable tool
for the coordination of its overall transportation improvement program
with minimal investment.
Gautam, N. C., (1997). IRS-1C applications for land use/land cover
mapping, change detection and planning. 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.1775-7 vol.4.
Keywords: Agriculture; Cartography; Geophysical techniques; Remote
sensing; Geophysical measurement technique; Land surface; Terrain mapping;
Satellite remote sensing; Optical imaging; Visible; Infrared; Indian Remote
Sensing satellite; irs 1c; Land use; Land cover; Change detection; Planning;
Vegetation mapping; Wide-field Imaging Sensor (WiFS); Linear Imaging Self
Scanning Sensor III; liss iii; Panchromatic sensor; Cadastral ; Urban application
Original abstract: Remote sensing applications using IRS-1A and IRS-1B
data has successfully demonstrated the capabilities in generation of district-wise
land use/land cover maps, depicting the information up to level-II on 1:250,000
scale which are being used as a basic input in land use planning of the
15 agro-climatic zones in the country. The launch of IRS-1C on 28 December,
1995 provided a new dimension in the application capabilities, in particular
for land use/land cover mapping on various scales and levels for use by
a diverse user community. An analysis has been made in the present paper
on the capabilities of Wide-field Imaging Sensor (WiFS), Linear Imaging
Self Scanning Sensor-III (LISS-III), Panchromatic sensor data for land
use applications. It was observed from the above studies that WiFS data
is useful in extracting land use/land cover information at Level-I for
use at National/Regional level applications, LISS-III data useful in extraction
of information at Level-II/III for use at District/Tehsil level applications
and Panchromatic data has the capability to provide information at Level-III/IV
for use in Cadastral and Urban applications.
Geling, G.; D. Ionescu, (1995). Further results on Kalman filters
for speckle noise reduction on SAR images. 1995 Canadian Conference
on Electrical and Computer Engineering (Cat. No.95TH8103) Montreal, Que.,
Canada 5-8 Sept. 1995
New York, NY, USA IEEE, pp.1152-5 vol.2.
Keywords: F. Gagnon
Original abstract: The modified adaptive block Kalman filter (MABKF)
developed by Geling and Ionescu [1994] was designed to reduce the level
of speckle in complex SAR images including urban regions where normal speckle
assumptions are no longer true. In order to improve the performance of
the filter two modifications have been developed. The MABKF filter methodology
has been combined with a dynamic model using a symmetric full-plane region
of support. Additionally, a multiplicative noise term has been added to
the dynamic equation to model the highly variable nature of a complex urban
scene containing many strong reflectors. The filters are demonstrated on
an ERS-1 SAR image of Victoria, B.C.
Gingras, D., (1998). Optics and photonics used in road transportation.
Opto-Contact: Workshop on Technology Transfers, Start-Up Opportunities,and
Strategic Alliances Quebec, Canada 13-14 July 1998
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.264-9.
Keywords: Active vision; Automated highways; Driver information
systems; Image sensors; Laser ranging; Laser velocimetry; Optical scanners;
Optical sensors; Road traffic; Surveillance; Video signal processing; Road
transportation; Contactless measurements; Precise remote measurements;
Photonics; Optical sensing; Automated traffic analysis; Road infrastructures
diagnosis; Quality assessment; Smart driving; Intelligent vehicles; Safety;
Inventories; Tolls; Various outdoor illumination conditions; 3D vision;
Laser triangulation; Video traffic monitoring; Video image processing;
Correlation-based velocimeter; Laser scanners ; Road sign recognition
Original abstract: Photonics is ideal for precise, remote and contactless
measurements in harsh conditions. Thanks to major breakthroughs in the
technologies involved, optical sensing is becoming more compact, robust
and affordable. The purpose of this paper is to provide an overview on
the capabilities of photonics applied to road transportation problems.
In particular we will consider four types of situations: (1) measurements
for traffic analysis and surveillance, (2) measurements for road infrastructures
diagnosis and quality assessment, (3) photonics in smart driving and intelligent
vehicles and (4) measurements for other purposes (safety, inventories,
tolls, etc.). These topics will be discussed and illustrated by using the
results of different projects that have been carried out at INO over the
last few years. We will look at different challenges we had to face such
as performing sensitive optical measurements in various outdoor illumination
conditions and performing fast and accurate measurements without interfering
with normal road traffic flow.
Gipps, P. G.; K. Q. Gu; A. Held; G. Barnett (2001). New technologies
for transport route selection. Transportation Research Part C (Emerging
Technologies), 9C, (2): 135-54.
Keywords: Photogrammetry; Transport route selection; Low cost high
quality routes ; Alignment planning
Original Abstract: Planning a new road or railway can be an expensive
and time-consuming process. There are numerous environmental issues that
need to be addressed, and the problem is exacerbated where the alignment
is also influenced by the location of services, existing roads and buildings,
and the financial, social and political costs of land resumption. A comprehensive
approach to the problem is available through the convergence of: geospatial
imaging, softcopy photogrammetry, regional significance analysis and alignment
optimisation. The first technology is concerned with obtaining low cost
data containing far more information than was available in the past. The
second two are concerned with extracting from that data, information essential
to the planning process. The final technology is about automating the way
alignments are generated to produce low cost, high quality routes. The
convergence of these enabling technologies can have a major impact on the
way that various jobs are performed-or whether they are done at all. Separately,
they can have a major influence on a large number of disciplines, but taken
in combination they can change the paradigm of alignment planning completely.
By taking tasks that were previously difficult, time-consuming and expensive,
and making them easy, fast and cheap, they can change completely the way
alignments are planned.
Girard, S.; P. Guerin; H. Maitre; M. Roux, (1998). Building detection
from high resolution color 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.278-89.
Keywords: Geography; Geophysical signal processing; Image colour
analysis; Image recognition; Image reconstruction; Image resolution; Remote
sensing; Building detection; High resolution color images; Reconstruction;
Dense urban areas; Aerial images; Dense digital elevation model; Sparse
disparity map; Region-based segmentation; Noise; Complexity; Planar approximation;
Fusion; Symmetrical regions; 3D object space; Bruxelles ; Suburb
Original abstract: We describe a new method for the detection and reconstruction
of buildings in dense urban areas using high resolution aerial images.
Our approach begins with the generation of a dense digital elevation model
(DEM). A sparse disparity map is densified using a region-based segmentation
of the left aerial image: each detected region is tested to be planar in
the disparity map. A strategy is proposed to optimize the generation of
these planar surfaces taking into account the noise present in the sparse
disparity map and the robustness and complexity of different algorithms
for planar approximation. The second step of our approach deals with the
generation of building hypotheses. Based on the DEM previously computed,
geometric and colorimetric criteria are used for the fusion of parallel
regions, for the detection of symmetrical regions in the 3D object space
and for the reconstruction of roof buildings. Experimental results are
presented on a scene in the suburb of Bruxelles with color images at the
resolution of 10 cm/pixel.
Goetz, S. J.; S. D. Prince; M. M. Thawley; A. J. Smith; R. Wright; M.
Weiner, (2000). Applications of multi-temporal land cover information
in the mid-Atlantic region: a RESAC initiative. 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.357-9 vol.1.
Keywords: Geophysical techniques; Remote sensing; Terrain mapping;
Vegetation mapping; Geophysical measurement technique; Land surface; United
States; usa; Multi-temporal land cover information; Mid-Atlantic region;
resac; Image sequence; Regional Earth Science Applications Center; Maryland;
Chesapeake Bay watershed; Satellite remote sensing; Change; Land use; Nutrient
runoff; Urban sprawl; Farm; Agriculture ; Forest
Original abstract: The mid-Atlantic Regional Earth Science Applications
Center (RESAC) was established in the Geography Department at the University
of Maryland (UMD) by NASA's Earth Science Applications Program. The mid-Atlantic
RESAC is to provide improved land cover mapping and ecological modeling
capabilities for a diverse consortium of partners in government, academia,
industry and NGOs within the 178000 km/sup 2/ Chesapeake Bay watershed.
It is one of 7 regional centers established nationwide and leverages expertise
in satellite remote sensing to address applications of regional significance
including land cover change, land use planning, carbon exchange modeling,
and integrated environmental monitoring. Examples of issues that are being
addressed include nutrient runoff to the Chesapeake Bay, urban sprawl,
farm and forest productivity, landscape fragmentation effects on biodiversity,
a land manager decision support system, and educational outreach. The mid-Atlantic
RESAC provides an example of how scientific advances can be focused on
practical applications that challenge our ability to manage resources sustainably.
A brief overview of the RESAC is provided and specific applications are
reviewed using examples that emphasize the utility of remote sensing and
GIS capabilities. Results of field activities undertaken during the 1999
growing season, for example, are used with a fusion of multi-temporal Landsat-7
Enhanced Thematic Mapper and SPOT panchromatic imagery to classify vegetation
types, and to characterize development of the severe drought that took
place in the region.
Goforth, M. A., (1998). Fusion of differing resolution imagery using
multiresolution analysis. Proceedings of the International Conference
on Multisource-Multisensor Information Fusion. FUSION '98 Las Vegas, NV,
USA 6-9 July 1998
Athens, GA, USA CSREA Press, pp.419-26 vol.1.
Keywords: Feature extraction; Geophysical signal processing; Image
classification; Image matching; Image resolution; Minimisation; Optical
transfer function; Remote sensing; Sensor fusion; Spectral analysis; Data
fusion; Multiresolution analysis; Panchromatic imagery; Spatial resolution;
Low-resolution spectral imagery; Spatial/spectral sharpening; mra/mtf;
Modulation transfer function; Detail extraction; Spectral distortion minimization;
Classification maps; Spectral fidelity; Landsat imagery; Aerial photography
; ERDAS Imagine
Original abstract: High-resolution panchromatic imagery can be used
to increase the spatial resolution of low-resolution spectral imagery through
spatial/spectral sharpening techniques. A model for fusion of data from
sensors with differing resolutions, called MRA/MTF, is presented. Before
fusion of imagery with differing resolution, the images are matched in
their spatial response through a correction to their modulation transfer
function (MTF). The spatial detail is extracted from the high-resolution
image by multiresolution analysis (MRA) and applied to the low-resolution
image in a way that minimizes the spectral distortion of the image so that
accurate classification maps can be derived from the sharpened imagery.
This presentation of the spectral fidelity is demonstrated visually as
well as quantitatively for Landsat imagery sharpened with aerial photography
and compared with other resolution enhancement algorithms available within
ERDAS Imagine.
Goncalves, M. L., (1999). A neural system for remote sensing multispectral
image classification. Neural Nets WIRN VIETRI-98. Proceedings of the
10th Italian Workshop on Neural Nets Salerno, Italy 21-23 May 1998
London, UK Springer-Verlag London, pp.218-23.
Keywords: Feature extraction; Image classification; Multilayer perceptrons;
Self-organising feature maps; Unsupervised learning; Remote sensing; Multispectral
image classification; Neural system; Artificial neural networks; Kohonen
self-organizing map; Classification ; Multilayer Perceptron
Original abstract: This work presents a system for Remote Sensing (RS)
multispectral image classification based on Artificial Neural Networks
(ANN), aiming at two objectives, namely: searching of techniques for improving
the performance in the classification task and to exploit the advantages
of unsupervised learning for feature extraction. The system is divided
in two phases: feature extraction by the Kohonen Self-Organizing Map (SOM)
and classification by a Multilayer Perceptron (MLP) network, trained by
a learning algorithm which uses 2nd-order information exactly calculated.
To evaluate the efficiency of this classification scheme, a comparative
analysis with the maximum likelihood algorithm, conventionally used for
RS multispectral images classification, is realized.
Goncalves, M. L.; M. L. de Andrade Netto; J. Zullo Junior, (1998). A
neural architecture for the classification of remote sensing imagery with
advanced learning algorithms. Neural Networks for Signal Processing
VIII. (Cat. No.98TH8378) Proceedings of the 1998 IEEE Signal Processing
Society Workshop Cambridge, UK 31 Aug.-2 Sept. 1998
New York, NY, USA IEEE, pp.577-86.
Keywords: Feature extraction; Image classification; Multilayer perceptrons;
Neural net architecture; Remote sensing; Self-organising feature maps;
Unsupervised learning; Neural architecture; Multispectral images; Kohonen
self-organizing map; Multilayer perceptron ; LANDSAT/TM image
Original abstract: This work presents an artificial neural networks
based architecture for the classification of remote sensing (RS) multispectral
imagery. The architecture consists of two processing modules: an image
feature extraction module using Kohonen self-organizing map and a classification
module using multilayer perceptron network. The architecture was developed
aiming at two specific goals: to exploit the advantages of unsupervised
learning for feature extraction, and the testing of techniques to increase
the learning algorithm's performance concerning training time. To test
the applicability of this work, the architecture was applied to the classification
of a LANDSAT/TM image segment from a pre-selected testing area and its
performance was compared with that of a maximum likelihood classifier,
conventionally used for RS multispectral images classification.
Gong, P.; J. Wang, (1997). Road network extraction from airborne
digital camera images: a multi-resolution comparison. 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.895-7 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Image resolution; Remote sensing; Geophysical
measurement technique; Land surface; Terrain mapping; Optical imaging;
Multispectral remote sensing; Visible; Infrared; Urban area; Suburban area;
Road network extraction; Airborne digital camera image; Multiresolution
comparison; Advanced linear analysis; Gradient direction profile analysis;
Algorithm; Clustering; Contextual classifier; Context; Image clustering
; Morphologically filtered image
Original abstract: As image resolution increases from 10-30 m to 0.5-2
m, road networks will appear to be narrow areas rather than thin lines.
This becomes a challenge for traditional linear analysis methods based
on mask operations but creates an opportunity for classification based
methods. The authors experimented with an advanced linear analysis, gradient
direction profile analysis, and a few classification algorithms including
a maximum classification, clustering and a contextual classifier for road
network extraction using airborne digital camera data acquired over Livermore,
California with approximately 1.6 m spatial resolution. Results indicate
that both the linear extraction and image clustering algorithms worked
reasonably well. The best road network results have been obtained by applying
the linear extraction algorithm to a morphologically filtered image that
was generated by combining the near infrared (NIR) and red (R) image bands
through NIR/R+NIR. With this method, the correctly extracted road pixels
account for 78.7% of the total road pixels obtained from image interpretation
with field verification. The image clustering method resulted in 74.5%
correctly extracted road pixels. When experimenting with the images resampled
at approximately 3 m and 5 m resolution, the best overall accuracies for
road extraction decreased to 74.6% and 61.6%, respectively.
Goodchild, M. F. (2000). GIS and transportation: status and challenges.
GeoInformatica, 4, (2): 127-39.
Keywords: Cartography; Computerised navigation; Geographic information
systems; Transportation; Visual databases; gis-t; Map view; Navigational
view; Behavioral view; Inventory; Description; Accuracy; Interoperability;
Connectivity; Planarity; Time-dependent attribute storage; Lane-level connectivity;
Standards; Representation; Unambiguous communication; Economic models ;
New technology response
Original Abstract: The evolution of GIS-T is characterized in three
stages: the map view, navigational view, and behavioral view. The static
nature of the map view favors applications related to inventory and description,
and raises difficult questions of accuracy and interoperability. The navigational
view adds concerns for connectivity and planarity, and the storage of time-dependent
attributes. Navigation also raises issues of representation related to
scale, including the need for lane-level connectivity. The behavioral view
stems from the work of Hagerstrand (1970), treating transportation events
as dynamic and occurring within the largely static transportation space.
Appropriate representations for the behavioral view have still to be worked
out. In all three cases the legacies of prior technologies and perspectives
are still evident. The paper presents a series of research challenges,
dealing with standards, representation, unambiguous communication, economic
models, response to new technologies, and application of knowledge gained
from GIS-T and ITS research to other fields.
Gosinski, T.; S. Avila, (1995). Implementing a regional traffic data
management system. 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.735-43.
Keywords: Geographic information systems; Government data processing;
Legislation; Road traffic; Town and country planning; Traffic information
systems; Regional traffic data management system; Intermodal Surface Transportation
Efficiency Act; Clean Air Act Amendment; Transportation decision-making;
Local governments; Regional governments; Metropolitan planning organizations;
Transportation data collection activities; Technical resources; Collected
data sets integration; Transportation project assessment; User access;
Houston-Galveston Area Council; Desktop client-server system; Innovative
System Developers Inc.; gis; Graphical user interface; Inter-agency users;
Intra-agency users; Integrated modeling environment ; Transportation planning
Original abstract: The development of the Intermodal Surface Transportation
Efficiency Act (ISTEA) and the Clean Air Act Amendment (CAAA) expands the
transportation decision-making role of local and regional governments.
This increased importance of decision-making in transportation issues requires
increased attention to both the justification and analysis of transportation
initiatives. Therefore, metropolitan planning organizations (MPOs) must
coordinate transportation data collection activities and maximize available
technical resources. Integrating collected data sets (such as traffic counts,
vehicle mixes, roadway characteristics, functional classifications, employer
statistics and land use information) are vital for the assessment of transportation
projects. Combining data with analytical tools and providing access to
all users enhances the success of programs such as air quality control,
employer trip reduction, management system development and other mandated
requirements of ISTEA and CAAA. The Houston-Galveston Area Council (H-GAC),
which is the Houston area MPO, is addressing these issues by developing
a desktop, client-server traffic data management system (TDMS). Furthermore,
H-GAC has teamed up with Innovative System Developers Inc. in utilizing
GIS technologies to allow transportation professionals to efficiently store,
display, query, analyze and disseminate information. The TDMS includes
a graphical user interface which allows both inter- and intra-agency users
to employ an integrated modeling environment in support of transportation
planning and programs.
Gouinaud, C.; F. Tupin; H. Maitre, (1996). Potential and use of radar
images for characterization and detection of urban areas. 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.474-6 vol.1.
Keywords: Geophysical techniques; Radar imaging; Remote sensing
by radar; Spaceborne radar; Land surface; Terrain mapping; Radar remote
sensing; Geophysical measurement technique; Radar image; Urban area; Town;
City; ers-1; Man-made structure; Captor response; Detection method; Landscape;
Aix-en-Provence; Kourou; French Guyana ; France
Original abstract: The resolution of ERS-1 images should let allow
man-made structures like urban areas to be detected. After a brief survey
of the captor response to urban objects, the authors propose a method to
detect urban areas. They illustrate the results obtained on two typical
landscapes: European agricultural hilly landscapes and tropical zones.
Some urban detections are presented both on Aix-en-Provence and Kourou
towns in French Guyana.
Gouinaut, C.; I. Pons, (1996). Use of geometrical SAR simulation
for visibility prediction: application to mission planning and urban study.
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.257-9 vol.1.
Keywords: Geophysical techniques; Radar imaging; Remote sensing
by radar; Spaceborne radar; Synthetic aperture radar; Geophysical measurement
technique; Radar remote sensing; View direction; Terrain mapping; Land
surface; City; Town; Urban area; Geometrical simulation; sar; Visibility
prediction; Observability prediction; Geometrical distortion; SAR image;
Shadow; Lay over; Multiincidence radar image; Digital elevation model;
Ray-tracing; Radar geometry; Incidence angle ; Mission planning
Original abstract: The specification of future radar satellites and
many remote-sensing applications need information about the geometrical
distortions seen in a SAR image. The main geometrical distortions are those
that are called "shadow" and "lay-over"; it is very difficult to quantify
them with a lone SAR image, but the use of many SAR images allows a numerical
evaluation of these distortions. Unfortunately not only is this procedure
very expensive, but also, before the launch of RADARSAT only SIR C produced
satellite multiincidence radar images. On the contrary, digital elevation
models are easy to access, for a large variety of countries and landscapes.
The authors show the interest of geometrical SAR simulations in order to
estimate the probability of geometrical distortions and extract practical
information concerning visibility. They describe their approach of SAR
simulation, based on an adaptation of ray-tracing to radar geometry, and
expose two specific applications. The first one is used to specify the
best incidence angle for the simulation with a representative DEM base
(100000 km/sup 2/), and the second one is used to predict the visibility
of urban objects with specific satellites. This work is based on incidence
angle specification for RADARSAT III, and emphasizes the radar potential
for urban study.
Goulias, D. G.; K. G. Goulias, (2000). GIS in pavement and transport
management. Management Information Systems 2000. Second International
Conference on Management Information Systems Incorporating GIS and Remote
Sensing. Udine, Italy May 2000
Southampton, UK WIT Press, pp.165-75.
Keywords: Civil engineering computing; Emergency services; Geographic
information systems; Traffic information systems; Transportation; Visual
databases; gis; Pavement management; Transport management; Transportation
planning; Spatial analysis; Time dependent analysis; Highway engineering;
gis-t; Maintenance data; Cost models; Emergency management; Human behavior
models; Demographic information ; Land-use information
Original abstract: The use of geographic information systems in transportation
(GIS-T) can greatly enhance spatial and time dependent analysis. Its use
in highway engineering and transportation planning/operations has been
significantly intensified since GIS permits the assimilation, integration,
modeling, and visualization of time and space related data and predictions.
This paper presents two representative case studies on the development
and use of GIS-T in: (i) pavement management and highway analysis, integrating
performance models, user and agency cost models and pavement condition
information (in terms of inventory and maintenance data); and (ii) emergency
management and traffic operations, integrating models of human behavior,
transportation network characteristics, and detailed regional demographic
and land-use information. In the development of these GIS based management
systems, temporal and spatial modeling was used for describing spatio-temporal
phenomena and predicting future conditions. The methodologies illustrated
can be adapted in other regions, and the GIS based systems are flexible
enough to allow for the integration of any models representing local and/or
regional conditions elsewhere.
Gracia, I.; M. Petrou; A. J. Fraser, (1998). Line tracking from satellite
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.261-7.
Keywords: Buried object detection; Edge detection; Feature extraction;
Image texture; Nonlinear filters; Optical tracking; Remote sensing; Line
tracking; Satellite images; Detection; Buried linear features; Surface
coverage; Buried structure; Contrast; Texture; Over-ground growth; Aerial
photographs; Statistical nonlinear filters; Enhancement; Lateral continuity
; Arbitrary shape
Original abstract: We present an algorithm for the detection and tracking
of buried linear features under a variety of surface coverages. The buried
structures manifest themselves as a few pixels wide bands with contrast
and texture changes of the over-ground growth, in high 1 m resolution aerial
photographs. Some statistical non-linear filters are used to enhance these
features, and their response is further enhanced by lateral continuity,
taking into consideration prior knowledge about the shape of the feature.
Grau, A.; J. Climent; J. Aranda, (1998). Terrain segmentation by
structural texture discrimination. 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.339-44.
Keywords: Image segmentation; Image texture; Remote sensing; Structural
texture discrimination; Terrain segmentation; Texture print; Texture analysis;
Gray level intensity function; Image region size; Histograms; String-to-string
correction problem; Placement rules; Primitives; Elements; Texture regions;
Distance measure; Minimum-cost sequences; Edit operations; Leveshtein distance;
Algorithm; Urban areas ; Rural areas
Original abstract: We present a new algorithm to generate the texture
print of a region in an image. For this texture analysis, a texture print
is found by means of counting the number of changes in the sign of the
derivative in the gray level intensity function by rows and by columns,
over a region with size N*N. These two histograms are represented as a
unique string R of symbols. Therefore, a string-to-string correction problem
as placement rules of elements (primitives) obtained statistically is used.
In order to discriminate different texture regions a distance measure on
strings based on minimum-cost sequences of edit operations is computed,
this measure is the Leveshtein distance. The proposed algorithm is useful
to discriminate between urban areas and rural areas due to the change in
their textural aspect.
Green, R. O.; M. L. Eastwood; C. M. Sarture; T. G. Chrien; M. Aronsson;
B. J. Chippendale; J. A. Faust; B. E. Pavri; C. J. Chovit; M. S. Solis;
M. R. Olah; O. Williams (1998). Imaging spectroscopy and the Airborne
Visible Infrared Imaging Spectrometer (AVIRIS). Remote Sensing of
Environment, V65, (N3): 227-248.
Keywords: AVIRIS sensor
Original Abstract: Imaging spectroscopy is of growing interest as a
new approach to Earth remote sensing. The Airborne Visible/Infrared Imaging
Spectrometer (AVIRIS) was the first imaging sensor to measure the solar
reflected spectrum from 400 nm to 2500 nm at 10 nm intervals. The calibration
accuracy and signal-to-noise of AVIRIS remain unique. The AVIRIS system
as well as the science research and applications have evolved significantly
in recent years. The initial design and upgraded characteristics of the
AVIRIS system are described in terms of the sensor, calibration, data system,
and flight operation. This update on the characteristics of AVIRIS provides
the context for the science research and applications that use AVIRIS data
acquired in the past several years. Recent science research and applications
are reviewed spanning investigations of atmospheric correction, ecology
and vegetation, geology and soils, inland and coastal waters, the atmosphere,
snow and ice hydrology, biomass burning, environmental hazards, satellite
simulation and calibration, commercial applications, spectral algorithms,
human infrastructure, as well as spectral modeling.
Growe, S.; R. Tonjes, (1998). Use of explicit knowledge and GIS data
for the 3D evaluation of remote sensing images. Proceedings. Fourteenth
International Conference on Pattern Recognition (Cat. No.98EX170) Brisbane,
Qld., Australia 16-20 Aug. 1998
Los Alamitos, CA, USA IEEE Comput. Soc, pp.1413-15 vol.2.
Keywords: Data visualisation; Feature extraction; Geographic information
systems; Image reconstruction; Image registration; Image texture; Knowledge
based systems; Remote sensing; Stereo image processing; Remote sensing
images; Image interpretation; Semantic nets; Digital landscape model; Geographic
information system; Real time visualization; 3D geometry ; Polygon mesh
Original abstract: The evaluation of 3D scenes observed from different
sensors requires the co-registration of sensor images and the reconstruction
of the 3D geometry. To solve both tasks the presented system exploits prior
knowledge, represented explicitly by semantic nets, and uses a digital
landscape model of a geographic information system (GIS) as a hint for
the object location. This is shown for the detection of control points
for image registration and the extraction of objects (roads, buildings)
for 3D reconstruction. For real time visualization the 3D geometry is approximated
by a polygon mesh with overlaid photo texture.
Growe, S.; R. Tonjes, (1997). A knowledge based approach to automatic
image registration. Proceedings. International Conference on Image
Processing (Cat. No.97CB36144) Santa Barbara, CA, USA 26-29 Oct. 1997
Los Alamitos, CA, USA IEEE Comput. Soc, pp.228-31 vol.3.
Keywords: Feature extraction; Geographic information systems; Image
matching; Image registration; Knowledge based systems; Radar imaging; Remote
sensing; Remote sensing by radar; Synthetic aperture radar; Knowledge based
approach; Automatic image registration; Automatic control point matching;
Remotely sensed images; Flight parameters; Sensor specific appearance;
Prior knowledge; Control points; gis; Semantic nets; Rules; A*-algorithm;
Crossroads; Aerial imagery ; SAR imagery
Original abstract: The presented work addresses the problem of automatic
control point matching for the registration of remotely sensed images.
The inaccuracy of flight parameters and the sensor specific appearance
of objects are the difficulties automatic registration suffers from. To
overcome these problems the presented system uses prior knowledge to select
appropriate structures for matching, i.e. control points, from a GIS and
to extract their corresponding features from the sensor data. The knowledge
is represented explicitly using semantic nets and rules. The best correspondence
between the GIS data and the image is found by an A*-algorithm. The automatic
control point matching is demonstrated for crossroads in aerial and SAR
imagery.
Guindon, B., (1998). Application of spatial reasoning methods to
the extraction of roads from high resolution satellite 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.1076-8 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image recognition; Remote sensing; Geophysical measurement
technique; Land surface; Terrain mapping; Image processing; Spatial reasoning
method; Road; Highway; High resolution satellite imagery; High resolution
imaging; Rule-based recognition algorithm; Residential street; Urban scene;
Town ; City
Original abstract: By the end of this decade the civilian remote sensing
community will have access to timely satellite imagery at high spatial
resolution (1-3 meters). This will open the door for new applications,
such as detailed topographic mapping. These data can be considered to be
in a *transition' spatial resolution regime between conventional, low resolution
satellite imagery and aerial photography. Correspondingly, information
extraction methodologies to exploit these data must draw on both the data-driven,
per-pixel processing of conventional satellite image analysis and the object-driven,
image understanding technologies now being developed for aerial photography.
This paper describes experiments to evaluate rule-based recognition algorithms
for the purpose of automating planimetric feature extraction from these
new satellite data. The overall feature extraction strategy is one drawn
from image understanding namely spatial reasoning with a segmented rendition
of the image. Recognition involves applying a set of evidence-accumulation
attribute (inherent spatial/spectral and context) tests to selected segments
in order to identify candidates which may form all or part of an object
of interest. Conventional classification *training' has been modifed to
develop a novel approach to evidence weight quantification and to assess
inter-test correlation, analogous to conventional covariance. A recognition
system has been developed to recognize residential streets in imagery.
Gunawardena, A.; J. Schroeder, (1998). Polynomial Hough transform
based feature extraction from SAR imagery. EUSAR'98. European Conference
on Synthetic Aperture Radar Proceedings of EURSAR '98: Friedrichshafen,
Germany 25-27 May 1998
Berlin, Germany VDE VERLAG GMBH, pp.273-6.
Keywords: Edge detection; Feature extraction; Hough transforms;
Matched filters; Polynomials; Radar imaging; Remote sensing by radar; Synthetic
aperture radar; Polynomial Hough transform; SAR imagery; Curvilinear features;
Roads; Rivers; Edge detector; 2-D Gaussian kernel; Matched filtering; Hough
space; Thresholding ; Real SAR data
Original abstract: This paper proposes a processing scheme for extraction
of curvilinear features such as roads and rivers from synthetic aperture
radar (SAR) imagery. The processing consists of three stages. The first
stage is an edge detector operating on data smoothed by a 2-D Gaussian
kernel. The second stage is a polynomial Hough transform. The final stage
consists of matched filtering in the Hough space followed by thresholding.
The performance of the proposed processing scheme is demonstrated using
real SAR data.
Haala, N.; C. Brenner (1999). Extraction of buildings and trees in
urban environments. Isprs Journal of Photogrammetry and Remote Sensing,
V54, (N2-3): 130-137.
Keywords: feature extraction airborne laser scanning
Synopsis: Discusses use of ALS in urban settings, extraction of urban
features. Their method: combine multispectral information from color images
with geometric information from laser scanner DSM.
Original Abstract: In this article, two methods for data collection
in urban environments are presented. The first method combines multispectral
imagery and laser altimeter data in an integrated classification for the
extraction of buildings, trees and grass-covered areas. The second approach
uses laser data and 2D ground plan information to obtain 3D reconstructions
of buildings.
Haala, N.; C. Brenner (1998). Interpretation of urban surface models
using 2D building information. Computer Vision and Image Understanding,
72, (2): 204-14.
Keywords: Computer vision; Feature extraction; Geographic information
systems; Image reconstruction; Image segmentation; Object recognition;
Remote sensing; Stereo image processing; Urban surface models; 2D building
images; 3D image reconstruction; Image interpretation; Digital surface
models; Stereo image matching; Aerial images; Surface geometry; Planar
surfaces ; Geographic information system
Original Abstract: In 3D building reconstruction the interpretation
process can be simplified if digital surface models (DSM), which can either
be derived from stereo matching of aerial images or be directly measured
by scanning laser systems, are used in addition to or instead of image
data. The images contain much information, but the resulting complexity
causes enormous problems for an automatic interpretation of this data type.
Since the information of a DSM is restricted to surface geometry its interpretation
is simplified by the absence of unnecessary details. Nevertheless, due
to insufficient spatial resolution and quality of the DSM, especially for
these applications, optimal results can only be achieved by the use of
additional data sources. Within the approach presented the segmentation
of planar surfaces from the DSM is supported by existing ground plans.
This 2D building information is also used to derive hypotheses on the possible
roof shapes in order to obtain a 3D boundary representation based on the
segmented planes.
Hae Yeoun, L.; P. Wonkyu; L. Heung-Kyu; K. Tak-gon, (2000). Towards
knowledge-based extraction of roads from 1 m-resolution satellite images.
4th IEEE Southwest Symposium on Image Analysis and Interpretation Proceedings
Austin, TX, USA 2-4 April 2000
Los Alamitos, CA, USA IEEE Comput. Soc, pp.171-6.
Keywords: Computer vision; Feature extraction; Gradient methods;
Image resolution; Image segmentation; Knowledge based systems; Remote sensing;
Knowledge-based extraction; Road extraction; Satellite images; IKONOS satellite;
Mapping; Spaceborne images; Photogrammetry; Road region extraction; Approximated
road regions; Region segmentation; Hierarchical watershed transformation;
Multi-scale gradient watershed transformation; Road gray level; Elongatedness
; Connectedness
Original abstract: As the IKONOS satellite with 1 m-resolution camera
was launched in 1999, mapping using spaceborne images will be an important
issue in the computer vision area as well as photogrammetry, mainly because
most major man-made objects of interest can be identifiable. One of the
automatically identifiable objects of importance may be roads. Detecting
roads using edge detection approaches may be very difficult because a number
of edge elements from such as buildings, etc., can be generated from edge
detector. In this paper, we propose a method for the extraction of approximated
road regions based on region segmentation that utilizes region information.
Our method consists of the following three steps. First, an image is segmented
using the modified hierarchical multi-scale gradient watershed transformation.
Then, the road candidates are identified using information about road gray
level, elongatedness and connectedness. The identified road candidates
are expanded by connecting the close-by roads knowing that roads are connected
objects. Our method was tested on the simulated spaceborne images and the
result shows that the automation of road extraction is quite promising.
Hagg, W.; K. Segl; M. Sties, (1995). Classification of urban areas
in multi-date ERS-1 images using structural features and a neural network.
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.901-3 vol.2.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Image sequences; Image texture; Neural
nets; Radar applications; Radar imaging; Remote sensing by radar; Spaceborne
radar; Synthetic aperture radar; Geophysical measurement technique; Radar
remote sensing; Image processing; SAR image; Land surface; Terrain mapping;
Urban area; Multi-date ERS-1 image; Image sequence; Structural feature;
Neural network; Neural net; Inhomogeneity ; RBF-Network
Original abstract: Describes a new method to extract structural informations
from images. The loss of spatial resolution and distortions-from edges,
as it occurs with standard texture algorithms, are reduced to a minimum.
Furthermore, the authors describe the inhomogeneity by three different
structure types according to the structures contained in SAR images. Finally
they use a neural network (RBF-Network) to get a more precise classification
of urban areas from SAR images.
Haley, L., (1997). Integrating GIS and Oracle for traffic analysis.
Proceedings AM/FM International Proceedings of AM/FM International's Annual
Conference *Entering the Mainstream' Nashville, TN, USA 23-26 March 1997
Aurora, CO, USA AM/FM Int, pp.209-17.
Keywords: Geographic information systems; Graphical user interfaces;
Integrated software; Planning; Public administration; Relational databases;
Traffic engineering computing; Transportation; Software integration; Oracle;
City of Bloomington; am/fm/gis; Relational database; Data tables; GenaMap;
Traffic engineers; Transportation planners; Traffic accident report; Traffic
count; Graphical user interface ; GENIUS II GUI builder
Original abstract: The City of Bloomington initiated the development
of an AM/FM/GIS system in 1989. A completed base map of land-based features
and water, wastewater, and storm water systems has been in place since
early 1994. The City's initial focus was on maintaining its base map, expanding
map features related to planning, public works, and utilities, and developing
end-user applications for basic viewing, outputting, and querying map information.
The City views GIS as part of a larger information management system and
is now working towards integrating GIS with other data systems to serve
end-user needs across departmental boundaries. With this goal in mind,
the City is developing applications to integrate Oracle relational database
software data tables with its GenaMap GIS software. One of the first applications
projects involved creating a traffic analysis application for traffic engineers
and transportation planners. Data tables were designed for traffic accident
report, traffic count, and thoroughfare data and linked to the GIS road
centerline network. Staff also entered intersection condition diagrams
into the GIS. End-users can display, manipulate, and output graphic and
ancillary information through a custom graphical user interface (GUI) created
with GenaMap's GENIUS II GUI builder.
Hardin, P. J., (1999). Neural networks vs. nonparametric neighbor-based
classifiers for semisupervised classification of Landsat imagery. Applications
and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation
II Denver, CO, USA 19-20 July 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.252-63.
Keywords: Feature extraction; Feedforward neural nets; Image classification;
Learning (artificial intelligence); Remote sensing; Nonparametric neighbor-based
classifiers; Semisupervised image classification; Landsat imagery; Landcover
maps; Clustering; Feedforward neural network ; Pixel assignment
Original abstract: Semisupervised classification is one approach to
converting multiband optical and infrared imagery into landcover maps.
First, a sample of image pixels is extracted and clustered into several
classes. The analyst next combines the clusters by hand to create a smaller
set of groups that correspond to a useful landcover classification. The
remaining image pixels are then assigned to one of the aggregated cluster
groups by use of a per-pixel classifier. This research reports the results
of an experiment conducted on six Landsat TM images to compare the accuracy
of pixel assignment performed by four nearest neighbor classifiers and
two neural network paradigms in a semisupervised context. In all the experiments,
it is shown that the feedforward network classifier generally produced
the highest accuracy on all six of the images, but it was not significantly
better than the accuracy produced by the best neighbor-based classifier.
Harman, L., (1999). Remote Sensing Applications for Transit Planning and Operations (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,
Hasegawa, H.; H. Aoki; F. Yamazaki; M. Matsuoka; I. Sekimoto, (2000).
Automated detection of damaged buildings using aerial HDTV 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.310-12 vol.1.
Keywords: Earthquakes; Geophysical signal processing; Geophysical
techniques; High definition television; Image processing; Image texture;
Remote sensing; Terrain mapping; Geophysical measurement technique; Town;
City; Urban area; Earthquake damage; Land surface; Optical imaging; Buildings;
Automated detection; Damaged buildings; Building damage; hdtv; Aerial image;
High-definition television; Kobe earthquake; ad 1995; Japan; Color indices;
Edge intensity; Hue; Saturation; Threshold value ; Colour index
Original abstract: In order to seek the possibility of automated detection
of damaged buildings from aerial television, the characteristics of high-definition
television (HDTV) images taken after the 1995 Kobe earthquake were investigated.
The relationships between the degree of building damage and the color indices
and edge intensity from the aerial images were examined by image processing
techniques. The characteristics of building damage were defined on the
basis of hue, saturation, brightness and edge intensity. Using the threshold
values of these parameters, the typical areas were classified into damaged
and undamaged pixels. A texture analysis was further conducted to these
pixels and damaged buildings were identified. The extracted damage distribution
by the proposed method agreed well with ground truth data and visual inspection
of the HDTV images.
Heene, G.; S. Gautama, (2000). Optimisation of a coastline extraction
algorithm for object-oriented matching of multisensor satellite imagery.
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.2632-4 vol.6.
Keywords: Edge detection; Feature extraction; Geophysical signal
processing; Geophysical techniques; Image processing; Object-oriented methods;
Oceanographic techniques; Optimisation; Remote sensing; Sensor fusion;
Geophysical measurement technique; Ocean; Coast; Coastline; Terrain mapping;
Feature extraction algorithm; Object-oriented matching; Multisensor satellite
imagery; Image fusion; Data fusion; Optimized extraction; Point based method;
Masking step; Edge focusing ; Closing step
Original abstract: The authors examine the optimized extraction of
coastlines in multisensor satellite imagery as a first step in the object-oriented
matching of these images, using whole coastlines as the matching features
instead of a point based method. Typically, they want to extract these
coastlines with the best positional accuracy possible, together with suppression
of unnecessary detail. For this purpose, they add two additional masking
steps, an edge focusing and a closing step to the edge detection process.
Heikkonen, J.; I. Kanellopoulos; A. Varfis; A. Steel; K. Fullerton,
(1997). Urban land use mapping with multi-spectral and SAR satellite
data using neural networks. 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.1660-2 vol.4.
Keywords: Backpropagation; Feature extraction; Geophysical signal
processing; Geophysical techniques; Geophysics computing; Image classification;
Image sequences; Image texture; Multilayer perceptrons; Radar imaging;
Remote sensing; Remote sensing by radar; Sensor fusion; Spaceborne radar;
Synthetic aperture radar; Geophysical measurement technique; Radar remote
sensing; Optical imaging; Data fusion; Land surface; Terrain mapping; Image
processing; Urban land use; Multispectral imaging; Multilayer perceptron;
Neural net; Neural network; Gabor feature; Multitemporal data; sar; res-1;
SOM algorithm; Decision tree algorithm ; Feature selection
Original abstract: Statistical, textural and Gabor features were extracted
from integrated multitemporal multispectral TM data and ERS-1 SAR imagery
for urban land use mapping. The computed features are first normalised
using the SOM algorithm and then a decision tree algorithm is applied for
feature selection. The classification procedure was carried out with a
multilayer perceptron, trained with the resilient backpropagation algorithm.
The authors' results demonstrate the potential of the proposed methodology.
Heikkonen, J.; A. Varfis (1998). Land cover/land use classification
of urban areas: a remote sensing approach. International Journal
of Pattern Recognition and Artificial Intelligence, 12, (4):
475-89.
Keywords: Cartography; Feature extraction; Pattern classification;
Remote sensing; Self-organising feature maps; Trees (mathematics); Land
cover classification; Land use classification; Urban areas; Feature coding;
Feature selection; Self-organizing map; Regression trees; Landsat TM; ERS-1
SAR images; Lisbon ; Neural networks
Original Abstract: This paper proposes a method for remote sensing
based land cover/land use classification of urban areas. The method consists
of four main stages: feature extraction, feature coding, feature selection
and classification. In the feature extraction stage, statistical, textural
and Gabor features are computed within local image windows of different
sizes and orientations to provide a wide variety of potential features
for the classification. Then the features are encoded and normalized by
means of the self-organizing map algorithm. For feature selection a classification
and regression trees based algorithm was developed to select a subset of
features for each class within the classification scheme at hand. The selected
subset of features is not attached to any specific classifier. The paper
reports experiments in land cover/land use classification with the Landsat
TM and ERS-1 SAR images gathered over the city of Lisbon to show the potentials
of the proposed method.
Heikkonen, J.; A. Varfis; G. Wilkinson; I. Kanellopoulos; K. Fullerton;
A. Steel, (1997). Satellite image-based land cover/land use classification
of urban areas. Neural Networks in Engineering Systems. Proceedings
of the 1997 International Conference on Engineering Applications of Neural
Networks Stockholm, Sweden 16-18 June 1997
Turku, Finland Syst. Eng. Assoc, pp.9-16 vol.1.
Keywords: Decision trees; Feature extraction; Geography; Image coding;
Image texture; Learning (artificial intelligence); Multilayer perceptrons;
Radar imaging; Remote sensing by radar; Self-organising feature maps; Statistical
analysis; Synthetic aperture radar; Satellite image; Land cover; Land use
classification; Urban areas; Feature coding; Feature selection; Statistical
features; Textural features; Gabor features; Self-organizing map; Decision
tree; Multilayer perceptron; Training; Lisbon; Landsat TM; ers-1 ; SAR
images
Original abstract: A system for satellite image-based land cover/land
use classification of urban areas is described. The system consists of
the following main stages: feature extraction, feature coding, feature
selection and classification. In feature extraction statistical, textural
and Gabor features are computed from satellite images. Next the features
are encoded and normalized by the self-organizing map algorithm and a decision
tree-based algorithm was developed to select relevant features for the
land cover/land use classification scheme at hand. Finally a multilayer
perceptron is trained to map the selected features into the classes. The
proposed system is tested on a land cover/land use classification task
in the city of Lisbon with Landsat TM and ERS-1 SAR images, and the results
show the potential of the proposed methodology.
Heinz, D. C.; C. I. Chang (2001). Fully constrained least squares
linear spectral mixture analysis method for material quantification in
hyperspectral imagery. Ieee Transactions on Geoscience and Remote
Sensing, V39, (N3): 529-545.
Keywords:
Original Abstract: Linear spectral mixture analysis (LSMA) is a widely
used technique in remote sensing to estimate abundance fractions of materials
present in an image pixel. In order for an LSMA-based estimator to produce
accurate amounts of material abundance, it generally requires two constraints
imposed on the linear mixture model used in LSMA, which are the abundance
sum-to-one constraint and the abundance nonnegativity constraint. The first
constraint requires the sum of the abundance fractions of materials present
in an image pixel to be one and the second imposes a constraint that these
abundance fractions be nonnegative. While the first constraint is easy
to deal with, the second constraint is difficult to implement since it
results in a set of inequalities and can only be solved by numerical methods.
Consequently, most LSMA-based methods are unconstrained and produce solutions
that do not necessarily reflect the true abundance fractions of materials.
In this case, they can only be used for the purposes of material detection,
discrimination, and classification, but not for material quantification.
The authors present a fully constrained least squares (FCLS) linear spectral
mixture analysis method for material quantification. Since no closed form
can be derived for this method, an efficient algorithm is developed to
yield optimal solutions. In order to further apply the designed algorithm
to unknown image scenes, an unsupervised least squares error (LSE)-based
method is also proposed to extend the FCLS method in an unsupervised manner.
Heinz, D. C.; I. C. Chein, (2000). Unsupervised fully constrained
squares linear spectral mixture analysis method for multispectral imagery.
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.1681-3 vol.4.
Keywords: Geophysical signal processing; Geophysical techniques;
Image processing; Multidimensional signal processing; Remote sensing; Terrain
mapping; Geophysical measurement technique; Land surface; Optical imaging;
Multispectral remote sensing; Fully constrained squares linear spectral
mixture analysis; Multispectral imagery; Subpixel detection; Endmembers;
Linear mixture analysis ; Multispectral image analysis
Original abstract: Subpixel detection and quantification of materials
in multispectral imagery presents a challenging problem due to a relatively
low number of spectral bands available for analysis in which case the number
of spectral bands may be less than the number of materials to be detected
and quantified. The problem is even more difficult when the image scene
is unknown and no prior knowledge is available. Under this circumstance,
the desired information must be obtained directly from the image data.
The authors present an unsupervised least squares-based linear mixture
analysis method coupled with a band expansion technique for multispectral
image analysis. This method allows the authors to extract necessary endmember
information from an unknown image scene so that the endmembers present
in the image can be detected and quantified. The band expansion technique
creates additional bands from the existing multispectral bands using band-to-band
nonlinear correlation. These expanded bands ease the problem of insufficient
bands in multispectral imagery and can improve and enhance the performance
of the proposed method. The experimental results demonstrate the advantages
of the proposed approach.
Heipke, C.; H. Mayer; C. Wiedemann; O. Jamet, (1997). Evaluation
of automatic road extraction. Joint ISPRS Commission III/IV Workshop.
3D Reconstruction and Modelling of Topographic Objects Stuttgart, Germany
17-19 Sept. 1997
Int. Arch. Photogramm. Remote Sens. (Australia), pp.151-60.
Keywords: Feature extraction; Geography; Image matching; Photogrammetry;
Redundancy; Remote sensing; Automatic road extraction algorithms; Internal
self-diagnosis; External evaluation; Image analysis; Manually plotted linear
road axes; Reference data; Extracted primitives matching; Quality measures;
Completeness; Correctness; Planimetric RMS differences; Gap statistics;
Exhaustivity; Geometrical accuracy; Multiple algorithms ; Experimental
results evaluation
Original abstract: Internal self-diagnosis and external evaluation
of the obtained results are essential for any automatic system. In the
long run, these factors are of major importance for the relevance of the
system for practical applications. Obviously, this statement is also true
for image analysis in photogrammetry and remote sensing. However, so far,
only relatively little work has been carried out in this area. This paper
deals with the external evaluation of automatic road extraction algorithms
by means of comparison to manually plotted linear road axes used as reference
data. The comparison is performed in two steps: (1) matching of the extracted
primitives to the reference network; and (2) calculation of quality measures.
Each part depends on the other: the less tolerant the matching, the less
exhaustive the extraction is considered to be, but the more accurate it
looks. Therefore, the matching process is an important part of the evaluation
process. The quality measures proposed for the automatically extracted
road data comprise completeness, correctness, quality, redundancy, planimetric
RMS differences and gap statistics. They aim at evaluating exhaustivity
as well as assessing geometrical accuracy. The evaluation methodology is
presented and discussed in detail. Results of a comparative evaluation
of three different automatic road extraction approaches are presented.
They show the overall status of the road extractors, as well as the individual
strengths and weaknesses of each individual approach. Thus, the applicability
of the evaluation method is proven.
Heipke, C.; W. Mayr; C. Wiedemann; H. Ebner, (1997). Automatic aerotriangulation
with frame and three-line imagery. 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.286-94.
Keywords: Feature extraction; Image matching; Remote sensing; Automatic
aerotriangulation; Frame imagery; Three-line imagery; Conjugate point extraction;
Geometric differences; Point features; Coarse-to-fine strategy; Image pyramids;
Feature-based matching; Overlapping image pairs; Manifold conjugate point
tuples; Exterior orientation parameters; 3D-coordinates; Distributed conjugate
points ; Stable block geometry
Original abstract: In this paper an approach for automatic aerotriangulation
(AAT) is presented, which is designed for frame and three-line imagery.
We focus on the extraction of conjugate points, because the geometric differences
in geometry of frame and three-line imagery can be considered as well-known
and are only different modules at the implementation stage. Our approach
uses point features and a coarse-to-fine strategy based on image pyramids.
To extract conjugate points we employ feature-based matching of image pairs
on all pyramid levels. After matching all overlapping pairs of images,
manifold conjugate point tuples are generated and checked for geometric
consistency individually as well as in their local neighborhood. Subsequently,
the exterior orientation parameters for the whole block are calculated
on each pyramid level in a robust bundle adjustment together with 3D-coordinates
for the conjugate point tuples in an arbitrary reference system. This information
serves as initial values on the next lower pyramid level. Control information
is not necessary a priori, but can be introduced at any stage of processing.
The approach has been tested with various imagery. A few hundred well distributed
conjugate points were extracted in all cases. In particular, a large number
of many-ray points, which are essential for a stable block geometry was
detected. The standard deviation of all image coordinates lies between
0.3 and 0.4 pixels. These results constitute a proof-of-concept and demonstrate
the feasibility of the presented approach.
Hellmann, M.; S. R. Cloude; K. P. Papathanassiou, (1997). Classification
using polarimetric and interferometric SAR-data. IGARSS'97. 1997 International
Geoscience and Remote Sensing Symposium. Remote Sensing - A Scientific
Vision for Sustainable Development (Cat. No.97CH360420) Singapore 3-8 Aug.
1997
New York, NY, USA IEEE, pp.1411-13 vol.3.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Radar imaging; Radar polarimetry; Remote
sensing by radar; Sensor fusion; Synthetic aperture radar; Geophysical
measurement technique; Land surface; Terrain mapping; Interferometric SAR;
InSAR ; Automatic classification
Original abstract: The investigation presented in this paper demonstrate
a first order approach to an automatic classification and extraction of
cartographic relevant features from SAR data. The authors propose a fusion
of polarimetric and interferometric classification techniques that is able
to solve several classification ambiguities which are not resolvable with
one method alone and is also able to improve significantly the accuracy
of the classification results. The complimentarity of the polarimetric
and interferometric coherence based classification approaches and the improvements
resulting from their combination are demonstrated using data from the space-shuttle-borne
SIR-C/X-SAR radar system.
Hellmann, M.; S. R. Cloude; K. P. Papathanassiou, (1997). Interpretation
of SAR-data using polarimetric and interferometric techniques. Wideband
Interferometric Sensing and Imaging Polarimetry San Diego, CA, USA 28-29
July 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.255-66.
Original abstract: The investigation presented in this paper demonstrates
the potential of the combination of polarimetric and interferometric classification
techniques for the extraction of map relevant features from space borne
SAR data. In the first part we discuss a polarimetric classification technique
based on Cloude's decomposition theorem (Cloude and Pottier 1995, 1997;
Pottier 1994). Afterwards we demonstrate the abilities of interferometric
classification. The complementarity of the polarimetric and interferometric
coherence based classification approaches can be used to resolve ambiguities
that remain if one method is applied alone. The improvements resulting
from their combination are available for an automatic classification and
extraction of cartographic relevant features from space borne SAR data.
Hellmann, M.; E. Kratzschmar, (1998). A new approach for interpretation
of full-polarimetric SAR-data. Proceedings of the PIERS Workshop on
Advances in Radar Methods Baveno, Italy 20-22 July 1998
Brussels, Belgium Commision of Eur. Communities, pp.204-7.
Keywords: Eigenvalues and eigenfunctions; Electromagnetic wave scattering;
Entropy; Feature extraction; Pattern classification; Radar polarimetry;
Remote sensing by radar; Spaceborne radar; Synthetic aperture radar; Full-polarimetric
SAR data; Unsupervised classification; Eigenvalue based analysis; H- alpha
feature extraction; Automatic classification; Scattering mechanisms; L-band
data; C-band data; Spaceborne SAR; SIR-C/X-SAR mission; Germany ; Ground
interaction
Original abstract: In this paper a new approach for unsupervised classification
of full polarimetric SAR-data suitable for automation is outlined. To reach
this aim it is important to develop an algorithm which is independent of
data set and sensor. A well known approach towards this goal is the eigenvalue
based analysis of the entropy H and alpha parameters. This H- alpha feature
extraction is independent of data set and sensor and suitable for unsupervised
and automatic classification due to the fact that it is possible to derive
information about the scattering mechanisms on the ground without a priori
knowledge. In this paper a extension of this algorithm is proposed. While
the H- alpha feature extraction uses an averaged alpha value and also the
entropy in the von-Neumann sense is an averaged value the new approach
uses the 3 eigenvalues and their relations. A physical interpretation of
the relationships between the eigenvalues is proposed. This algorithm can
improve the class accuracy which is not sufficient for maps in the H- alpha
classification case. For the classification L-band and C-band data of the
space-shuttle-borne SIR-C/X-SAR mission from the test site Oberpfaffenhofen,
Germany were used. The combination of both frequencies allows a more detailed
classification of the scene due to different ground interaction of the
different wavelengths. Therefore different scattering mechanisms can be
seen in different bands and from the combination of both bands ambiguities
can be resolved. For validation purposes the classification is compared
with the ATKIS (official German GIS) data.
Hellwich, O.; M. Gunzl, (2000). Landuse classification by fusion
of optical and multitemporal SAR imagery. 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.2435-7 vol.6.
Keywords: Remote sensing by radar; Synthetic aperture radar; Terrain
mapping; Landuse classification; Multitemporal SAR imagery; Surface roughness;
Soil moisture; Object extraction; Passive optical imagery; Speckle effect;
Areal objects; All-weather capability; Time series; Optical image data;
Data fusion; Multispectral data ; Object recognition
Original abstract: Optical imagery such as high resolution panchromatic
or multispectral data, and synthetic aperture radar (SAR) data show different
information about the imaged objects, and have different advantages and
disadvantages when used for object extraction or landuse classification.
Multispectral optical image data is largely determined by the type of the
material an object consists of. Panchromatic data which is often available
with a higher resolution than multispectral data emphasizes geometric detail
of the objects, e.g. the complex structure of anthropogenic objects such
as road networks. In contrary to this, SAR data contain information about
surface roughness and - to a lower degree - soil moisture. These different
types of information are referring to completely different object qualities
and are, therefore, largely uncorrelated which helps to reduce ambiguities
in the results of object extraction. The main advantage of passive optical
imagery with respect to SAR data is the lack of the speckle effect leading
to images with a far better extractability of linear as well as areal objects.
A major advantage of SAR is its all-weather capability which allows the
acquisition of time series of imagery with exact acquisition dates under
any climatic conditions. In this paper, these complementary properties
of SAR and optical image data are demonstrated and used to improve landuse
classification results.
Hellwich, O.; C. Streck, (1996). Linear structures in SAR coherence
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.330-2 vol.1.
Keywords: Coherence; Edge detection; Feature extraction; Geophysical
signal processing; Hydrological techniques; Radar imaging; Radiowave interferometry;
Remote sensing by radar; Rivers; Spaceborne radar; Synthetic aperture radar;
SAR coherence data; Thin linear structures; Roads; Railway lines; Speckle
effects; Coherent imaging; Interferometric processing; Visibility; Spaceborne
scenes; Airborne SAR; Optimal size; Correlation window; Linear structure
extraction; Intensity ; Amplitude
Original abstract: The extraction of thin linear structures like roads,
rivers and railway lines from synthetic aperture radar (SAR) scenes has
been shown to be a difficult task owing to the speckle effects of coherent
imaging (e.g. Hendri et al., 1988), Therefore, for line extraction it is
reasonable to use all information that SAR scenes offer, and not only the
amplitude data. One source of additional information is the coherence data
computed by interferometric processing of two SAR scenes. The visibility
of linear structures in SAR coherence data has been investigated. Scene
pairs from the ERS-1 and the ERS-2 SAR sensors, the X-SAR experiment and
a scene from a two-antenna airborne SAR system were evaluated The time
difference between the acquisitions of the spaceborne scenes forming interferometric
scene pairs was one to 35 days. An optimal size of the correlation window
used to derive coherence maps for linear structure extraction was determined
by visual inspection. The correlation between the intensity and the coherence
data was used to infer how much information the coherence adds to the information
of the amplitude of both scenes.
Hellwich, O.; C. Wiedemann, (1999). Multisensor data fusion for automated
scene interpretation. 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.284-95.
Keywords: Feature extraction; Geography; Image classification; Image
recognition; Image segmentation; Knowledge based systems; Principal component
analysis; Radar imaging; Remote sensing by radar; Sensor fusion; Synthetic
aperture radar; Multisensor data fusion; Automated scene interpretation;
Linear objects; Two-dimensional objects; Feature-level fusion; Object level
fusion; Data sources; DAIS hyperspectral data; AES-1 SAR data; High-resolution
panchromatic digital orthoimages; Rural test areas; Road network; Agricultural
fields; Small villages; Scene interpretation; Conceptual model; Semantic
net; Network nodes; Hyperspectral bands; Extraction results; Areal objects;
Principal component transformation; Image intensity; Interferometric elevation;
Classifications; Rule-based methods ; Segment-based method
Original abstract: An approach to the combined extraction of linear
as well as two-dimensional objects from multisensor data based on a feature-
and object level fusion of the results is proposed. The data sources are
DAIS hyperspectral data, AES-1 SAR data, and high-resolution panchromatic
digital orthoimages. Rural test areas consisting of a road network, agricultural
fields, and small villages were investigated. The scene interpretation
is based on a conceptual model consisting of a semantic net for each of
the sensors and a semantic net of the real world objects. The sensor nets
and the object net are combined into one network by means of a geometry
and material level of network nodes. Road networks are extracted from the
panchromatic orthoimage and from selected hyperspectral bands. Based on
the knowledge that roads compose networks the extraction results are combined.
Two-dimensional, i.e. areal objects are extracted from hyperspectral data
after a principal component transformation. The SAR data are segmented
using image intensity and interferometric elevation. The classifications
of the hyperspectral and SAR data are combined with the extracted road
network using rule- and segment-based methods. In the outlook, comments
are given on the trade-off between the improvement of the results using
the new method and the increasing costs for data acquisition.
Hemmer, T. H., (1996). Towards automation of the extraction of lines
of communication from multispectral images using a spatio-spectral extraction
technique. 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.115-26.
Keywords: Cartography; Feature extraction; Image resolution; Remote
sensing; Spectral analysis; Automated mapping; Lines of communication;
Multispectral images; Spatio-spectral extraction technique; Commercial
sensor resolutions; Identification; Spectral information ; Linear mixture
model
Original abstract: Adequate imagery for automated mapping of large
areas became available with the successful launch of the 30-meter 7-band
thematic mapper (TM) on Landsat 4 in 1982. Yet an adequate approach to
automated line-of-communication (LOC) extraction continues to elude the
remote sensing community. Perhaps the single biggest complicating factor
is the inherently subpixel nature of the problem; almost all LOCs are narrower
than current commercial sensor resolutions. Other complications include:
spatial and temporal variability of LOC surface spectra, proximity to,
and abundance of, spectrally similar materials, and atmospheric effects.
We describe progress towards the detection and identification of LOCs using
a technique that simultaneously extracts both spatial and spectral information.
The approach currently uses a linear mixture model for simultaneously decomposing
the image into fractional compositions and corresponding spectra using
physical constraints. The algorithm differs from other approaches in that
no traditional preprocessing or prior spatial or spectral information is
required to extract the LOCs and their spectra. The algorithm has been
successfully applied to TM and M-7 data. Results are presented.
Henderson, F. M.; X. Zong-Guo (1997). SAR applications in human settlement
detection, population estimation and urban land use pattern analysis: a
status report. IEEE Transactions on Geoscience and Remote Sensing,
35, (1): 79-85.
Keywords: Demography; Geography; Geophysical techniques; Radar applications;
Remote sensing by radar; Synthetic aperture radar; Geophysical measurement
technique; Land use; Terrain mapping; Radar remote sensing; Urban area;
sar; Human settlement detection; Town; City; Population estimation; Pattern
analysis; Urbanized area ; Population migration
Original Abstract: Over 70 percent of the population of the world's
developed countries live in urbanized areas. In developing countries migration
to urban areas is continuing at an increasing rate. Detection and analysis
of settlement patterns, estimating population, and monitoring population
migration in a timely manner are requisite to accurately assess the impact
of human activities on the environment. Monitoring urban land use change
patterns is among the most critical information needs for future economic
development planning, natural resource allocation, and environmental and
ecosystem management. Previous research has demonstrated the potential
of imaging radar systems in analyzing urban, population, and settlement
phenomena. However, the variability and complexity within and between urban
land use morphologies present a convoluted environment for analysis. Studies
of vegetation, soils, geology, hydrology, and ice and snow have all received
more attention and been the subject of considerably more widespread and
in-depth radar research. Nevertheless, imaging radars offer some distinct
advantages and opportunities for urban-based research. With the arrival
of operational space imaging SAR systems, a review of the current status
of applications of radar remote sensing in urban studies should be useful
for focusing the authors' attention on this important area of radar research
and identification of specific problems for in-depth analysis. This paper
traces the history of imaging radar research for urban, settlement, and
population analysis. It presents a status report on the applications of
SAR in settlement detection, population estimation, assessment of the impact
of human activities on the physical environment, mapping and analyzing
urban land use patterns, and interpretation of socioeconomic characteristics.
The demonstrated capabilities and limitations of past and current imaging
radar systems with reference to these applications are described. Potential
avenues of future research are addressed.
Henricsson, O. (1998). The role of color attributes and similarity
grouping in 3D building reconstruction. Computer Vision and Image
Understanding, 72, (2): 163-84.
Keywords: Computer vision; Edge detection; Feature extraction; Image
colour analysis; Image reconstruction; Remote sensing; Stereo image processing;
Color attributes; Similarity grouping; 3D building reconstruction; aruba
; Aerial images
Original Abstract: We present ARUBA, a general framework for automated
3D building reconstruction from multiple color aerial images. After highlighting
the strategy and concisely describing the framework and its 2D and 3D processing
modules, we evaluate the reconstructed roofs with respect to accurate reference
data. The paper shows that geometry, although important, should not be
the only source of information exploited in the reconstruction process.
The main objectives are to demonstrate that: 1) color is a very important
cue in reconstructing a general class of objects; 2) it is crucial to retain
all information during the entire processing chain, 3) a general class
of objects parts can be efficiently extracted by grouping edges and lines
by means of similarity, and 4) a mutual interaction between 2D and 3D processing
is important.
Henry, B., (2000). The potential of LiDAR in urban and regional development.
URISA Proceedings. 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.379-81.
Keywords: cad; Civil engineering computing; Geographic information
systems; Town and country planning; Visual databases; LiDAR dataset; Urban/regional
development; Urban habitats; Natural environment; Urban areas; Data layers;
Development enterprise; Spatial relations; Geographic layers; Buildings;
Highways; Waterways; Trees; Ground contours; Terrain surfaces; CAD systems
; gis
Original abstract: Just like a beaver's dam or an owl's nest our urban
habitats are a complex array of materials crafted to meet our species'
needs, but exposed to the natural environment in which we live; an environment,
seemly sedate and controlled, that proves highly sensitive to changes we
make maintaining and expanding our habitat. With the advent of geographic
information systems, we have been able to study the relationships between
our habitats and their environment, we have created systems for planning
new growth, managing our current situation and designing solutions for
the unexpected forces of nature. However, even the smallest of urban areas
is a big place. In order to make accurate decisions, data layers for all
areas that affect an environment should be included and at as high an accuracy
level as possible. LiDAR presents a method of capturing a large urban or
regional area in a manner suitable to all aspects within a planning and
development enterprise. A LiDAR dataset is not just a picture of a city
or region, but its essence. All the spatial relations existing within the
area are available in 3 dimensions. Using various tools, the raw data can
be transformed into geographic layers such as buildings, highways, waterways,
trees, ground contours, and terrain surfaces. These layers can be added
to GIS or CAD systems, aiding planners and developers in their decisions.
The paper presents an overview of the tools and methods available for creating
data layers from LiDAR and provides insight into using these layers throughout
the planning and development enterprise.
Hepner, G. F.; B. Houshmand; I. Kulikov; N. Bryant (1998). Investigation
of the integration of AVIRIS and IFSAR for urban analysis. Photogrammetric
Engineering and Remote Sensing, V64, (N8): 813-820.
Keywords: AVIRIS , IFSAR integration
Hernandez, R. R. (1995). Enterprisewide GIS reduces traffic congestion.
GIS World, 8, (4): 48-51.
Keywords: Geographic information systems; Town and country planning;
Traffic; Transportation; Enterprise-wide geographic information system;
Traffic congestion; Los Angeles Metropolitan Transportation Authority;
Traffic planners; GIS-based transportation development project; Graphical
environment; Analytical environment; Real-time traffic monitoring; GIS
database; Metropolitan planning agency; New roads; Light-rail links; Transit
systems; Real-time information; Bus schedules; Hot-line number; arc/info;
Environmental Systems Research Institute; IBM RS/6000 workstations ; Token
ring network
Original Abstract: With the help of GIS technology and some creative
forward-thinking by the Los Angeles Metropolitan Transportation Authority
(MTA), Los Angeles' traffic planners are in the midst of one of the largest
GIS-based transportation development projects ever-designing, developing
and implementing an enterprisewide GIS. The GIS will provide a graphic
and analytical environment for real-time traffic monitoring and planning
of the entire Los Angeles County region. The GIS database under development
will be one of the largest in use by a metropolitan planning agency, covering
some 4,000 square miles. The system will link users in several MTA departments
and other agencies to accommodate a range of applications, from providing
analysis tools for planning new roads and light-rail links to tools for
operating transit systems and providing real-time information on bus schedules
using a hot-line number. The project uses ARC/INFO GIS software from the
Environmental Systems Research Institute, running on IBM RS/6000 workstations
on a token ring network at MTA's downtown Los Angeles headquarters. In
the first year of implementation, services have been extended to numerous
groups within MTA, including transportation modeling, planning, scheduling
and operations, and benefits/assessment. Similar hardware and GIS software
eventually will link into an enterprisewide system among MTA offices and
other agencies.
Herr, A. V., Jr.; J. A. Szemraj; L. Parks, (1995). A joint effort
to develop a national transportation data base. 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.428-35 vol.1.
Keywords: Geographic information systems; Merging; Research initiatives;
Transaction processing; Transportation; Visual databases; National transportation
database development; usa; US Geological Survey; Bureau of the Census;
Data merging; Transportation feature data; Data accuracy; Data quality;
Common core data set; Road features; Digital line graph data; Topographic
quadrangles; Topologically Integrated Geographic Encoding and Referencing;
TIGER system data; High-resolution commercial data; Feature identification
code scheme; Geodata sources; Transaction file; Automated geospatial database
updating; Federal Geographic Data Committee National Spatial Data Infrastructure
Framework; Data initiative; Data revision ; Data exchange
Original abstract: The US Geological Survey (USGS) and the Bureau of
the Census (BOC) have entered into a pilot program that studies the merging
of transportation feature data of differing accuracies and qualities in
order to create a common core data set. The data used are the road features
from USGS digital line graph (DLG) data collected from the 1:100,000-scale
topographic quadrangles, the BOC Topologically Integrated Geographic Encoding
and Referencing (TIGER) system data, and higher resolution commercial data.
The purpose is to integrate the best qualities of each data set to create
an improved common core feature data set, to develop a feature identification
code scheme that will allow users to quickly and easily equate features
to their own geodata sources, and to develop a scheme for a transaction
file that will allow for the automated updating of geospatial databases.
These objectives support the Federal Geographic Data Committee National
Spatial Data Infrastructure Framework data initiative. This paper describes
the approach used for ingesting, conflating, revising and exchanging the
data, and discusses the results of this first pilot project for the development
effort.
Hideo, T., (1999). Urban gas monitoring system using optical sensors.
13th International Conference on Optical Fibre Sensors Kyongju, South Korea
12-16 April 1999
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.332-6.
Keywords: Air pollution measurement; Gas sensors; Leak detection;
Monitoring; Optical modulation; Optical sensors; Organic compounds; Remote
sensing by laser beam; Spectrochemical analysis; Urban gas monitoring system;
Methane monitoring system; Distributed-feedback semiconductor laser; Detection
limit; Concentration pathlength product; High sensitivity; Second-harmonic
detection; Wavelength modulation frequency; Methane absorption line; Positioning
system; Mobile GIS; Gas leakage points; Buried pipelines; Digital map;
Real time; Vehicle mounted system; Sensitivity; Linearity ; 1.66 micron
Original abstract: We have developed a methane monitoring system using
a 1.66 mu m distributed-feedback semiconductor laser. The detection limit
of the system is 70 ppb m in concentration pathlength product with the
time constant of 1 s. This high sensitivity is achieved by the second-harmonic
detection of wavelength modulation frequency of the laser whose center
wavelength is stabilized on an the absorption line of methane. The system
was installed on a vehicle in combination with a positioning system and
a mobile GIS that enabled to record and indicate gas leakage points from
buried pipelines on the digital map in real time.
Hill, J. M. (2000). Wide-Area Topographic Mapping and Applications
Using Airborne LIght Detection and
Ranging (LIDAR) Technology. Photogrammetric Engineering and
Remote Sensing, V66, (N8).
Keywords: LIDAR system
Synopsis: This is a "highlight" article describing recent LIDAR applications.
There are sections on transportation and urban landscape applications.
This is a good 'intro to LIDAR' article.
Hillman, R., (1997). GIS-based innovations for modelling public transport
accessibility. Geographic Information - Exploiting the Benefits. Proceedings
of the AGI'97 Conference Proceedings of Conference on Products and Services
Relating to Geographical Information Systems Birmingham, UK 7-9 Oct. 1997
London, UK Assoc. Geogr. Inf, pp.1-6.
Keywords: Geographic information systems; Government policies; Planning;
Public administration; Transportation; Visual databases; GIS-based innovations;
Local government; Government transport policy; Accessibility modelling;
Spatial databases; Geodemographic data; Land use data; Travel times; Development
control ; Public transport network planning
Original abstract: Central and local government transport policy is
increasingly focused on promoting sustainable transport schemes, and in
particular shifting dependence from the private car towards the increased
use of public transport. The effective implementation of this process is
facilitated by information about the transport networks that are managed,
and the effects of changes to those networks. Increasingly the measurement
of public transport accessibility is viewed as a useful tool in this planning
process. This provides data on the ease, or otherwise, of travel between
two points; and may take into consideration factors such as walking to
a network access point, travel through the network, interchanges, and access
to the intended destination. GIS provides an excellent environment for
the modelling of accessibility. Transport data is inherently spatial in
nature and the GIS provides access to additional data such as geodemographic
and land use data sets. This enables the planner to look not only at the
basic travel times between points but to assess the utility of specific
destinations to specific user groups. This paper briefly studies the reasons
for measuring public transport accessibility and considers various methods
of calculating accessibility indices. Examples are drawn from a variety
of applications including development control and public transport network
planning. Data issues in developing and maintaining public transport databases
are investigated.
Hippie, J. D.; D. J. Daugherty, (2000). Urban validation site for
testing impervious surface models derived from remotely sensed imagery.
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.2074-6 vol.5.
Keywords: Geophysical signal processing; Geophysical techniques;
Hydrological techniques; Remote sensing; Sensor fusion; Terrain mapping;
Hydrology; Runoff; Land surface; Measurement technique; Urban site; Town;
City; Validation site; Impervious surface model; Impervious surface; Hydraulic
model; Landscape; Multiple sensor; Multifarious classification; Springfield;
Missouri; United States; usa; Land cover; Industrial land use; Park ; Open
space
Original abstract: Accurate quantification of impervious surfaces is
a necessary input in a variety of urban applications including hydrologic
and hydraulic models and landscape change. The purpose is to assess the
performance and effectiveness of multiple sensor platforms for the delineation
of impervious surface in an urban setting using multifarious classification
strategies. Data acquired from airborne and satellite based sensors are
used, along with a variety of classification and data fusion strategies,
to gather a cost versus reliability measurement for each of the systems.
A framework is presented to aid users in selecting the appropriate dataset
and methodology for their specific situational needs. The impervious surface
generation models are applied to remotely sensed data collected over the
Springfield Urban Validation Site (UVS), an approximately 1-km N-S by 4-km
E-W urban corridor within the City of Springfield, Missouri. The site is
highly documented with respect to position and composition of structures
and land covers and consists of varying aged residential developments,
commercial, institutional, parks and open space, and light industrial land
uses. The models and comparisons developed here can be reliably used to
estimate the costs and spatial variability of different methods of impervious
surface generation from various imagery inputs, aiding urban planners and
managers in the assessment of the errors and biases of various impervious
surface generation strategies.
Hipple, J. D.; D. J. Daugherty; J. M. Dunajcik, (2000). Long-term
growth visualization and change detection for urban planning applications:
a Springfield MO urbanized watershed. 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.2875-7 vol.7.
Keywords: Geophysical techniques; Remote sensing; Terrain mapping;
Geophysical measurement technique; Land use; Land surface; United States;
usa; Urban area; Expansion; Growth; Town; City; Visualization; Change detection;
Urban planning; Springfield; Urbanized watershed; Missouri; Landsat; Optical
imaging ; Multispectral remote sensing
Original abstract: A long-term growth analysis was conducted for the
City of Springfield, Missouri. The Springfield Department of Planning and
Development was interested in determining the characteristics and patterns
of urban growth within the metropolitan area over the past three decades.
The interest in assessing urban growth and development trends within the
region stems from present day environmental problems in areas recently
annexed or areas that have undergone intensive development. A myriad of
problems exist if the city continues to grow as expected (a fifty percent
increase in area over the next 20 years). A historic look at urban growth
through remote sensing allows planners and the public to visualize the
expansion occurring in and around the city. The assessment of growth impacts
uses a multi-tiered strategy where the NALC Landsat MSS triplicate sets
provides long-term data for analysis and Landsat TM and ETM+ data provides
the higher resolution data for a refined analysis. The methodology consisted
of the identification of highly changed areas through numerous change detection
techniques using the NALC data-sets. Once identified, the higher resolution
data-sets were used to characterize the types of change that occurred.
The authors present results dealing with one highly impacted area, that
of a rapidly urbanized watershed. An assessment, such as the one presented,
will aid determining environmental *priority areas' due to urban growth
and assist in developing growth policies.
Hivernat, C.; X. Descombes; S. Randriamasy; J. Zerubia (2000). Matching
of two line networks: application to the analysis and registration of road
networks extracted from a couple map/SPOT image. Traitement du Signal,
17, (1): 21-32.
Keywords: Cartography; Edge detection; Feature extraction; Graphs;
Image matching; Image registration; Image segmentation; Markov processes;
Matrix algebra; Remote sensing; Line network matching; Image analysis;
Road networks; SPOT image; Line graph matching; Segments; Markov model;
Labelling problem; Rotation invariance; Translation invariance; Cartographic
database; Road pixel chaining; Qualification step ; Registration matrix
Original Abstract: We consider the problem of line graph matching.
The nodes correspond to segments characterized by their length and their
angle. A Markov model allows us to embed the problem into a labelling problem.
The derived model is invariant with respect to rotations and translations.
The algorithm is applied to road networks extracted from a SPOT image and
a cartographic database. The matching is performed after having chained
the road pixels extracted from the image. After the matching, a qualification
step provides a registration matrix and allows us to interpret the results
in order to update the cartographic database.
Hoffman, R. N.; D. W. Johnson (1994). Application of Eofs to Multispectral
Imagery - Data Compression and Noise Detection for Aviris. Ieee
Transactions on Geoscience and Remote Sensing, V32, (N1): 25-34.
Keywords: AVIRIS , data compression, noise detection
Original Abstract: Investigates the first stage of a two stage approach
to data compression for multispectral imagery. The first stage is to compress
the data spectrally using empirical orthogonal functions (EOFs). In the
second stage, each EOF image is further compressed using standard techniques,
such as transform encoding. The characteristics of EOFs make them ideal
for spectral compression. The EOFs form the orthogonal basis in the data
space which provides the most economical data representation. Furthermore,
and perhaps of more interest, EOFs are effective noise filters. In the
authors experiments with the 224 channel AVIRIS data, lossy compression
ratios of order 50:1 are attained by the EOF representation under the condition
that the residual rms error be smaller than the independently measured
instrument noise.
Hoffmann, A.; G. M. Smith; F. Lehmann, (2000). The classification
of fine spatial resolution imagery: parcel-based approaches using HRSC-A
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.3009-11 vol.7.
Keywords: Geophysical signal processing; Geophysical techniques;
Image classification; Remote sensing; Terrain mapping; Geophysical measurement
technique; Land surface; Image processing; Fine spatial resolution imagery;
Parcel-based approach; hrsc-a; High Resolution Sterwo Camera Airborne;
Optical imaging ; Land cover type
Original abstract: Large amounts of remotely sensed data are now being
collected from airborne platforms carrying digital scanners and digital
cameras with spatial resolutions from 2 m down to 15 cm. Spaceborne instruments
are now being launched with spatial resolutions between 1 and 4 m. These
systems are used to address mapping issues in locating and identifying
objects or areas on the surface. The fine spatial resolution of the data
now becoming available would at first appear to be a major advantage for
mapping applications compared to conventional satellite systems. However,
it must be remembered that similar reasoning proceeded the launch of Landsat
4 and the Systeme Probatoire de l'Observation de la Terre (SPOT-I) in the
1980s. Work comparing TIM and HRV with the established 80 m spatial resolution
Landsat Multispectral Scanner System (MSS) found that finer spatial resolutions
actually reduced classification accuracy for certain land cover types.
The coarse spatial resolution of the MSS smoothed out spatial complexity
within heterogeneous land cover types, such as urban, as scene components,
such as buildings and vegetation, become lost within a pixel. At finer
spatial resolutions a scale boundary is crossed where the data recorded
for each pixel is related not to the character of object or area as a whole,
but to components of it and this requires a re-definition of the information
that can be extracted. The current move toward even finer spatial resolution
data sets should raise the same question how these types of data should
be analysed using (semi-)automated techniques. This paper describes a methodology
for classifying fine spatial resolution data to land cover types. The problem
faced was two fold; firstly, how to extract meaningful information from
the pixels within the fine spatial resolution images and secondly, how
to integrate this detailed information at the pixel level to useable classes
and appropriate scales.
Hoffmann, A.; J. W. Van Der Vegt; F. Lehmann, (2000). Towards automated
map updating: detecting houses with new digital data-acquisition and processing
techniques. 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.5, pp.2108-10.
Keywords: Automated map updating
Original abstract: Up to now large scale mapping (scales >1:10000)
is done nearly exclusively with aerial photographs. New digital camera
systems will replace these analogue systems in the near future. This paper
describes an approach for automated detection of houses, using a data set
of the High Resolution Stereo Camera-Airborne (HRSC-A). The system provides
multispectral information with a resolution of 15 cm (3000 m flight altitude)
and Digital Surface Models with a resolution of 50 cm, depicting elevation
in steps of 10 cm. The elevation and spectral information supplied by the
sensor was used for this study. New object-oriented approaches allow the
interpretation of these high resolution data sets. The combination of a
new approach (multiresolution segmentation, hierarchical networks) and
the multispectral high resolution data of HRSC-A with its accurate Digital
Surface Model shows very promising results.
Horowitz, A. J. (1997). Integrating GIS concepts into transportation
network data structures. Transportation Planning and Technology,
V21, (N1-2): 139-153.
Keywords:
Hoyano, A.; K. Asano; A. Iino (1997). Urban environment and thermal
infrared imaging technology. Journal of the Japan Society of Infrared
Science and Technology, 7, (2): 2-12.
Keywords: Geophysical techniques; Infrared imaging; Remote sensing;
Temperature distribution; Thermal infrared imaging technology; Urban environment;
Radiation temperature distribution; Environmental information; Heat island
; Land cover classification
Original Abstract: This article describes the application of thermal
infrared imaging technology to the urban environment. The method of applying
the thermal infrared imaging technique is classified into two parts. One
uses thermal infrared images directly for analyzing radiation temperature
distribution in urban areas and the other creates environmental information
which is effective for assessment of urban environment. Some examples of
practical methods including the author's investigations are presented.
Hoyano, A.; A. Iino, (1997). Application of high resolution side-looking
MSS data to heat island potential in urban area. 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.1239-42 vol.3.
Keywords: Air pollution measurement; Atmospheric boundary layer;
Atmospheric techniques; Atmospheric temperature; Geophysical techniques;
Infrared imaging; Atmosphere; Boundary layer; Temperature; Air pollution;
Town city; Remote sensing; Geophysical measurement technique; High resolution
side-looking MSS; Multispectral remote sensing; IR imaging; Optical imaging;
Heat island potential; Urban area; Side-looking airborne MSS; Surface temperature
distribution; Land surface; Complex ground surface form; Residential region;
Urban land use change ; Terrain mapping
Original abstract: The authors employed side-looking airborne MSS data
with high resolution to investigate the actual conditions of surface temperature
distributions in an urban area with the complex ground surface form. In
addition, airborne MSS and GIS data were used to calculate the HIP of various
types of residential regions, and results verified its effectiveness for
monitoring urban land use change and thermal environment.
Huber, R., (1998). Airborne InSAR image interpretation towards cartographic
mapping. 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.1911-13 vol.4.
Keywords: Airborne radar; Bayes methods; Cartography; Feature extraction;
Geophysical signal processing; Geophysical techniques; Geophysics computing;
Image classification; Image texture; Multilayer perceptrons; Radar imaging;
Remote sensing by radar; Synthetic aperture radar; Topography (Earth);
Geophysical measurement technique; Land surface topography; Terrain mapping;
Radar remote sensing; Interferometric SAR; Airborne InSAR image interpretation;
Cartographic mapping; High-resolution; AeS-1 X-Band InSAR; X-band; shf;
Microwave radar; Automatic map production; Interpretation task; Coherence
image; Elevation; Backscatter image; Image feature; Foreshortening; Shadow
ambiguity; Multilayer perceptron classifier; Contextual classification;
Bayesian method; Bayes method ; Neural net
Original abstract: The capabilities of the airborne high-resolution
AeS-1 X-Band InSAR data for automatic cartographic map production are investigated.
The cartographic interpretation task becomes feasible by using coherence
images and elevation information provided by InSAR processing additionally
to the SAR backscatter image. Moreover, as in visual interpretation, features
in SAR images are classified upon their textural appearance and background
knowledge. Special attention is paid to SAR foreshortening and shadow ambiguities
and their impact onto classification. Those ambiguity areas are derived
from the DEM and taken into account in training example selection and a
semantic classification step supporting a textural multilayer perceptron
classifier. A contextual classification operating on MLP results incorporates
class context and a-priori knowledge on class composition by Bayesian information
fusion.
Huet, B.; E. N. Hancock, (1996). Cartographic indexing into a database
of remotely sensed images. Proceeding. Third IEEE Workshop on Applications
of Computer Vision. WACV'96 (Cat. No.96TB100084) Sarasota, FL, USA 2-4
Dec. 1996
Los Alamitos, CA, USA IEEE Comput. Soc. Press, pp.8-14.
Keywords: Cartography; Indexing; Remote sensing; Statistical analysis;
Visual databases; Cartographic indexing; Remotely sensed images; Simple
statistical methods; Application vehicle; Aerial image database; Cartographic
model; Semi urban areas; Road network; Imaging distortions; Simple Euclidean
transform; Pairwise histograms; Angle differences; Cross ratios; Line segment
extraction; Raw aerial images; Sensitivity analysis; Discriminating index;
Image distortion; Variable quality ; Input line segmentation
Original abstract: The paper aims to develop simple statistical methods
for indexing line patterns. The application vehicle used in this study
involves indexing into an aerial image database using a cartographic model.
The images contained in the database are of urban and semi urban areas.
The cartographic model represents a road network known to appear in a subset
of the images contained within the database. There are known to be severe
imaging distortions present and the data cannot be recovered by applying
a simple Euclidean transform to the model. We effect the cartographic indexing
into the database using pairwise histograms of the angle differences and
the cross ratios of the lengths of line segments extracted from the raw
aerial images. We investigate several alternative ways of performing histogram
comparison. Our conclusion is that the Matusita and Bhattachargya distances
provide significant performance advantages over the L/sub 2/ norm employed
by M. Swain and D. Ballard (1990). Moreover, a sensitivity analysis reveals
that the angle difference histogram provides the most discriminating index
of line structure; it is robust both to image distortion on to the variable
quality of input line segmentation.
Hugenschmidt, J. (2000). Railway track inspection using GPR.
Journal of Applied Geophysics, V43, (N2-4): 147-155.
Keywords:
Original Abstract: Swiss Federal Railways SBB inspect their railway
tracks at regular intervals. The first step of track renewal planning is
a geotechnical study. Inspection is focused on the thickness of the ballast,
on subsoil material penetrating upwards into the ballast and on geotechnical
properties of subgrade and subsoil materials. Up to now, the inspection
has been done mainly by digging trenches at evenly spaced intervals and
in locations of special interest. In order to evaluate the benefits and
limits of GPR railway track inspections, three GPR surveys were carried
out on three different railway lines. Data were acquired using a mobile
system travelling at 10 kmrh. Subsequent to radar data acquisition, trenches
were dug. The positioning of some of the trench locations was based on
preliminary GPR results in order to support the interpretation of GPR data.
Only those trenches were available during interpretation of radar data.
In addition, SBB performed their usual investigation programme. This provided
an opportunity for checking the radar results in great detail.
Hugenschmidt, J. (1998). Ground Penetrating Radar for road engineering.
Materials and Structures, V31, (N207): 192-194.
Keywords:
Hugenschmidt, J.; M. N. Partl; H. deWitte (1998). GPR inspection
of a mountain motorway in Switzerland. Journal of Applied Geophysics,
V40, (N1-3): 95-104.
Keywords:
Original Abstract: A radar survey was carried out to support the planning
of maintenance work on Switzerland's Gotthard Motorway. This work became
necessary after damaged pavement layers had been detected by visual inspection
and coring. Radar data acquisition, processing and interpretation focused
on the investigation of pavement damage. However, additional information
such as layer thicknesses and the position of the rock surface could be
extracted from the acquired dataset. Results of the radar survey were verified
by local coring and during repair work. The radar survey proved to be a
useful complement to traditional pavement monitoring methods providing
not only quasi-continuous information between boreholes but also locating
previously unknown problem zones. The comparison between datasets that
were acquired before and after the maintenance work suggests the success
of the repair work and the suitability of GPR as a quality control tool.
Hurd, J. D.; D. L. Civco, (1996). Multisource remote sensing data
image analysis for Connecticut statewide land cover mapping. GIS/LIS'96
Annual Conference and Exposition Proceedings Proceedings of Geographic
Information Systems/Land Information Systems Denver, CO, USA 19-21 Nov.
1996 Bethesda, MD, USA American Society for Photogrammetry & Remote
Sensing, pp.564-72.
Keywords: Image processing; Terrain mapping; Remote sensing data
image analysis; Connecticut; Statewide land cover mapping; Land cover map;
Urban areas ; Pollution modeling
Original abstract: In 1990, under a grant from the joint Long Island
Sound Study (LISS) of the Connecticut Department of Environmental Protection
and the United States Environmental Protection Agency, land cover maps
of the state of Connecticut were prepared through computer-assisted analysis
of satellite digital remote sensing data. Land cover information was extracted
from multi-seasonal Landsat Thematic Mapper and Multispectral Scanner (MSS)
imagery for 23 land cover types. The accuracy of these data has proven
to be adequate for the initial purposes for which they were intended, i.e.,
area-wide nonpoint pollution modeling using land use-dependent coefficients.
However, categories of urban and suburban land cover, particularly low
density development, were found to be some of the least accurate yet most
essential categories for the development of nonpoint load estimates. Urban
regions have been found to be a major source of nutrients to rivers, lakes,
and estuaries. It has therefore proven necessary to develop a procedure
to create a new land cover map which better identifies different densities
of urban areas and provides an up-to-date map for the state of Connecticut.
Hussin, Y. A., (1995). Effect of polarization and incidence angle
on radar return from urban features using L-band aircraft radar data.
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.178-80 vol.1.
Keywords: Airborne radar; Backscatter; Geophysical techniques; Radar
applications; Radar cross-sections; Radar polarimetry; Remote sensing by
radar; Geophysical measurement technique; Remote sensing; Terrain mapping;
Land surface; Town city; Polarization; Incidence angle; Radar return; UHF
L-band; Radar scattering backscatter; Urban features; Aircraft radar; Radar
energy reflectance; Buildings; Fence; Tower; Multiple incidence angle;
Decimetric; sir-b; Look direction; Objects orientation ; 24.5 cm
Original abstract: The objective of this research was to study the
effect of different polarization (HH, VV, VH, and HV) on the radar energy
reflectance or backscatter from variety of corner reflectors (e.g. buildings,
fences, towers, etc.). Multipolarized and multiple incidence angle L-band
(24.5 cm.) JPL (Jet Propulsion Laboratory) aircraft L-band data and SIR-B
HH-polarized multiple incidence angle data were used in this study. The
results showed that the radar energy reflectance was strongly influenced
by radar look direction in relation to objects orientation, type of polarization
within the normal range of incidence angle. The corner reflectors were
clearly seen and significantly reflect the radar energy on the like-polarized
data, but not on the cross-polarized data and low incidence angle. Within
the like-polarized data, HH-polarized data showed different pattern of
reflectance comparing to the VV-polarized data. This paper discusses the
reflectance in different polarizations and the apparent reasons for such
radar energy.
Hussin, Y. A.; K. D. P. Shantha, (1995). Updating terrain information
in topographic databases using radar aircraft images part. III. A change
detection approach. 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.320-2 vol.1.
Keywords: Airborne radar; Cartography; Feature extraction; Geographic
information systems; Geophysical signal processing; Geophysical techniques;
Radar applications; Radar imaging; Radar polarimetry; Remote sensing; Remote
sensing by radar; Topography (Earth); Geophysical measurement technique;
Map revision update updating; Land surface; Terrain information; Topographic
database; Radar aircraft image; Change detection; Image analysis; Topographic
feature; Linear feature; Road; L-band; Automatic feature detection ; Image
processing
Original abstract: The main objective of this research was to investigate
the use of radar images for updating terrain information in topographic
databases. The strategy was to utilize change detection image analysis
techniques in addition to conventional methods to detect topographic features
in radar images, with special emphasis on linear features (e.g. roads).
The results show that main and secondary roads can be visually detected
using 7*11 meter (in the range and azimuth) spatial resolution HH-polarized
L-band aircraft radar data. Automatic feature detection (conventional and
model-based) procedures can be employed for the detection of main roads.
However, spatial resolution is important since it was not possible to identify
tracks and unpaved roads with low resolution. Hence, for the road feature
extraction, a very high resolution image must be used. The experimental
results shows positive indications for updating main and secondary roads
in road network at 1:25,000 scale.
Huston, D.; J. Q. Hu; K. Maser; W. Weedon; C. Adam (2000). GIMA ground
penetrating radar system for monitoring concrete bridge decks. Journal
of Applied Geophysics, V43, (N2-4): 139-146.
Keywords:
Original Abstract: Ground Penetrating Radar GPR has been investigated
as a non-destructive method for evaluating damage in concrete structures.
However, the commercially available techniques are limited to detection
of gross quantities of deterioration, due to the limited resolution of
the system. The objective of this research is to evaluate a ground penetrating
radar system with a novel Good Impedance Match Antenna GIMA for concrete
structural assessment. This system has the capacity to detect concrete
cracks as small as 1 mm thick, while being able to reflect from and detect
features at depths of up to 360 mm. Laboratory results of testing of the
GIMA antenna by using a step-frequency and a high-frequency impulse system
are presented. The experimental results reveal that the GIMA antenna is
capable for use in frequency ranges, at least as broad as 500 Mhz to 6
GHz for the step-frequency and 1 to 16 GHz for the high-frequency impulse
system.
Ifarraguerri, A.; C. I. Chang (2000). Unsupervised hyperspectral
image analysis with projection pursuit. Ieee Transactions on Geoscience
and Remote Sensing, V38, (N6): 2529-2538.
Keywords: hyperspectral image analysis , projection pursuit, HYDICE,
principal component analysis, data compression
Original Abstract: Principal components analysis (PCA) is effective
at compressing information in multivariate data sets by computing orthogonal
projections that maximize the amount of data variance. Unfortunately, information
content in hyperspectral images does not always coincide with such projections.
The authors propose an application of projection pursuit (PP), which seeks
to find a set of projections that are "interesting," in the sense that
they deviate from the Gaussian distribution assumption. Once these projections
are obtained, they can be used for image compression, segmentation, or
enhancement for visual analysis. To find these projections, a two-step
iterative process is followed where they first search for a projection
that maximizes a projection index based on the information divergence of
the projection's estimated probability distribution from the Gaussian distribution
and then reduce the rank by projecting the data onto the subspace orthogonal
to the previous projections. To calculate each projection, they use a simplified
approach to maximizing the projection index, which does not require an
optimization algorithm. It searches for a solution by obtaining a set of
candidate projections from the data and choosing the one with the highest
projection index. The effectiveness of this method is demonstrated through
simulated examples as well as data from the hyperspectral digital imagery
collection experiment (HYDICE) and the spatially enhanced broadband array
spectrograph system (SEBASS).
Ifarraguerri, A.; C. I. Chang (1999). Multispectral and hyperspectral
image analysis with convex cones. Ieee Transactions on Geoscience
and Remote Sensing, V37, (N2 PT1): 756-770.
Keywords: hyperspectral image analysis , linear spectral unmixing,
convex cone analysis, HYDICE (hyperspectral digital imagery collection
experiment)
Original Abstract: A new approach to multispectral and hyperspectral
image analysis is presented. This method, called convex cone analysis (CCA),
is based on the bet that some physical quantities such as radiance are
nonnegative. The vectors formed by discrete radiance spectra are linear
combinations of nonnegative components, and they lie inside a nonnegative,
convex region. The object of CCA is to find the boundary points of this
region, which can be used as endmember spectra for unmixing or as target
vectors for classification. To implement this concept, the authors find
the eigenvectors of the sample spectral correlation matrix of the image.
Given the number of endmembers or classes, they select as many eigenvectors
corresponding to the largest eigenvalues. These eigenvectors are used as
a basis to form linear combinations that have only nonnegative elements,
and thus they lie inside a convex cone. The vertices of the convex cone
will be those points whose spectral vector contains as many zero elements
as the number of eigenvectors minus one. Accordingly, a mixed pixel can
be decomposed by identifying the vertices that were used to form its spectrum.
An algorithm for finding the convex cone boundaries is presented, and applications
to unsupervised unmixing and classification are demonstrated with simulated
data as well as experimental data from the hyperspectral digital imagery
collection experiment (HYDICE).
Iisaka, J.; T. Sakurai-Amano, (1995). Automated terrain feature detection
from remotely sensed images integrating spectral, spatial and geometrical
attributes of objects. 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.486-95 vol.1.
Keywords: Feature extraction; Genetic algorithms; Geographic information
systems; Object recognition; Remote sensing; Town and country planning;
Visual databases; Terrain feature detection; Remotely sensed images; Geometrical
attributes; Spatial attributes; Spectral attributes; Spatial image computing;
Soft computing; Database; Image cue detection; Image cue analysis; Pattern
recognition; Terrain feature component analysis; Road feature detection;
Urban area delineation; Forest clear-cut area detection ; Ocean cold ring
detection
Original abstract: This paper describes an approach to extract terrain
features from remotely sensed images by using spatial image computing functions,
soft computing functions and a database. The processes to detect terrain
features are divided into the detection of image cues which are primal
image entities in an image with/without physical meaning, image cue analysis,
image object/pattern recognition, terrain feature component analysis and
terrain feature identification. Then a unified method for spectral and
spatial image processing is described. This method facilitates the implementation
of the terrain understanding processes and gives a new perspective in image
computing. Some results of using the method of automated terrain feature
detection are also demonstrated such as road feature detection from TM
data, urban area delineation from SAR image, forest clear-cut area detection
from TM data, and ocean cold ring detection which are extracted by using
genetic algorithms.
Ikuta, K.; N. Yoshikane; N. Vasa; Y. Oki; M. Maeda; M. Uchiumi; Y. Tsumura;
J. Nakagawa; N. Kawada (1999). Differential absorption lidar at 1.67
mu m for remote sensing of methane leakage. Japanese Journal of
Applied Physics Part 1-Regular Papers Short Notes & Review Papers,
V38, (N1A): 110-114.
Keywords:
Ioannilli, M.; U. Schiavoni, (1996). GIS in transport planning: a
districting procedure. 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.695-8 vol.1.
Keywords: Geographic information systems; Interactive systems; Town
and country planning; Transportation; GIS applications; Transport planning;
Districting procedure; Urban areas; Interactive procedure ; Transport model
implementation
Original abstract: A number of GIS applications have been developed
to support transport planning in urban areas. The flow of an interactive
procedure for districting-that is the first step for transport model implementation-is
reported.
Ito, Y.; S. Omatu, (1997). Polarimetric SAR data classification using
scattering models and neural networks. 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.132-40.
Keywords: Backpropagation; Electromagnetic wave scattering; Image
classification; Neural nets; Radar polarimetry; Remote sensing by radar;
Spaceborne radar; Synthetic aperture radar; Polarimetric SAR data classification;
Scattering models; Integrated neural network classifier; Mueller matrix;
Stokes vector; Back-propagation; Competitive neural network; lvq1; lvq2.1;
SIR-C C-band data; Water category; Factory categories; Urban categories;
Learning process; Eight-dimension feature vector; Pseudo relative; Backscattering
coefficients; hh ; vv
Original abstract: We consider a polarimetric SAR data classification
method which includes scattering models. The proposed method is an integrated
neural network classifier composed of two classification procedures. First,
SAR data is pre-classified into three scattering classes by individually
computing the Mueller matrix and Stokes vector. Second, we construct a
neural network appropriate to each scattering class in order to classify
the SAR data into realistic categories. Either the competitive or back-propagation
neural network is employed as a classifier. The former learns by the LVQ1
and LVQ2.1 algorithms. As a result of the procedure using SIR-C C-band
data, pixels in the water category will be classified almost exclusively
into the odd class. The even class includes only factory and urban categories.
Therefore, it can be concluded that the neural classifier contains a smaller
network and a more efficient learning process since it is applied to more
limited category classifications. The neural network classifier employs
an eight-dimension feature vector with backscattering coefficients and
pseudo relative phases between HH and VV from the L and C bands. Average
accuracy of the competitive neural network is slightly higher than that
of the back-propagation network.
Jackson-Pringle, J.; F. K. Wilson, (2000). Use of remote sensing
to study the impact of land-cover/land-use change on the environment: a
Baltimore area, Maryland case study. 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.2871-3 vol.7.
Keywords: Geophysical techniques; Remote sensing; Terrain mapping;
Geophysical measurement technique; Land use; Urban area; Expansion; Optical
imaging; Multispectral remote sensing; Town city; United States; usa; Land-cover;
Land-use change; Baltimore; Maryland; Land-cover change; Landsat Thematic
Mapper; TM image ; AD 1990 to 1999
Original abstract: Remote sensing was utilized, to analyze and study
land-use/land-cover change impact on the environment of a section of Baltimore
County and City. This study area was selected because it is one of the
fastest growing regions in the state of Maryland. This growth (population
and land-use activities) continues to exert immense pressure on both its
resource and environment. Accordingly, a study was scoped to determine
the magnitude of land-use/land-cover change, with special emphasis on transportation,
and assess its impact on the local environment over the past ten years.
The study utilized data sets obtained from several sources. Such data include
remotely sensed imagery, land-use/land-cover maps, hydrology, and roads.
The remote sensing data comprised mostly Landsat Thematic Mapper (TM) images
acquired from the early 1990 to 1999 with varying temporal internals. The
Environment for Visualizing Images (ENVI) was used to process and analyze
the data on a Personal Computer (PC) environment. Five level-I land-use/land-cover
categories (urban, vegetation, cultivated, mix (bare/built-Up), and Water)
were analyzed for change in an attempt to reveal a general pattern and
trend. Initial analysis of the TM images for 1990 and 1999 showed increase
in the urban category and a decrease in the cultivated land. The final
results from this study are expected to be beneficial to scientists, resource
planners, managers, and policy makers.
Jarvis, C. H.; N. Stuart (1996). The sensitivity of a neural network
for classifying remotely sensed imagery. Computers & Geosciences,
22, (9): 959-67.
Keywords: Backpropagation; Feedforward neural nets; Image classification;
Learning (artificial intelligence); Remote sensing; Sensitivity; Neural
network sensitivity; Remotely sensed imagery classification; Feedforward
backpropagation neural network; Urban land cover classification; Landsat
TM data; Network nodes; Hidden layers; Input layers; Surplus nodes; Momentum;
Network learning; Optimal pairing; Convergence; Dockland area; Parametric
method; Parametric classifiers; Network parameters; Training times ; Accuracy
Original Abstract: A series of experiments are conducted on a feedforward
backpropagation neural network which is used to classify land cover from
Landsat TM data. By investigating the effects of changing the numbers of
network nodes in the input and hidden layers, potentially surplus nodes
can be identified and removed to create a more compact network, without
loss of classification accuracy. By exploring how momentum can be used
with different rates of network learning, an optimal pairing is found which
leads to a more rapid convergence and better classification of urban land
cover than obtained in previous studies where momentum rarely was used.
These optimal network parameters are used to classify an extract of a Landsat
TM image of a dockland area with accuracy equal to that obtained using
the maximum likelihood method. Given that in this case, the nature of the
image data is ideal for a parametric method, this result is not unexpected.
The competence of the neural technique is however demonstrated and criteria
are given to help determine in advance when neural techniques may be preferable
to parametric classifiers. Taken together, the findings show that careful
balancing and adjustment of network parameters may be required to obtain
a satisfactory result. The method can guide new users in configuring a
popular neural network to suit their image data. Given the specific nature
of our results, further research on neural networks in remote sensing could
benefit from more systematic reporting of network parameters, training
times and accuracies obtained.
Jaynes, C., (1999). View alignment of aerial and terrestrial imagery
in urban environments. Integrated Spatial Databases. Digital Images
and GIS. International Workshop ISD'99. Selected Papers (Lecture Notes
in Computer Science Vol.1737) Proceedings of NSFWS99: International Workshop
on Integrated Spatial Databases: Digital Images and GIS Portland, ME, USA
14-16 June 1999
Berlin, Germany Springer-Verlag, pp.3-19.
Keywords: Computational geometry; Geographic information systems;
Image reconstruction; Image registration; Image texture; Photography; Remote
sensing; Sensor fusion; Surveillance; Town and country planning; View alignment;
Aerial imagery; Terrestrial imagery; Urban environments; Information fusion;
Automatic model reconstruction; High-resolution building models; Built-up
areas; Calibrated aerial photography; Building location; Building 2D footprint;
Rooftop shape; Ground-level images; Close-range high-resolution views;
Pose information; 3D model; Symbolic model matching; Pose refinement technique;
High-resolution facade texture mapping; Model geometry; Segmentation; Pixel
regions; Vertical structures; Context-sensitive processing; Symbolic extraction
; Surface structures
Original abstract: Introduces an algorithm that fuses information from
aerial and terrestrial views for the automatic reconstruction of high-resolution
building models within built-up areas. Calibrated aerial photography is
commercially available for wide areas of coverage and has been shown to
be a useful source of information about the location of buildings at the
site, their 2D footprint and their rooftop shape. In contrast, terrestrial
imagery is usually uncalibrated, not available commercially for most urban
areas, and difficult to acquire. These ground-level images do, however,
provide close-range, high-resolution views that are not normally available
in aerial data. Our approach uses the pose information typically associated
with aerial surveillance imagery to acquire an initial 3D model of the
buildings at the site. Uncontrolled terrestrial imagery is then aligned
to the model using a symbolic model matching and pose refinement technique.
Once aligned, ground-level views can be used to enhance the site model
in a number of ways. High-resolution facade textures can be mapped onto
the model geometry using the recovered pose information and standard texture-mapping
algorithms. The same algorithms allow explicit segmentation of building
facades from terrestrial views as regions of pixels that project on to
vertical structures in the model. Context-sensitive processing can be applied
to these facade regions for the symbolic extraction of surface structures
such as windows, doors and pillars.
Jensen, J. R.; D. C. Cowen (1999). Remote sensing of urban suburban
infrastructure and socio-economic attributes. Photogrammetric Engineering
and Remote Sensing, V65, (N5): 611-622.
Keywords:
Jensen, J. R.; D. J. Cowen; J. Halls; S. Narumalani; N. J. Schmidt;
B. A. Davis; B. Burgess (1994). Improved Urban Infrastructure Mapping
and Forecasting for Bellsouth Using Remote Sensing and Gis Technology.
Photogrammetric Engineering and Remote Sensing, V60, (N3):
339-346.
Keywords:
Jian, L.; W. Renbiao (1998). An efficient algorithm for time delay
estimation. IEEE Transactions on Signal Processing, 46,
(8): 2231-5.
Keywords: Delays; Fourier transforms; Least squares approximations;
Parameter estimation; Pattern classification; Radar applications; Radar
detection; Radar signal processing; Time delay estimation; Computationally
efficient algorithm; wrelax; Relaxation-based minimizer; Nonlinear least
squares; Roadway subsurface anomalies detection; Subsurface anomalies classification;
Ultra-wideband ground-penetrating radar; Performance; Weighted Fourier
transform ; Range resolution
Original Abstract: We present a conceptually simple and computationally
efficient algorithm, which is referred to as WRELAX for the well-known
time delay estimation problem. The method is a relaxation-based minimizer
of a complicated nonlinear least squares criterion, WRELAX can be applied
to detecting and classifying roadway subsurface anomalies by using an ultra-wideband
ground-penetrating radar. Numerical and experimental examples are provided
to demonstrate the performance of the new algorithm.
Jimenez, L. O.; D. A. Landgrebe (1999). Hyperspectral data analysis
and supervised feature reduction via projection pursuit. Ieee Transactions
on Geoscience and Remote Sensing, V37, (N6): 2653-2667.
Keywords: hyperspectral data analysis , projection pursuit
Original Abstract: As the number of spectral bands of high-spectral
resolution data increases, the ability to detect more detailed classes
should also increase, and the classification accuracy should increase as
well. Often the number of labelled samples used for supervised classification
techniques is limited, thus limiting the precision with which class characteristics
can be estimated. As the number of spectral bands becomes large, the limitation
on performance imposed by the limited number of training samples can become
severe. A number of techniques for case-specific feature extraction have
been developed to reduce dimensionality without loss of class separability.
Most of these techniques require the estimation of statistics at full dimensionality
in order to extract relevant features for classification. If the number
of training samples is not adequately large, the estimation of parameters
in high-dimensional data will not be accurate enough. As a result, the
estimated features may not be as effective as they could be. This suggests
the need for reducing the dimensionality via a preprocessing method that
takes into consideration high-dimensional feature-space properties. Such
reduction should enable the estimation of feature-extraction parameters
to be more accurate. Using a technique referred to as projection pursuit
(PP), such an algorithm has been developed. This technique is able to bypass
many of the problems of the limitation of small numbers of training samples
by making the computations in a lower-dimensional space, and optimizing
a function called the projection index. A current limitation of this method
is that, as the number of dimensions increases, it is likely that a local
maximum of the projection index will be found that does not enable one
to fully exploit hyperspectral-data capabilities.
Jinwook, G.; L. Chulhee, (2000). Analytical decision boundary feature
extraction for neural networks. 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. IEEE 2000 International Geoscience and Remote
Sensing Symposium. Honolulu, HI, USA 24-28 July 2000
Piscataway, NJ, USA IEEE, pp.3072-4 vol.7.
Keywords: Feature extraction; Feedforward neural nets; Geophysical
signal processing; Geophysical techniques; Geophysics computing; Image
processing; Remote sensing; Terrain mapping; Geophysical measurement technique;
Land surface; Neural net; Decision boundary; Analytical method; Feedforward
neural network; Normal vector; 3 layer ; Sigmoid function
Original abstract: Recently, a feature extraction method based on decision
boundary has been proposed for neural networks. The method is based on
the fact that the vector normal to the decision boundary contains information
useful for discriminating between classes. However, the normal vector was
estimated numerically, resulting in inaccurate estimation and a long computational
time. The authors propose a new method to calculate the normal vector analytically
and derive all the necessary equations for 3 layer feedforward neural networks
with a sigmoid function. Experiments show that the proposed method provides
a noticeably improved performance.
Johnston, R. A.; T. De La Barra (2000). Comprehensive regional modeling
for long-range planning: linking integrated urban models and geographic
information systems. Transportation Research, Part A (Policy and
Practice), 34A, (2): 125-36.
Keywords: Geographic information systems; Town and country planning;
Transportation; Regional modeling; Long-range planning; Integrated urban
models; Regional transportation; Land use policies; tranus; Market-based
urban model; Land allocation model; Regional policy assessments; Spatial
competition ; User welfare
Original Abstract: Demonstrates the sequential linking of two types
of models to permit the comprehensive evaluation of regional transportation
and land use policies. First, we operate an integrated urban model (TRANUS),
which represents both land and travel markets with zones and networks.
The travel and land use projections from TRANUS are outlined, to demonstrate
the general reasonableness of the results, as this is the first application
of a market-based urban model in the US. Second, the land use projections
for each of the 58 zones in the urban model were fed into a geographic
information system (GIS)-based land allocation model, which spatially allocates
the several land uses within each zone according to simple accessibility
rules. While neither model is new, this is one of the first attempts to
link these two types of models for regional policy assessments. Other integrated
urban models may be linked to other GIS land allocation models in this
fashion. Pairing these two types of models allows the user to gain the
advantages of the urban models, which represent spatial competition across
a region and produce measures of user welfare (traveler and locator surplus),
and the advantages of the GIS land allocation models, which produce detailed
land use maps that can then be used for environmental impact assessment.
Jones, K. J., (2000). 2D wavelet feature detection for defining curved
boundaries in Landsat images. Image and Video Communications and Processing
2000 San Jose, CA, USA 25-28 Jan. 2000
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.796-806.
Keywords: Agriculture; Edge detection; Feature extraction; Remote
sensing; Vegetation mapping; Wavelet transforms; 2D wavelet feature detection;
Curved boundaries; Landsat images; Multiscale feature detection; Homogeneous
regions; Crops; Man-made boundaries; River beds; 2-D curve; 2-D edges ;
Remote sensing images
Original abstract: Multiscale feature detection is extended over a
large region of Landsat images to define boundaries between homogeneous
regions formed by individual crops. It is expected that it will be possible
to define a grid between homogeneous regions defined by both man-made boundaries
(2-D edges) and river beds (2-D curves) which define the availability of
water. This approach might be usefully applied to remote sensing images
based on other wavelengths (i.e. IR or laser remote sensing).
Jong-Hyn, P.; R. Tateishi; K. Wikantika; P. Jong-Geol, (1999). The
potential of high resolution remotely sensed data for urban infrastructure
monitoring. IEEE 1999 International Geoscience and Remote Sensing Symposium.
IGARSS'99 (Cat. No.99CH36293) Hamburg, Germany 28 June-2 July 1999
Piscataway, NJ, USA IEEE, v.V2, pp.1137-9.
Keywords: Multisource imagery Urban infrastructure monitoring, High
spatial resolution
Original abstract: The object of this research investigated the urban
infrastructure monitoring using high resolution remotely sensed data. Multi-source
imagery with high spatial resolution has great potential to improve the
performance of detailed urban expansion and infrastructure analysis. These
images allowed for continual monitoring of infrastructure needs. Multi-temporal
analysis of satellite imagery is effective for urban growth and changes
of infrastructure because a high correlation exists between spectral variation
in images from different dates and urban land cover change.
Jong-Hyun, P.; R. Tateishi; S. Dong-Jo; P. Chong-Hwa, (1998). Urban
expansion and change analysis using Russian 2m resolution DD-5, IRS-1C,
and Landsat TM 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.2577-9 vol.5.
Keywords: Geophysical signal processing; Geophysical techniques;
Remote sensing; Sensor fusion; Terrain mapping; Town and country planning;
Geophysical measurement technique; Land surface; Land use; Town planning;
Multispectral remote sensing; Image processing; Urban expansion; Change
analysis; dd-5; irs-1c; Landsat TM; Land cover; Agricultural land; Multisource
information fusion; Multisource imagery; Korea ; Seoul
Original abstract: This research was a pilot study for urban feature
interpretation and change analysis using multisource data. Data are used
Landsat TM, IRS-1C, and Russian 2m high resolution photographic image (DD-5).
The objective of this research is to analyze change in land cover from
agricultural land to a construction site or residential development using
multisource information fusion. Firstly, this study is to fuse the spectral
information from Landsat TM combine it with the spatial information from
DD-5 and IRS-1C. This data combination is essential for the change detection
and analysis. Secondly, this study is to compare the development of the
town, which is based on natural and artificial features before the new
town construction. The agricultural and forest area were destroyed and
urbanized by 5 new town constructions of The Seoul metropolitan region.
The authors' conclusions are that multisource imagery with moderate spatial
resolution has potential to improve the performance of detailed information
to policy maker for regional planning and decision making.
Kabanov, M. M.; S. N. Kapustin, (1998). Detecting buildings by remote
sensing of urban territories. Ascending and descending strategy of control.
Pattern Recognition and Image Analysis: New Information Technologies (PRIA-3-97)
Moscow, Russia Dec. 1997
MAIK Nauka/Interperiodica Publishing
Pattern Recognit. Image Anal. (Russia), pp.315-16.
Keywords: Image enhancement; Image segmentation; Object detection;
Remote sensing; Urban territories; Buildings detection; Mapping; Raster
image; Space pictures; Aerial pictures; Raster processing ; Sequential
detection
Original abstract: The updating of maps of urban territories is one
of the most difficult problems of modern mapping. The need for the constant
renewal of the maps necessitates the automation of input and updating of
the information. The detection of buildings in the raster image (aerial
and space pictures) is one of the key problems in this case. We developed
and realized two methods of raster processing for building detection (with
an ascending and descending strategy of control) that provide the best
results when combined. Both methods are based on the stepwise processing
of the raster image with sequential detection of the necessary objects.
Kageyama, Y.; M. Nishida; T. Oi, (2000). Analysis of the segments
extracted by automated lineament detection. 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.289-91 vol.1.
Keywords: Earth crust; Feature extraction; Geology; Geophysical
signal processing; Geophysical techniques; Image segmentation; Pattern
recognition; Radar imaging; Remote sensing; Remote sensing by radar; Synthetic
aperture radar; Tectonics; Topography (Earth); Geophysical measurement
technique; Land surface; Topography; Relief; Multispectral remote sensing;
Optical imaging; Crust structure; Automated lineament detection; Fault;
Lineament detection; Automatic extraction; Image processing; sar; Landsat
5 thematic mapper; Stream pattern; Subsurface structure; Drainage system
; Radar remote sensing
Original abstract: Lineaments are important features showing subsurface
elements or structural weaknesses such as faults. Most lineament maps have
been drawn based on fieldwork by experts and visual analysis of enhanced
image data. In visual interpretation and mapping of lineaments, geologists
use their knowledge and experience to extract the lineaments from the curved
and straight lines in image data. A different expert may extract different
segment elements through a visual approach. In order to conduct the lineament
detection under the same conditions, automatic extraction for lineaments
though image processing is useful. In an earlier paper, an extraction method
for lineaments using airborne Synthetic Aperture Radar (SAR) data was presented.
The results indicated that the segments given by the method agree with
a lineament map drawn by experts. The objective of this paper is to examine
the relationship between extracted segments from both airborne SAR and
Landsat 5 thematic mapper (TM) data and geographical features. River erosion
creates various stream patterns that are influenced by the subsurface structure.
Many lineaments can be extracted from a drainage system for topography.
This paper seeks to compare extracted segments and water systems. Also,
relief energies can indicate the level of the river erosion. The relief
energy at a study site has been compared and the correspondence between
the computation and extracted segments is described. Finally, the difference
between segments in SAR and TM data has been compared.
Katartzis, A.; H. Sahli; V. Pizurica; J. Cornelis (2001). A model-based
approach to the automatic extraction of linear features from airborne images.
IEEE Transactions on Geoscience and Remote Sensing, 39, (9):
2073-9.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Radar imaging; Remote sensing; Remote sensing by radar; Terrain
mapping; Geophysical measurement technique; Land surface; Radar remote
sensing; Image processing; Model-based approach; Automatic extraction;
Linear feature; Airborne image; Road; Path; sar; Airborne image analysis;
Synthetic aperture radar ; Optical imaging
Original Abstract: The authors describe a model-based method for the
automatic extraction of linear features, like roads and paths, from aerial
images. The paper combines and extends two earlier approaches for road
detection in SAR satellite images and presents the modifications needed
for the application domain of airborne image analysis together with representative
results.
Kaufman, Y. J.; D. Tanre (1996). Strategy for Direct and Indirect
Methods for Correcting the Aerosol Effect on Remote Sensing - from Avhrr
to Eos-Modis. Remote Sensing of Environment, V55, (N1):
65-79.
Keywords:
Original Abstract: Aerosol scatters solar radiation before it reaches
the surface and scatters and absorbs it again after it is reflected from
the surface and before it reaches the satellite sensor. The effect is spectrally
and spatially dependent. Therefore, atmospheric aerosol (dust, smoke, and
air pollution particles) has a significant effect on remote sensing. Correction
for the aerosol effect on remote sensing of land areas was never achieved
on an operational basis though several case studies were demonstrated.
We distinguish between direct correction, in which the aerosol loading
is derived from the image itself (or supplied from external sources) followed
by correction of the image using an appropriate radiative transfer model,
and indirect correction, achieved by defining remote sensing functions
that are less dependent on the aerosol loading. To some degree this was
already achieved in global remote sensing of vegetation where a composite
of several days of the normalized difference vegetation index (NDVI) measurements,
choosing the maximal value, was used instead of a single cloud-screened
value. The atmospheric resistant vegetation index (ARVI) introduced recently
for the Earth Observing System (EOS) Moderate Resolution Imaging Spectroradiometer
(MODIS) is the most appropriate example of indirect correction, where the
index is defined in such a way that the atmospheric effect in a blue spectral
channel cancels to a large degree the atmospheric effect in the red channel
in computations of the vegetation index. Atmospheric corrections can also
use aerosol climatology or simultaneous measurements with ground-based
instrumentation. These aspects of aerosol studies and remote sensing are
reviewed in this article. New advances in ground-based instrumentation
and future satellite systems (including measurements of polarization) are
discussed. In the conclusions a strategy is introduced for a combination
of ground-based measurements, with direct and indirect corrections that
is implemented for the EOS-MODIS and recommended for other similar platforms.
Such strategy, planned in advance, is a first step to face the challenge
and take advantage of the opportunities that the remote sensing community
will face with the launch of EOS and ADEOS in the next several years.
Kavzoglu, T.; P. M. Mather, (2000). Using feature selection techniques
to produce smaller neural networks with better generalisation capabilities.
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.3069-71 vol.7.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Geophysics computing; Neural nets; Remote sensing; Terrain
mapping; Geophysical measurement technique; Land surface; Image processing;
Feature selection; Smaller neural network; Neural net size; Generalisation;
Optimum network size ; Input features
Original abstract: The issue of feature selection is of considerable
importance, particularly where artificial neural networks are used, as
the size of the network is directly related to the number of input sources.
Despite the fact that artificial neural networks have been applied to solve
many problems in different fields, and found to be superior to conventional
statistical classifiers, they have a major drawback: the need to define
the optimum network size for a particular problem. In remote sensing applications,
which are generally in the area of image classification, the use of more
input features would make the network overspecific to the training data.
Over-specificity reduces the generalisation capabilities of a neural network.
Keechoo, C.; P. Incheol, (1996). A spatial decision support system
for transportation planning and investment decision analysis. URISA
Proceedings, Annual Conference. Papers from the Annual Conference of the
Urban and Regional Information Systems Association Proceedings of URISA
1996 Annual Meeting on Information Systems Salt Lake City, UT, USA 27 July-1
Aug. 1996
Washington, DC, USA Urban & Regional Inf. Syst. Assoc, pp.222-31.
Keywords: Decision support systems; Economics; Expert systems; Geographic
information systems; Traffic information systems; Transportation; Visual
databases; Transportation planning; Investment decision analysis; Expert
spatial decision support system; Data layers; Economic feasibility study;
Operating cost savings; GIS database; Sensitivity analysis; Cost data changes;
Economic efficiency indices; Benefit/cost ratio; Net present value; Infrastructure
expansion plans; Developing countries; Transportation planning model; Economic
feasibility model; Optimum route selection procedure ; Integrated GIS architecture
Original abstract: The paper proposes a more normative use of GIS for
transportation within the framework of an expert spatial decision support
system-how GIS can be exploited for generating optimum route based on such
data layers as slope, land use, aspect, and land value, etc. Coupled with
transportation planning models, GIS may be an efficient tool for conducting
an economic feasibility study of the proposed routes. That is, both benefits
(time and operating cost savings) and costs (construction and maintenance)
may be easily calculated based on GIS database. In addition, sensitivity
analysis can be easily conducted with cost data changes and various economic
efficiency indices (such as benefit/cost ratio, net present value and/or
internal rate of return) can be calculated. Considering numerous infrastructure
expansion plans especially in developing countries, the methodology combining
transportation planning model, optimum route selection procedure, GIS,
and economic feasibility model seems to be useful for evaluating economic
feasibility of the route proposed. In this sense, the purpose of the paper
is both to propose a structure of integrating different models and methodologies
for route selection and its evaluation inside an integrated GIS architecture.
Keechoo, C.; J. Wonjae (2000). Development of a transit network from
a street map database with spatial analysis and dynamic segmentation.
Transportation Research Part C (Emerging Technologies), 8C,
(1-6): 129-46.
Keywords: Geographic information systems; Service industries; Transportation;
Visual databases; Transit network development; Street map database; Spatial
analysis; Dynamic segmentation; Integrated transit-oriented travel demand
modeling procedure; gis; Transit stop digitizing; Route system building;
Topological relation; Street map databases; Legacy urban transportation
planning systems; utps; Travel modeling packages; Omnibus route design
; 'bus route planning
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.
Keenan, P. B. (1998). Spatial decision support systems for vehicle
routing. Decision Support Systems, 22, (1): 65-71.
Keywords: Decision support systems; Geographic information systems;
Management science; Transportation; Visual databases; Spatial decision
support systems; Vehicle routing ; Decision making
Original Abstract: The vehicle routing field is a well-developed area
of management science application. There is increasing recognition that
effective decision making in this field requires the incorporation of vehicle
routing techniques into a decision support system (DSS). In order to provide
decision support for a wide range of problems, routing techniques should
be combined with systems that can take advantage of new technologies. These
include spatial techniques drawn from the field of geographic information
systems (GIS). A synthesis of appropriate algorithms and a GIS based computer
system is identified as being necessary for effective decision support
for the vehicle routing problem.
Kennedy, R. E.; W. B. Cohen; G. Takao (1997). Empirical methods to
compensate for a view-angle-dependent brightness gradient in AVIRIS imagery.
Remote Sensing of Environment, V62, (N3): 277-291.
Keywords: AVIRIS
Original Abstract: A view-angle-dependent brightness gradient was observed
in an AVIRIS image of a forested region in Oregon's Cascade Mountains.
A method of removing the view-angle effect was sought that would not alter
the radiometric integrity of the image, and which would require minimal
ancillary information. Four methods were tested and evaluated in terms
of remaining brightness gradient and in terms of retention of spectral
characteristics. All methods used a quadratic fitting equation to model
the changes in brightness across view angles. Other descriptive coefficients
were calculated to aid in interpretation. The observed view-angle effect
varied with wavelength in a manner consistent with predictions of bidirectional
reflectance distribution function characteristics for vegetation. View-angle
effects were determined to contain both additive and multiplicative components,
with multiplicative components being strong in the chlorophyll absorption
region. The view-angle effect in a given pixel was a function of both an
underlying view-angle response determined by surface structure and the
inherent brightness of that pixel. The most successful compensation method
was the one that best accounted for broad differences between pixels in
these two components. Despite the simplifying assumptions necessary for
empirical view-angle correction techniques, they can still be useful for
hyperspectral remote-sensing data in situations where the view-angle brightness
variations would mask variance useful for extracting scene information.
Kiema, J. B. K., (2000). Wavelet compression and data fusion: An
investigation into the automatic classification of urban environments using
colour photography and laser scanning data. Proceedings 15th International
Conference on Pattern Recognition. Barcelona, Spain 3-7 Sept. 2000
Los Alamitos, CA, USA IEEE Comput. Soc, pp.85-9 vol.3.
Keywords: Data compression; Feature extraction; Image classification;
Image coding; Image segmentation; Infrared imaging; Maximum likelihood
estimation; Photogrammetry; Remote sensing by laser beam; Sensor fusion;
Terrain mapping; Wavelet compression; Data fusion; Urban environments;
Colour photography; Automatic classification; Airborne laser scanning data;
Colour infrared imagery; Context information; Feature base; Nonspectral
features; Spectral features; Maximum likelihood classification approach;
Urban scenes ; Wavelet-based algorithm
Original abstract: The field of wavelets has opened up new opportunities
for the compression of satellite sensory imagery. The paper examines the
influence of wavelet compression on the automatic classification of urban
environments. Airborne laser scanning data is introduced as an additional
channel along-side the spectral channels of colour infrared imagery. This
effectively integrates the local height and multi-spectral information
sources. To incorporate context information, the feature base is expanded
to include both spectral and non-spectral features. A maximum likelihood
classification approach is then applied. It is demonstrated that the classification
of urban scenes is considerably improved by fusing multi-spectral and geometric
data sets. The fused imagery is then systematically compressed (channel
by channel) at compression rates ranging from 5 to 100 using a wavelet-based
algorithm. The compressed imagery is then classified using the approach
described here-above. Analysis of the results obtained indicates that a
compression rate of up to 20 can conveniently be employed without adversely
affecting the segmentation results.
Kim, K.; N. Levine (1996). Using GIS to improve highway safety.
Computers, Environment and Urban Systems, 20, (4-5): 289-302.
Keywords: Data analysis; Geographic information systems; Safety;
Traffic information systems; Visual databases; gis; Highway safety; United
States; Intermodal Surface Transportation Efficiency Act; istea; Information
management systems; Public resources; Traffic safety GIS prototype; Spatial
analysis; Traffic collisions; Hawaii ; Motor vehicle collisions
Original Abstract: In the United States the Intermodal Surface Transportation
Efficiency Act (ISTEA) of 1991 has encouraged the development of information
management systems. GIS, to promote safety and efficient expenditure of
public resources, is an example. This paper therefore describes the development
of a traffic safety GIS prototype for spatial analysis of traffic collisions
in Honolulu, Hawaii. Various classes of spatial analyses, which involve
points, segments, and zones, with special reference to the nature of motor
vehicle collisions and traffic safety research, have been developed.
Kimura, H.; H. Kinoshita, (2000). Interferometric features of land
surface from a series of JERS-1 SAR interferograms. 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.2227-9 vol.5.
Keywords: Geophysical techniques; Remote sensing by radar; Spaceborne
radar; Synthetic aperture radar; Terrain mapping; Vegetation mapping; Geophysical
measurement technique; Land surface; Radar remote sensing; Interferometric
feature; jers-1; SAR interferogram; InSAR; Differential interferometry;
Corner reflector; Ground reference points; Coherency; Differential phase;
Land surface type; Forest; Urban; Residential; Paddy; Agriculture ; Farm
Original abstract: Experiments for differential interferometry were
conducted over sixteen months using corner reflectors (CRs). From eleven
scenes acquired during the period, four high-quality interferograms are
produced. Using CRs as ground reference points, baselines are estimated.
Referring to the digital elevation model (DEM), topographic effects are
removed. Interferometric features (coherency and differential phase) are
analyzed for typical land surface types; i.e. forest, urban, residential,
paddy and farm.
Kolbe, T. H.; L. Plumer; A. B. Cremers, (1996). Using constraints
for the identification of buildings in aerial images. PACT 96. Proceedings
of the Second International Conference on the Practical Application of
Constraint Technology Proceedings of PACT 96. London, UK 24-26 April 1996
Blackpool, UK Practical Application Company, pp.143-54.
Keywords: Constraint handling; Feature extraction; Geographic information
systems; Logic programming languages; Object detection; Town and country
planning; Building identification; Aerial images; Geo information systems;
Photogrammetry; Image processing; Low level syntactic operators; Line detectors;
Simple pattern matchers; Explicit models; Semantically meaningful objects;
Representation formalisms; Extracted image features; Aspect graphs; Constructive
solid geometry; Constraint logic programming; Representation formalism;
Implementation language; Strong heuristics ; Complex search problem
Original abstract: Aerial images constitute an important data source
for geo information systems. In order to get actual data at reasonable
costs, the development of (semi) automatic tools has been an active research
topic in photogrammetry and image processing in the recent years. Based
on established techniques for low level syntactic operators such as filters,
feature extraction, line detectors and simple pattern matchers, nowadays
there is strong interest in explicit models in order to improve the identification
of semantically meaningful objects. From the pixel to the object level,
several representation formalisms such as graphs of extracted image features,
aspect graphs and constructive solid geometry (CSG) are applied. Constraint
logic programming has been identified as an adequate representation formalism
and implementation language for building the necessary experimental environment,
specifying the models on the different levels, expressing strong heuristics
and approaching the complex search problem involved in object detection.
The paper focusses on the detection of buildings. It discusses model representation
by CLP program fragments and the required adaption and extensions of the
CLP(FD) solver of ECLIPSE, the Prolog/CLP platform underlying our implementation.
Illustrating examples show how the problems arising in the detection of
buildings are approached by CLP techniques.
Kumar, S.; J. Ghosh; M. M. Crawford (2001). Best-bases feature extraction
algorithms for classification of hyperspectral data. IEEE Transactions
on Geoscience and Remote Sensing, 39, (7): 1368-79.
Keywords: Feature extraction; Geophysical signal processing; Geophysical
techniques; Image classification; Multidimensional signal processing; Remote
sensing; Terrain mapping; Geophysical measurement technique; Land surface;
Multispectral remote sensing; Hyperspectral remote sensing; Best bases
feature extraction algorithm; Top-down algorithm; Bottom-up algorithm;
Agglomerative tree ; Fisher direction
Original Abstract: Due to advances in sensor technology, it is now
possible to acquire hyperspectral data simultaneously in hundreds of bands.
Algorithms that both reduce the dimensionality of the data sets and handle
highly correlated bands are required to exploit the information in these
data sets effectively. the authors propose a set of best-bases feature
extraction algorithms that are simple, fast, and highly effective for classification
of hyperspectral data. These techniques intelligently combine subsets of
adjacent bands into a smaller number of features. Both top-down and bottom-up
algorithms are proposed. The top-down algorithm recursively partitions
the bands into two (not necessarily equal) sets of bands and then replaces
each final set of bands by its mean value. The bottom-up algorithm builds
an agglomerative tree by merging highly correlated adjacent bands and projecting
them onto their Fisher direction, yielding high discrimination among classes.
Both these algorithms are used in a pairwise classifier framework where
the original C-class problem is divided into a set of (/sub 2//sup C/)
two-class problems. The new algorithms (1) find variable length bases localized
in wavelength, (2) favor grouping highly correlated adjacent bands that,
when merged either by taking their mean or Fisher linear projection, yield
maximum discrimination, and (3) seek orthogonal bases for each of the (/sub
2//sup C/) two-class problems into which a C-class problem can be decomposed.
Experiments on an AVIRIS data set for a 12-class problem show significant
improvements in classification accuracies while using a much smaller number
of features.
Kumar, S.; J. Ghosh; M. M. Crawford, (2000). Multiresolution feature
extraction for pairwise classification of hyperspectral data. Applications
of Artificial Neural Networks in Image Processing V San Jose, CA, USA 27-28
Jan. 2000
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.60-71.
Keywords: Computational complexity; Correlation methods; Feature
extraction; Geophysical signal processing; Image classification; Image
resolution; Terrain mapping; Multiresolution feature extraction; Pairwise
classification; Hyperspectral data; Landcover type prediction; Airborne
sensors; Spaceborne sensors; Remote sensing; Hyperspectral data acquisition;
EM spectrum; Electromagnetic spectrum window; Statistically correlated
bands; Efficient top-down multiresolution class-dependent feature extraction
algorithm; Pairwise classification scheme; Recursive band decomposition;
Subspaces ; AVIRIS data set
Original abstract: Prediction of landcover type from airborne/spaceborne
sensors is an important classification problem in remote sensing. Due to
advances in sensor technology, it is now possible to acquire hyperspectral
data simultaneously in more than 100 bands, each of which measures the
integrated response of a target over a narrow window of the electromagnetic
spectrum. The bands are ordered by their wavelengths and spectrally adjacent
bands are generally statistically correlated. Using such high dimensional
data for classification of landcover potentially provides greatly improved
results. However, it is necessary to select bands that provide the best
possible discrimination among the classes of interest. In this paper, we
propose an efficient top-down multiresolution class-dependent feature extraction
algorithm for hyperspectral data to be used with a pairwise classification
scheme. First, the C class problem is divided into (/sup C//sub 2/) two
class problems. Features for each pair of classes are extracted independently.
The algorithm decomposes the bands recursively into groups of adjacent
bands (subspaces) in a top-down fashion. The features extracted are specific
to the pair of classes that are being distinguished and exploit the ordering
information in the hyperspectral data. Experiments on a 183 band AVIRIS
data set for a 12 class problem show significant improvements in both classification
accuracies and the number of features required for all 66 pairs of classes.
Kuo-Tu, K., (1995). Using back-propagation neural networks and image
processing techniques to identify roads in Landsat TM imagery. Intelligent
Engineering Systems Through Artificial Neural Networks. Vol.5. Fuzzy Logic
and Evolutionary Programming. Proceedings of the Artificial Neural Networks
in Engineering (ANNIE'95) Proceedings of Intelligent Engineering Systems
through Artificial Neural Networks St. Louis, MO, USA 12-15 Nov. 1995
New York, NY, USA ASME Press, pp.809-14.
Keywords: Backpropagation; Image recognition; Neural nets; Object
detection; Remote sensing; Traffic engineering computing; Back-propagation
neural networks; Image processing techniques; Road identification; Landsat
TM imagery; Landsat Thematic Mapper satellite images; Interstate highways;
Bridges; Urban area roads; Residential area roads ; Parkways
Original abstract: The research reported in this paper investigates
an automated technique for the detection of roads (interstate highways,
two-lane highways, bridges, urban area roads, residential area roads, and
parkways) in Landsat Thematic Mapper satellite images. It is shown that
the hybrid system which combines traditional image processing techniques
with back-propagation neural networks performs better than using only image
processing techniques or only neural network techniques.
Kurtz, J. L.; J. M. Cowdery; J. H. Meloy; C. H. Overman, (2000). Subsurface
measurements utilizing the fusion of ground-coupled and air-launched GPR.
Subsurface Sensing Technologies and Applications II San Diego, CA, USA
31 July-3 Aug. 2000
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.466-73.
Keywords: Civil engineering; Permittivity measurement; Radar signal
processing; Radar tracking; Remote sensing by radar; Sensor fusion; Surface
topography measurement; Thickness measurement; Subsurface measurements;
Data fusion; Air-launched ground penetrating radar; Ground-coupled ground
penetrating radar; Signal processing techniques; Roadways; Subsurface layers;
Dielectric constant; Layer interface time differences; Layer thickness
measurement; Dual GPR system; Tracking; Asphalt air void content ; Surface
roughness
Original abstract: The authors are currently working on a task to fuse
the data from ground-coupled and air-launched ground penetrating radar
(GPR) systems. The goal of the project is to improve the overall accuracy
of the system and to extract additional information from the data. It is
important that to be able to obtain accurate depth and dielectric constant
information for roadways and the constituent subsurface layers. This has
not been consistently possible with current systems that rely on the amplitude
measurements of air-launched GPR because of variations in surface roughness
and material types. Using layer interface time differences from dual ground-coupled
antennas can mitigate the effects of surface roughness and variations of
the properties of materials by removing the dependence on amplitude measurements;
although locating the surface of the roadway is often difficult and inaccurate.
By using both systems, the air-launched GPR to locate the surface of the
roadway and the ground-coupled system with multiple antennas to locate
subsequent layers of the roadway, more accurate information about subsurface
roadway depth and dielectric constant can be obtained. This additional
information may allow better detection of subsurface anomalies. In addition,
by using the error obtained by calculating the thickness of the surface
layer with the air-launched system and comparing with the thickness calculated
with the fused data, an estimate of the roughness of the roadway surface
can be obtained. This paper describes the methods and signal processing
techniques being developed for this project as well as provide examples
of processed data that demonstrate applications.
Kurtz, J. L.; J. W. Fisher, III; G. Skau; J. Armaghani; J. G. Moxley,
(1997). Advances in ground-penetrating radar for road subsurface measurements.
Radar Sensor Technology II Orlando, FL, USA 24 April 1997
SPIE-Int. Soc. Opt. Eng
Proc. SPIE - Int. Soc. Opt. Eng. (USA), pp.11-21.
Keywords: Matched filters; Pattern classification; Radar applications;
Radar signal processing; Remote sensing by radar; Time-domain analysis;
Ground-penetrating radar; Road subsurface measurements; Subsurface characterization;
Florida Department of Transportation; High resolution measurements; Depth
profile scan rates; Time domain data; Thickness; Road surface; Subsurface
layers; Signal processing; Voids; Road layer interface; Florida DOT; Detection;
Classification; 1 GHz ; 50 to 55 mph
Original abstract: Ground penetrating radar (GPR) is becoming an increasingly
useful tool for road subsurface characterization. The Florida Department
of Transportation (FDOT) has obtained a 1 GHz ground penetrating radar
with the ability to make high resolution measurements. Depth profile scan
rates of the new radar are about 50 scan/sec and the radar operates on
a test van travelling at speeds up to 50-55 mph. The time domain data collected
by the GPR allow the determination of thickness of the road surface and
subsurface layers and, with appropriate signal processing, the data can
provide information about voids and other anomalies within road layer interfaces.
This paper describes the salient features of the Florida DOT ground penetrating
radar, measurement results, and applications of GPR for road assessments.
It also describes preliminary results of a University of Florida project
which is employing advanced signal processing techniques to detect and
classify subsurface anomalies in road layers.
Kux, H. J. H.; L. R. Penido; J. T. de Mattos, (1999). GIS techniques
applied to highway planning: the Sao Paulo metropolitan ring road (RODOANEL),
Brazil. 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.2699-701 vol.5.
Keywords: Geographic information systems; Town and country planning;
GIS techniques; Highway planning; Sao Paulo metropolitan ring road; rodoanel;
Brazil; Ground appropriateness; Sao Paulo Metropolitan Region; Synthetic
map; Thematic maps; Relief; Slope; Geology; Land use; Land cover; dersa
; Sao Paulo State Department of Highways
Original abstract: This study presents a GIS application to help the
analysis of the ground appropriateness to construct the ring road surrounding
Sao Paulo Metropolitan Region. A synthetic map was made, through the integration
of thematic maps on relief, slope, geology, land use/land cover. The map
obtained presents 5 quantitative classes of aptness for the location of
this highway, considering two trace alternatives for this highway, presented
by DERSA [Sao Paulo State Dept. of Highways].
Kyung Soo, C., (1995). Standardization efforts for digital road maps
and databases in Korea. *Steps Forward'. Proceedings of the Second
World Congress on Intelligent Transport Systems *95 Yokohama Japan 9-11
Nov. 1995
Tokyo, Japan Vehicle, Road & Traffic Intelligence Soc, pp.2459-64
vol.5.
Keywords: Driver information systems; Geographic information systems;
Navigation; Road traffic; Standardisation; Traffic control; Standardization;
Digital road maps; Korea; ATMS programs; Local governments; Automobile
industries; In-vehicle navigation devices; ITS planning and research group
; Korea Transportation Research Society
Original abstract: This paper identifies the available raw data and
its supplying institutions in Korea for digital road maps (DRM) and the
related databases. Various ATMS programs which are authorized in many local
governments in Korea are described, currently the consortium of automobile
industries is developing nationwide DRM database for in-vehicle navigation
devices. The general description of the databases and their organization
are provided in this paper. Finally, this paper explains the approaches
and activities of the ITS planning and research group (K.ITS P&RG)
in the Korea Transportation Research Society (KTRS) for the integrated
solution for these problems.