Model-based SAR ATR system

Katsushi Ikeuchi, Mark D. Wheeler, Taku Yamazaki, Takeshi Shakunaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Recognizing a target in SAR images is an important, yet challenging application of model-based vision. This paper describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. An invariant histogram is a histogram of invariant values defined by geometric features such as points and lines in SAR images. Although a few invariances are sufficient to recognize a target, we histogram all invariant values given by all possible target feature pairs. This redundant representation enables robust recognition under severe occlusions typical of SAR recognition scenarios. Multi-step deformable template matching examines the existence of an object by superimposing templates over potential energy field generated from images or primitive features. It determines the template configuration which has the minimum deformation and the best alignment of the template with features. The deformability of the template absorbs the instability of SAR features. We have implemented the system and evaluated the system performance using hybrid SAR images, generated from synthetic model signatures and real SAR background signatures.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsEdmund G. Zelnio, Robert J. Douglass
Pages376-387
Number of pages12
Volume2757
Publication statusPublished - 1996
Externally publishedYes
EventAlgorithms for Synthetic Aperture Radar Imagery III - Orlando, FL, USA
Duration: Apr 10 1996Apr 12 1996

Other

OtherAlgorithms for Synthetic Aperture Radar Imagery III
CityOrlando, FL, USA
Period4/10/964/12/96

Fingerprint

Template matching
Formability
Potential energy
Invariance

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ikeuchi, K., Wheeler, M. D., Yamazaki, T., & Shakunaga, T. (1996). Model-based SAR ATR system. In E. G. Zelnio, & R. J. Douglass (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2757, pp. 376-387)

Model-based SAR ATR system. / Ikeuchi, Katsushi; Wheeler, Mark D.; Yamazaki, Taku; Shakunaga, Takeshi.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Edmund G. Zelnio; Robert J. Douglass. Vol. 2757 1996. p. 376-387.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ikeuchi, K, Wheeler, MD, Yamazaki, T & Shakunaga, T 1996, Model-based SAR ATR system. in EG Zelnio & RJ Douglass (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 2757, pp. 376-387, Algorithms for Synthetic Aperture Radar Imagery III, Orlando, FL, USA, 4/10/96.
Ikeuchi K, Wheeler MD, Yamazaki T, Shakunaga T. Model-based SAR ATR system. In Zelnio EG, Douglass RJ, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2757. 1996. p. 376-387
Ikeuchi, Katsushi ; Wheeler, Mark D. ; Yamazaki, Taku ; Shakunaga, Takeshi. / Model-based SAR ATR system. Proceedings of SPIE - The International Society for Optical Engineering. editor / Edmund G. Zelnio ; Robert J. Douglass. Vol. 2757 1996. pp. 376-387
@inproceedings{1aecb73cdf0c42edb4d92fe5676871f9,
title = "Model-based SAR ATR system",
abstract = "Recognizing a target in SAR images is an important, yet challenging application of model-based vision. This paper describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. An invariant histogram is a histogram of invariant values defined by geometric features such as points and lines in SAR images. Although a few invariances are sufficient to recognize a target, we histogram all invariant values given by all possible target feature pairs. This redundant representation enables robust recognition under severe occlusions typical of SAR recognition scenarios. Multi-step deformable template matching examines the existence of an object by superimposing templates over potential energy field generated from images or primitive features. It determines the template configuration which has the minimum deformation and the best alignment of the template with features. The deformability of the template absorbs the instability of SAR features. We have implemented the system and evaluated the system performance using hybrid SAR images, generated from synthetic model signatures and real SAR background signatures.",
author = "Katsushi Ikeuchi and Wheeler, {Mark D.} and Taku Yamazaki and Takeshi Shakunaga",
year = "1996",
language = "English",
isbn = "0819421383",
volume = "2757",
pages = "376--387",
editor = "Zelnio, {Edmund G.} and Douglass, {Robert J.}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Model-based SAR ATR system

AU - Ikeuchi, Katsushi

AU - Wheeler, Mark D.

AU - Yamazaki, Taku

AU - Shakunaga, Takeshi

PY - 1996

Y1 - 1996

N2 - Recognizing a target in SAR images is an important, yet challenging application of model-based vision. This paper describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. An invariant histogram is a histogram of invariant values defined by geometric features such as points and lines in SAR images. Although a few invariances are sufficient to recognize a target, we histogram all invariant values given by all possible target feature pairs. This redundant representation enables robust recognition under severe occlusions typical of SAR recognition scenarios. Multi-step deformable template matching examines the existence of an object by superimposing templates over potential energy field generated from images or primitive features. It determines the template configuration which has the minimum deformation and the best alignment of the template with features. The deformability of the template absorbs the instability of SAR features. We have implemented the system and evaluated the system performance using hybrid SAR images, generated from synthetic model signatures and real SAR background signatures.

AB - Recognizing a target in SAR images is an important, yet challenging application of model-based vision. This paper describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. An invariant histogram is a histogram of invariant values defined by geometric features such as points and lines in SAR images. Although a few invariances are sufficient to recognize a target, we histogram all invariant values given by all possible target feature pairs. This redundant representation enables robust recognition under severe occlusions typical of SAR recognition scenarios. Multi-step deformable template matching examines the existence of an object by superimposing templates over potential energy field generated from images or primitive features. It determines the template configuration which has the minimum deformation and the best alignment of the template with features. The deformability of the template absorbs the instability of SAR features. We have implemented the system and evaluated the system performance using hybrid SAR images, generated from synthetic model signatures and real SAR background signatures.

UR - http://www.scopus.com/inward/record.url?scp=0029765649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029765649&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029765649

SN - 0819421383

SN - 9780819421388

VL - 2757

SP - 376

EP - 387

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

A2 - Zelnio, Edmund G.

A2 - Douglass, Robert J.

ER -