MSTAR's extensible search engine and model-based inferencing toolkit

John W Wissinger, Robert Ristroph, Joseph Diemunsch, William Severson, Eric Freudenthal

Research output: Chapter in Book/Report/Conference proceedingChapter

14 Citations (Scopus)

Abstract

The DARPA/AFRL `Moving and Stationary Target Acquisition and Recognition' (MSTAR) program is developing a model-based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The motivation for this work is to develop a high performance ATR capability that can identify ground targets in highly unconstrained imaging scenarios that include variable image acquisition geometry, arbitrary target pose and configuration state, differences in target deployment situation, and strong intra-class variations. The MSTAR approach utilizes radar scattering models in an on-line hypothesize-and-test operation that compares predicted target signature statistics with features extracted from image data in an attempt to determine a `best fit' explanation of the observed image. Central to this processing paradigm is the Search algorithm, which provides intelligent control in selecting features to measure and hypotheses to test, as well as in making the decision about when to stop processing and report a specific target type or clutter. Intelligent management of computation performed by the Search module is a key enabler to scaling the model-based approach to the large hypothesis spaces typical of realistic ATK problems. In this paper, we describe the present state of design and implementation of the MSTAR Search engine, as it has matured over the last three years of the MSTAR program. The evolution has been driven by a continually expanding problem domain that now includes 30 target types, viewed under arbitrary squint/depression, with articulations, reconfigurations, revetments, variable background, and up to 30% blocking occlusion. We believe that the research directions that have been inspired by MSTAR's challenging problem domain are leading to broadly applicable search methodologies that are relevant to computer vision systems in many areas.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages554-570
Number of pages17
Volume3721
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 Algorithms for Synthetic Aperture Radar Imagery VI - Orlando, FL, USA
Duration: Apr 5 1999Apr 9 1999

Other

OtherProceedings of the 1999 Algorithms for Synthetic Aperture Radar Imagery VI
CityOrlando, FL, USA
Period4/5/994/9/99

Fingerprint

target recognition
Search engines
Automatic target recognition
target acquisition
engines
Revetments
Image acquisition
Intelligent control
Processing
Synthetic aperture radar
Computer vision
Radar
radar scattering
Statistics
Scattering
Imaging techniques
Geometry
occlusion
computer vision
clutter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Wissinger, J. W., Ristroph, R., Diemunsch, J., Severson, W., & Freudenthal, E. (1999). MSTAR's extensible search engine and model-based inferencing toolkit. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3721, pp. 554-570). Society of Photo-Optical Instrumentation Engineers.

MSTAR's extensible search engine and model-based inferencing toolkit. / Wissinger, John W; Ristroph, Robert; Diemunsch, Joseph; Severson, William; Freudenthal, Eric.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3721 Society of Photo-Optical Instrumentation Engineers, 1999. p. 554-570.

Research output: Chapter in Book/Report/Conference proceedingChapter

Wissinger, JW, Ristroph, R, Diemunsch, J, Severson, W & Freudenthal, E 1999, MSTAR's extensible search engine and model-based inferencing toolkit. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3721, Society of Photo-Optical Instrumentation Engineers, pp. 554-570, Proceedings of the 1999 Algorithms for Synthetic Aperture Radar Imagery VI, Orlando, FL, USA, 4/5/99.
Wissinger JW, Ristroph R, Diemunsch J, Severson W, Freudenthal E. MSTAR's extensible search engine and model-based inferencing toolkit. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3721. Society of Photo-Optical Instrumentation Engineers. 1999. p. 554-570
Wissinger, John W ; Ristroph, Robert ; Diemunsch, Joseph ; Severson, William ; Freudenthal, Eric. / MSTAR's extensible search engine and model-based inferencing toolkit. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3721 Society of Photo-Optical Instrumentation Engineers, 1999. pp. 554-570
@inbook{3cbc35ee0ffd43d69cfbb6f52ce0df54,
title = "MSTAR's extensible search engine and model-based inferencing toolkit",
abstract = "The DARPA/AFRL `Moving and Stationary Target Acquisition and Recognition' (MSTAR) program is developing a model-based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The motivation for this work is to develop a high performance ATR capability that can identify ground targets in highly unconstrained imaging scenarios that include variable image acquisition geometry, arbitrary target pose and configuration state, differences in target deployment situation, and strong intra-class variations. The MSTAR approach utilizes radar scattering models in an on-line hypothesize-and-test operation that compares predicted target signature statistics with features extracted from image data in an attempt to determine a `best fit' explanation of the observed image. Central to this processing paradigm is the Search algorithm, which provides intelligent control in selecting features to measure and hypotheses to test, as well as in making the decision about when to stop processing and report a specific target type or clutter. Intelligent management of computation performed by the Search module is a key enabler to scaling the model-based approach to the large hypothesis spaces typical of realistic ATK problems. In this paper, we describe the present state of design and implementation of the MSTAR Search engine, as it has matured over the last three years of the MSTAR program. The evolution has been driven by a continually expanding problem domain that now includes 30 target types, viewed under arbitrary squint/depression, with articulations, reconfigurations, revetments, variable background, and up to 30{\%} blocking occlusion. We believe that the research directions that have been inspired by MSTAR's challenging problem domain are leading to broadly applicable search methodologies that are relevant to computer vision systems in many areas.",
author = "Wissinger, {John W} and Robert Ristroph and Joseph Diemunsch and William Severson and Eric Freudenthal",
year = "1999",
language = "English (US)",
volume = "3721",
pages = "554--570",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

TY - CHAP

T1 - MSTAR's extensible search engine and model-based inferencing toolkit

AU - Wissinger, John W

AU - Ristroph, Robert

AU - Diemunsch, Joseph

AU - Severson, William

AU - Freudenthal, Eric

PY - 1999

Y1 - 1999

N2 - The DARPA/AFRL `Moving and Stationary Target Acquisition and Recognition' (MSTAR) program is developing a model-based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The motivation for this work is to develop a high performance ATR capability that can identify ground targets in highly unconstrained imaging scenarios that include variable image acquisition geometry, arbitrary target pose and configuration state, differences in target deployment situation, and strong intra-class variations. The MSTAR approach utilizes radar scattering models in an on-line hypothesize-and-test operation that compares predicted target signature statistics with features extracted from image data in an attempt to determine a `best fit' explanation of the observed image. Central to this processing paradigm is the Search algorithm, which provides intelligent control in selecting features to measure and hypotheses to test, as well as in making the decision about when to stop processing and report a specific target type or clutter. Intelligent management of computation performed by the Search module is a key enabler to scaling the model-based approach to the large hypothesis spaces typical of realistic ATK problems. In this paper, we describe the present state of design and implementation of the MSTAR Search engine, as it has matured over the last three years of the MSTAR program. The evolution has been driven by a continually expanding problem domain that now includes 30 target types, viewed under arbitrary squint/depression, with articulations, reconfigurations, revetments, variable background, and up to 30% blocking occlusion. We believe that the research directions that have been inspired by MSTAR's challenging problem domain are leading to broadly applicable search methodologies that are relevant to computer vision systems in many areas.

AB - The DARPA/AFRL `Moving and Stationary Target Acquisition and Recognition' (MSTAR) program is developing a model-based vision approach to Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). The motivation for this work is to develop a high performance ATR capability that can identify ground targets in highly unconstrained imaging scenarios that include variable image acquisition geometry, arbitrary target pose and configuration state, differences in target deployment situation, and strong intra-class variations. The MSTAR approach utilizes radar scattering models in an on-line hypothesize-and-test operation that compares predicted target signature statistics with features extracted from image data in an attempt to determine a `best fit' explanation of the observed image. Central to this processing paradigm is the Search algorithm, which provides intelligent control in selecting features to measure and hypotheses to test, as well as in making the decision about when to stop processing and report a specific target type or clutter. Intelligent management of computation performed by the Search module is a key enabler to scaling the model-based approach to the large hypothesis spaces typical of realistic ATK problems. In this paper, we describe the present state of design and implementation of the MSTAR Search engine, as it has matured over the last three years of the MSTAR program. The evolution has been driven by a continually expanding problem domain that now includes 30 target types, viewed under arbitrary squint/depression, with articulations, reconfigurations, revetments, variable background, and up to 30% blocking occlusion. We believe that the research directions that have been inspired by MSTAR's challenging problem domain are leading to broadly applicable search methodologies that are relevant to computer vision systems in many areas.

UR - http://www.scopus.com/inward/record.url?scp=0032671355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032671355&partnerID=8YFLogxK

M3 - Chapter

VL - 3721

SP - 554

EP - 570

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

ER -