Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295207
J. Benediktsson, J. Palmason, J. R. Sveinsson
Classification of hyperspectral data with high spatial resolution is discussed. A method based on mathematical morphology for pre-processing of the hyperspectral data is investigated. In this approach, opening and closing morphological transforms are used in order to isolate bright (opening) and dark (closing) structures in images, where bright/dark means brighter/darker than the surrounding features in the images. Then, a morphological profile is constructed based on the repeated use of openings and closings with a differently sized structuring element. In order to apply the morphological approach to hyperspectral data, principal components are computed. Then, the principal components are used as base images for the morphological profiles. The use of extended morphological profiles, based on more than one principal component is proposed. In experiments, two data sets are classified. The proposed method performs well in terms of classification accuracies. It gives similar overall accuracies to statistical approaches.
{"title":"Morphological pre-processing for classification of hyperspectral data from urban areas","authors":"J. Benediktsson, J. Palmason, J. R. Sveinsson","doi":"10.1109/WARSD.2003.1295207","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295207","url":null,"abstract":"Classification of hyperspectral data with high spatial resolution is discussed. A method based on mathematical morphology for pre-processing of the hyperspectral data is investigated. In this approach, opening and closing morphological transforms are used in order to isolate bright (opening) and dark (closing) structures in images, where bright/dark means brighter/darker than the surrounding features in the images. Then, a morphological profile is constructed based on the repeated use of openings and closings with a differently sized structuring element. In order to apply the morphological approach to hyperspectral data, principal components are computed. Then, the principal components are used as base images for the morphological profiles. The use of extended morphological profiles, based on more than one principal component is proposed. In experiments, two data sets are classified. The proposed method performs well in terms of classification accuracies. It gives similar overall accuracies to statistical approaches.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124709837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295171
D. Stein
Hyperspectral sensors have been deployed from airborne and spaceborne platforms to collect imaging spectrometry data for environmental, economic, and military applications including scene classification and material identification. A variety of models have been applied to hyperspectral imagery including the normal mixture (NMM), linear mixture (LMM), and subspace (SM) models, for purposes that include developing land cover classification maps, retrieving environmental parameters, detecting objects of interest, and predicting system performance. None of these models account for both subpixel mixing, i.e., multiple material types occupying the same pixel, and intra-class spectral variability. The stochastic mixture model and the normal compositional model (NCM) were defined to explicitly allow for these characteristics, and to bring second order statistical information to bear on compositional problems. In this paper, the normal compositional model is defined, methods of estimating the parameters are described, and applications that demonstrate its utility are presented.
{"title":"Application of the normal compositional model to the analysis of hyperspectral imagery","authors":"D. Stein","doi":"10.1109/WARSD.2003.1295171","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295171","url":null,"abstract":"Hyperspectral sensors have been deployed from airborne and spaceborne platforms to collect imaging spectrometry data for environmental, economic, and military applications including scene classification and material identification. A variety of models have been applied to hyperspectral imagery including the normal mixture (NMM), linear mixture (LMM), and subspace (SM) models, for purposes that include developing land cover classification maps, retrieving environmental parameters, detecting objects of interest, and predicting system performance. None of these models account for both subpixel mixing, i.e., multiple material types occupying the same pixel, and intra-class spectral variability. The stochastic mixture model and the normal compositional model (NCM) were defined to explicitly allow for these characteristics, and to bring second order statistical information to bear on compositional problems. In this paper, the normal compositional model is defined, methods of estimating the parameters are described, and applications that demonstrate its utility are presented.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121982590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295226
J.S. Pearlman, A. Dyk, D. Goodenough, Zhenkui Ma, M. Crawford, A. Neuenschwander, Jisoo Ham
In considering the design of an operational space-based hyperspectral imager, instrument characteristics such as signal-to-noise, ground resolution and spectral coverage are factors for both system capability and cost. To provide a basis for imager optimization, an exploratory study was performed to investigate the impact of instrument characteristics on forest species classification, as an example criterion. A study site with pure and mixed western hemlock and Douglas fir stands was imaged with Hyperion and AVIRIS. The data were analyzed using classification accuracy of a maximum a posteriori Bayesian classifier applied to selected maximum noise fraction (MNF) transformed features and a random subspace binary hierarchical classifier as a metric for instrument performance. Quantitative results for signal-to-noise, ground resolution, and spectral range suggest operational parameters for hyperspectral imaging systems and clearly indicate the need for advances in methodology for analysis of hyperspectral data.
{"title":"Analysis of forest environments - classification as a metric of hyperspectral instrument performance","authors":"J.S. Pearlman, A. Dyk, D. Goodenough, Zhenkui Ma, M. Crawford, A. Neuenschwander, Jisoo Ham","doi":"10.1109/WARSD.2003.1295226","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295226","url":null,"abstract":"In considering the design of an operational space-based hyperspectral imager, instrument characteristics such as signal-to-noise, ground resolution and spectral coverage are factors for both system capability and cost. To provide a basis for imager optimization, an exploratory study was performed to investigate the impact of instrument characteristics on forest species classification, as an example criterion. A study site with pure and mixed western hemlock and Douglas fir stands was imaged with Hyperion and AVIRIS. The data were analyzed using classification accuracy of a maximum a posteriori Bayesian classifier applied to selected maximum noise fraction (MNF) transformed features and a random subspace binary hierarchical classifier as a metric for instrument performance. Quantitative results for signal-to-noise, ground resolution, and spectral range suggest operational parameters for hyperspectral imaging systems and clearly indicate the need for advances in methodology for analysis of hyperspectral data.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122478269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295172
M. Datcu, K. Seidel
The progress in information retrieval, computer vision and image analysis makes possible to establish very complete bases of algorithms and operators. A specialist in remote sensing or image processing has the tools now allowing him, at least in theory, to configure applications solving complex problems of image understanding. However, in reality, the Earth observation data analysis is still performed in a very laborious way at the end of repeated cycles of trial and error. To this end we propose a novel advanced remote sensing information processing system, based on human centered concepts, which implement new features and functions allowing improved feature extraction, search on a semantic level, the availability of collected knowledge, interactive knowledge discovery and new visual user interfaces.
{"title":"Human centered concepts for exploration and understanding of satellite images","authors":"M. Datcu, K. Seidel","doi":"10.1109/WARSD.2003.1295172","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295172","url":null,"abstract":"The progress in information retrieval, computer vision and image analysis makes possible to establish very complete bases of algorithms and operators. A specialist in remote sensing or image processing has the tools now allowing him, at least in theory, to configure applications solving complex problems of image understanding. However, in reality, the Earth observation data analysis is still performed in a very laborious way at the end of repeated cycles of trial and error. To this end we propose a novel advanced remote sensing information processing system, based on human centered concepts, which implement new features and functions allowing improved feature extraction, search on a semantic level, the availability of collected knowledge, interactive knowledge discovery and new visual user interfaces.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126366337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295220
D. Goodenough, T. Han, J. Pearlman, A. Dyk, S. McDonald
For forest chemical concentration mapping with hyperspectral imagery, it is a common practice to relate chemical measurements to image spectra by one of several linear regression techniques. To improve the mapping accuracy, we apply arithmetic transformations to the image spectra to reduce the spectra variations due to differences of fractional compositions within pixels. Canopy endmember fractions, derived from a linear spectral unmixing, are used to adjust the chemical measurements to reflect the pixel fractional composition. It is found in this study that the 2/sup nd/ derivative of absorbance spectra have the best correlation with foliar nitrogen measurements. Moreover, the adjustments with canopy endmember fractions can improve this correlation. Finally a foliar nitrogen concentration map is created by using a multiple linear regression to relate the canopy-fraction-adjusted nitrogen measurements to the 2/sup nd/ derivative absorbance spectra.
{"title":"Forest chemistry mapping with hyperspectral data","authors":"D. Goodenough, T. Han, J. Pearlman, A. Dyk, S. McDonald","doi":"10.1109/WARSD.2003.1295220","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295220","url":null,"abstract":"For forest chemical concentration mapping with hyperspectral imagery, it is a common practice to relate chemical measurements to image spectra by one of several linear regression techniques. To improve the mapping accuracy, we apply arithmetic transformations to the image spectra to reduce the spectra variations due to differences of fractional compositions within pixels. Canopy endmember fractions, derived from a linear spectral unmixing, are used to adjust the chemical measurements to reflect the pixel fractional composition. It is found in this study that the 2/sup nd/ derivative of absorbance spectra have the best correlation with foliar nitrogen measurements. Moreover, the adjustments with canopy endmember fractions can improve this correlation. Finally a foliar nitrogen concentration map is created by using a multiple linear regression to relate the canopy-fraction-adjusted nitrogen measurements to the 2/sup nd/ derivative absorbance spectra.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126138483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295178
J. Lira, A. Rodríguez
A series of problems in remote sensing require the segmentation of specific spectral objects such as water bodies, saline soils or agricultural fields. Further analysis of these objects, from multi-spectral images, may include the calculation of optical reflectance variables such as chlorophyll concentration, albedo or vegetation humidity. To derive reliable measurements of these variables a precise segmentation - from the rest of image - of the spectral objects is needed. In this work we propose a new methodology to segment spectral objects based on canonical analysis and a split-and-merge clustering algorithm. Three examples are provided to demonstrate the goodness of the methodology.
{"title":"Segmentation of spectral objects from multi-spectral images using canonical analysis","authors":"J. Lira, A. Rodríguez","doi":"10.1109/WARSD.2003.1295178","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295178","url":null,"abstract":"A series of problems in remote sensing require the segmentation of specific spectral objects such as water bodies, saline soils or agricultural fields. Further analysis of these objects, from multi-spectral images, may include the calculation of optical reflectance variables such as chlorophyll concentration, albedo or vegetation humidity. To derive reliable measurements of these variables a precise segmentation - from the rest of image - of the spectral objects is needed. In this work we propose a new methodology to segment spectral objects based on canonical analysis and a split-and-merge clustering algorithm. Three examples are provided to demonstrate the goodness of the methodology.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134521764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295174
I. Koren, J. Joseph
A new approach to cluster analysis is proposed, namely morphological component analysis (MCA), to enhance discrimination of features in multi-channel satellite images. The characterization of clusters, in this method, is morphological, unlike some of the classical cluster approaches in which the clusters are defined by their centers. By using the shape and orientation of the clusters, it is possible to define an affine transformation of the cluster space into a new one in which the selected clusters are orthogonal or better separated. Such an operation can be considered as supervised independent component analysis.
{"title":"Morphological component analysis for feature detection in satellite images","authors":"I. Koren, J. Joseph","doi":"10.1109/WARSD.2003.1295174","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295174","url":null,"abstract":"A new approach to cluster analysis is proposed, namely morphological component analysis (MCA), to enhance discrimination of features in multi-channel satellite images. The characterization of clusters, in this method, is morphological, unlike some of the classical cluster approaches in which the clusters are defined by their centers. By using the shape and orientation of the clusters, it is possible to define an affine transformation of the cluster space into a new one in which the selected clusters are orthogonal or better separated. Such an operation can be considered as supervised independent component analysis.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124987030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295200
D. Ramasubramanian, L. Kanal
The amount of image data acquired by space-based remote sensing missions has increased phenomenally over the years. This poses severe constraints on storage and network bandwidth resources. Image compression methods are employed to overcome some of these problems. However, in order to perform any image processing operations (such as feature extraction, segmentation, spectral analysis etc.), images need to be decompressed first. Obviously, decoding or decompression requires more computational and storage resources. Also, this step does not produce new information. By directly operating on compressed images, we can eliminate the need for decompression and save time and space. In this paper, we present a framework to classify remotely sensed images in the compressed domain. Specifically, we propose a compression model based on Vector Quantization. Indices and codevectors that represent macro blocks of an image are exploited in the subsequent classification phase. Our experiments demonstrate that the proposed method is very efficient.
{"title":"Classification of remotely sensed images in compressed domain","authors":"D. Ramasubramanian, L. Kanal","doi":"10.1109/WARSD.2003.1295200","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295200","url":null,"abstract":"The amount of image data acquired by space-based remote sensing missions has increased phenomenally over the years. This poses severe constraints on storage and network bandwidth resources. Image compression methods are employed to overcome some of these problems. However, in order to perform any image processing operations (such as feature extraction, segmentation, spectral analysis etc.), images need to be decompressed first. Obviously, decoding or decompression requires more computational and storage resources. Also, this step does not produce new information. By directly operating on compressed images, we can eliminate the need for decompression and save time and space. In this paper, we present a framework to classify remotely sensed images in the compressed domain. Specifically, we propose a compression model based on Vector Quantization. Indices and codevectors that represent macro blocks of an image are exploited in the subsequent classification phase. Our experiments demonstrate that the proposed method is very efficient.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127740454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295205
J. Tyo, R. C. Olsen
We present a new pseudocolor mapping strategy for use with spectral imagery based on a principal components analysis of spectral data. The mapping capitalizes on the similarities between human vision and hyperspectral data. The transformation results in final images where the color assigned to each pixel is solely determined by the position within the data cloud. Materials with similar spectral characteristics are presented in similar hues. This display strategy can be the first step in a supervised classification and clustering method.
{"title":"PC-based display strategy for spectral imagery","authors":"J. Tyo, R. C. Olsen","doi":"10.1109/WARSD.2003.1295205","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295205","url":null,"abstract":"We present a new pseudocolor mapping strategy for use with spectral imagery based on a principal components analysis of spectral data. The mapping capitalizes on the similarities between human vision and hyperspectral data. The transformation results in final images where the color assigned to each pixel is solely determined by the position within the data cloud. Materials with similar spectral characteristics are presented in similar hues. This display strategy can be the first step in a supervised classification and clustering method.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132961221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-10-27DOI: 10.1109/WARSD.2003.1295201
P. S. Hong, Lance M. Kaplan, M.J.T. Smith
This paper presents a method for appending texture information to existing hyperspectral data to increase classification accuracy. The features extracted for texture classification are based on the subbands of various configurations of the octave-band directional filter bank. This filter bank represents a computationally efficient alternative to other 2-D decompositions, and it is able to divide frequency space into equivalent and meaningful partitions. Results using different radial and angular resolutions are presented, and the different filter bank configurations are compared and discussed with respect to other decompositions.
{"title":"Hyperspectral image segmentation using filter banks for texture augmentation","authors":"P. S. Hong, Lance M. Kaplan, M.J.T. Smith","doi":"10.1109/WARSD.2003.1295201","DOIUrl":"https://doi.org/10.1109/WARSD.2003.1295201","url":null,"abstract":"This paper presents a method for appending texture information to existing hyperspectral data to increase classification accuracy. The features extracted for texture classification are based on the subbands of various configurations of the octave-band directional filter bank. This filter bank represents a computationally efficient alternative to other 2-D decompositions, and it is able to divide frequency space into equivalent and meaningful partitions. Results using different radial and angular resolutions are presented, and the different filter bank configurations are compared and discussed with respect to other decompositions.","PeriodicalId":395735,"journal":{"name":"IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134356922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：