Author: Jason E. West
Publisher:
ISBN:
Category : Detectors
Languages : en
Pages : 192
Book Description
"Algorithms exploiting hyperspectral imagery for target detection have continually evolved to provide improved detection results. Adaptive matched filters, which may be derived in many different scientific fields, can be used to locate spectral targets by modeling scene background as either structured geometric) with a set of endmembers (basis vectors) or as unstructured stochastic) with a covariance matrix. In unstructured background research, various methods of calculating the background covariance matrix have been developed, each involving either the removal of target signatures from the background model or the segmenting of image data into spatial or spectral subsets. The objective of these methods is to derive a background which matches the source of mixture interference for the detection of sub pixel targets, or matches the source of false alarms in the scene for the detection of fully resolved targets. In addition, these techniques increase the multivariate normality of the data from which the background is characterized, thus increasing adherence to the normality assumption inherent in the matched filter and ultimately improving target detection results. Such techniques for improved background characterization are widely practiced but not well documented or compared. This thesis will establish a strong theoretical foundation, describing the necessary preprocessing of hyperspectral imagery, deriving the spectral matched filter, and capturing current methods of unstructured background characterization. The extensive experimentation will allow for a comparative evaluation of several current unstructured background characterization methods as well as some new methods which improve stochastic modeling of the background. The results will show that consistent improvements over the scene-wide statistics can be achieved through spatial or spectral subsetting, and analysis of the results provides insight into the tradespaces of matching the interference, background multivariate normality and target exclusion for these techniques"--Abstract.
Matched Filter Stochastic Background Characterization for Hyperspectral Target Detection
Author: Jason E. West
Publisher:
ISBN:
Category : Detectors
Languages : en
Pages : 192
Book Description
"Algorithms exploiting hyperspectral imagery for target detection have continually evolved to provide improved detection results. Adaptive matched filters, which may be derived in many different scientific fields, can be used to locate spectral targets by modeling scene background as either structured geometric) with a set of endmembers (basis vectors) or as unstructured stochastic) with a covariance matrix. In unstructured background research, various methods of calculating the background covariance matrix have been developed, each involving either the removal of target signatures from the background model or the segmenting of image data into spatial or spectral subsets. The objective of these methods is to derive a background which matches the source of mixture interference for the detection of sub pixel targets, or matches the source of false alarms in the scene for the detection of fully resolved targets. In addition, these techniques increase the multivariate normality of the data from which the background is characterized, thus increasing adherence to the normality assumption inherent in the matched filter and ultimately improving target detection results. Such techniques for improved background characterization are widely practiced but not well documented or compared. This thesis will establish a strong theoretical foundation, describing the necessary preprocessing of hyperspectral imagery, deriving the spectral matched filter, and capturing current methods of unstructured background characterization. The extensive experimentation will allow for a comparative evaluation of several current unstructured background characterization methods as well as some new methods which improve stochastic modeling of the background. The results will show that consistent improvements over the scene-wide statistics can be achieved through spatial or spectral subsetting, and analysis of the results provides insight into the tradespaces of matching the interference, background multivariate normality and target exclusion for these techniques"--Abstract.
Publisher:
ISBN:
Category : Detectors
Languages : en
Pages : 192
Book Description
"Algorithms exploiting hyperspectral imagery for target detection have continually evolved to provide improved detection results. Adaptive matched filters, which may be derived in many different scientific fields, can be used to locate spectral targets by modeling scene background as either structured geometric) with a set of endmembers (basis vectors) or as unstructured stochastic) with a covariance matrix. In unstructured background research, various methods of calculating the background covariance matrix have been developed, each involving either the removal of target signatures from the background model or the segmenting of image data into spatial or spectral subsets. The objective of these methods is to derive a background which matches the source of mixture interference for the detection of sub pixel targets, or matches the source of false alarms in the scene for the detection of fully resolved targets. In addition, these techniques increase the multivariate normality of the data from which the background is characterized, thus increasing adherence to the normality assumption inherent in the matched filter and ultimately improving target detection results. Such techniques for improved background characterization are widely practiced but not well documented or compared. This thesis will establish a strong theoretical foundation, describing the necessary preprocessing of hyperspectral imagery, deriving the spectral matched filter, and capturing current methods of unstructured background characterization. The extensive experimentation will allow for a comparative evaluation of several current unstructured background characterization methods as well as some new methods which improve stochastic modeling of the background. The results will show that consistent improvements over the scene-wide statistics can be achieved through spatial or spectral subsetting, and analysis of the results provides insight into the tradespaces of matching the interference, background multivariate normality and target exclusion for these techniques"--Abstract.
Remote Sensing
Author: John R. Schott
Publisher: Oxford University Press
ISBN: 0199724393
Category : Technology & Engineering
Languages : en
Pages : 701
Book Description
Remote Sensing deals with the fundamental ideas underlying the rapidly growing field of remote sensing. John Schott explores energy-matter interaction, radiation propagation, data dissemination, and described the tools and procedures required to extract information from remotely sensed data using the image chain approach. Organizations and individuals often focus on one aspect of the remote sensing process before considering it as a whole, thus investigating unjustified effort, time, and expense to get minimal improvement. Unlike other books on the subject, Remote Sensing treats the process as a continuous flow. Schott examines the limitations obstructing the flow of information to the user, employing numerous applications of remote sensing to earth observation disciplines. For this second edition, in addition to a thorough update, there are major changes and additions, such as a much more complete treatment of spectroscopic imaging, which has matured dramatically in the last ten years, and a more rigorous treatment of image processing with an emphasis on spectral image processing algorithms. Remote Sensing is an ideal first text in remote sensing for advanced undergraduate and graduate students in the physical or engineering sciences, and will also serve as a valuable reference for practitioners.
Publisher: Oxford University Press
ISBN: 0199724393
Category : Technology & Engineering
Languages : en
Pages : 701
Book Description
Remote Sensing deals with the fundamental ideas underlying the rapidly growing field of remote sensing. John Schott explores energy-matter interaction, radiation propagation, data dissemination, and described the tools and procedures required to extract information from remotely sensed data using the image chain approach. Organizations and individuals often focus on one aspect of the remote sensing process before considering it as a whole, thus investigating unjustified effort, time, and expense to get minimal improvement. Unlike other books on the subject, Remote Sensing treats the process as a continuous flow. Schott examines the limitations obstructing the flow of information to the user, employing numerous applications of remote sensing to earth observation disciplines. For this second edition, in addition to a thorough update, there are major changes and additions, such as a much more complete treatment of spectroscopic imaging, which has matured dramatically in the last ten years, and a more rigorous treatment of image processing with an emphasis on spectral image processing algorithms. Remote Sensing is an ideal first text in remote sensing for advanced undergraduate and graduate students in the physical or engineering sciences, and will also serve as a valuable reference for practitioners.
Computer Analysis of Images and Patterns
Author: George Azzopardi
Publisher: Springer
ISBN: 3319231170
Category : Computers
Languages : en
Pages : 821
Book Description
The two volume set LNCS 9256 and 9257 constitutes the refereed proceedings of the 16th International Conference on Computer Analysis of Images and Patterns, CAIP 2015, held in Valletta, Malta, in September 2015. The 138 papers presented were carefully reviewed and selected from numerous submissions. CAIP 2015 is the sixteenth in the CAIP series of biennial international conferences devoted to all aspects of computer vision, image analysis and processing, pattern recognition, and related fields.
Publisher: Springer
ISBN: 3319231170
Category : Computers
Languages : en
Pages : 821
Book Description
The two volume set LNCS 9256 and 9257 constitutes the refereed proceedings of the 16th International Conference on Computer Analysis of Images and Patterns, CAIP 2015, held in Valletta, Malta, in September 2015. The 138 papers presented were carefully reviewed and selected from numerous submissions. CAIP 2015 is the sixteenth in the CAIP series of biennial international conferences devoted to all aspects of computer vision, image analysis and processing, pattern recognition, and related fields.
Robust Matched Filters for Target Detection in Hyperspectral Imaging Data
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 5
Book Description
Most detection algorithms for hyperspectral imaging applications assume a targetwith a perfectly known spectral signature. In practice, the target signature is either imperfectly measured (target mismatch) and/or it exhibits spectral variability. The objective of this paper is to introduce a robust matched lter that takes the uncertainty and/or variability of target signatures into account. It is shown that, if we describe this uncertainty with an ellipsoid in the spectral space, we can design a matched lter that provides a response of the same magnitude for all spectra within this ellipsoid. Thus, by changing the size of this ellipsoid, we can control the "spectral selectivity" of the matched lter. The ability of the robust matched lter to deal effectively with target mismatch and spectral variability is demonstrated with hyperspectral imaging data from the HYDICE sensor.
Publisher:
ISBN:
Category :
Languages : en
Pages : 5
Book Description
Most detection algorithms for hyperspectral imaging applications assume a targetwith a perfectly known spectral signature. In practice, the target signature is either imperfectly measured (target mismatch) and/or it exhibits spectral variability. The objective of this paper is to introduce a robust matched lter that takes the uncertainty and/or variability of target signatures into account. It is shown that, if we describe this uncertainty with an ellipsoid in the spectral space, we can design a matched lter that provides a response of the same magnitude for all spectra within this ellipsoid. Thus, by changing the size of this ellipsoid, we can control the "spectral selectivity" of the matched lter. The ability of the robust matched lter to deal effectively with target mismatch and spectral variability is demonstrated with hyperspectral imaging data from the HYDICE sensor.
Electro-optical Remote Sensing
Author: Gary W. Kamerman
Publisher: SPIE-International Society for Optical Engineering
ISBN: 9780819460103
Category : Technology & Engineering
Languages : en
Pages : 232
Book Description
Proceedings of SPIE present the original research papers presented at SPIE conferences and other high-quality conferences in the broad-ranging fields of optics and photonics. These books provide prompt access to the latest innovations in research and technology in their respective fields. Proceedings of SPIE are among the most cited references in patent literature.
Publisher: SPIE-International Society for Optical Engineering
ISBN: 9780819460103
Category : Technology & Engineering
Languages : en
Pages : 232
Book Description
Proceedings of SPIE present the original research papers presented at SPIE conferences and other high-quality conferences in the broad-ranging fields of optics and photonics. These books provide prompt access to the latest innovations in research and technology in their respective fields. Proceedings of SPIE are among the most cited references in patent literature.
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery
Author:
Publisher:
ISBN:
Category : Computer algorithms
Languages : en
Pages : 424
Book Description
Publisher:
ISBN:
Category : Computer algorithms
Languages : en
Pages : 424
Book Description
Detection Algorithms for Hyperspectral Imaging Applications
Author: Dimitris G. Manolakis
Publisher:
ISBN:
Category :
Languages : en
Pages : 79
Book Description
Publisher:
ISBN:
Category :
Languages : en
Pages : 79
Book Description
Multicovariance Matched Filter for Target Detection in Images
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 9
Book Description
Our original research on the multicovariance matched filter deals with optimum low resolution target detection in a single-frame, multicolor image, such as a multispectral infrared or polarimetric synthetic aperture radar picture. The multicovariance method completely uses all the joint variability of the problem, in both space and frequency, in a way that generalizes both the traditional spatial matched filter and also techniques involving scalar ratios between frequency bands. The main new focus of our work, directed toward achieving the best target detection performance that is possible, is to develop a preprocessing step involving optimal adaptive estimation of the local clutter background. This involves segmenting the image into regions, which correspond to different background/clutter statistical models. Statistics of real data are being studied and used in new state-of-the-art hierarchical segmentation algorithms based on Markov Random Field, polynomial and autoregressive models for vector-valued random processes. The major algorithmic challenges here are in estimating the best possible background/clutter models and in accurately estimating the boundaries between different model regions. We are in the process of developing extremely efficient and robust algorithms to estimate these clutter models. These are similar to familiar algorithms from mainstream signal processing, but solve the interpolation problem for Markov Random Fields, which is different than the usual linear prediction problem. (MM).
Publisher:
ISBN:
Category :
Languages : en
Pages : 9
Book Description
Our original research on the multicovariance matched filter deals with optimum low resolution target detection in a single-frame, multicolor image, such as a multispectral infrared or polarimetric synthetic aperture radar picture. The multicovariance method completely uses all the joint variability of the problem, in both space and frequency, in a way that generalizes both the traditional spatial matched filter and also techniques involving scalar ratios between frequency bands. The main new focus of our work, directed toward achieving the best target detection performance that is possible, is to develop a preprocessing step involving optimal adaptive estimation of the local clutter background. This involves segmenting the image into regions, which correspond to different background/clutter statistical models. Statistics of real data are being studied and used in new state-of-the-art hierarchical segmentation algorithms based on Markov Random Field, polynomial and autoregressive models for vector-valued random processes. The major algorithmic challenges here are in estimating the best possible background/clutter models and in accurately estimating the boundaries between different model regions. We are in the process of developing extremely efficient and robust algorithms to estimate these clutter models. These are similar to familiar algorithms from mainstream signal processing, but solve the interpolation problem for Markov Random Fields, which is different than the usual linear prediction problem. (MM).
Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery
Author:
Publisher:
ISBN:
Category : Computer algorithms
Languages : en
Pages : 622
Book Description
Publisher:
ISBN:
Category : Computer algorithms
Languages : en
Pages : 622
Book Description
A Learning-based Approach for Natural Background Characterization
Author: Songnian Rong
Publisher:
ISBN:
Category : Automatic tracking
Languages : en
Pages : 150
Book Description
Publisher:
ISBN:
Category : Automatic tracking
Languages : en
Pages : 150
Book Description