Invariant histograms and deformable template matching for SAR target recognition

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

Research output: Contribution to conferencePaper

24 Citations (Scopus)

Abstract

Recognizing a target in synthetic-aperture radar (SAR) images is an important, yet challenging, application of the model-based vision technique. 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 invariants are sufficient to recognize a target, we use a histogram of all invariant values given by all possible target feature pairs. This redundant histogram enables robust recognition under severe occlusions typical in 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 synthesized model signatures and real SAR background signatures.

Original languageEnglish
Pages100-105
Number of pages6
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - San Francisco, CA, USA
Duration: Jun 18 1996Jun 20 1996

Other

OtherProceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySan Francisco, CA, USA
Period6/18/966/20/96

Fingerprint

Radar target recognition
Template matching
Synthetic aperture radar
Formability
Potential energy

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Ikeuchi, K., Shakunaga, T., Wheeler, M. D., & Yamazaki, T. (1996). Invariant histograms and deformable template matching for SAR target recognition. 100-105. Paper presented at Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, .

Invariant histograms and deformable template matching for SAR target recognition. / Ikeuchi, Katsushi; Shakunaga, Takeshi; Wheeler, M. D.; Yamazaki, Taku.

1996. 100-105 Paper presented at Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, .

Research output: Contribution to conferencePaper

Ikeuchi, K, Shakunaga, T, Wheeler, MD & Yamazaki, T 1996, 'Invariant histograms and deformable template matching for SAR target recognition' Paper presented at Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 6/18/96 - 6/20/96, pp. 100-105.
Ikeuchi K, Shakunaga T, Wheeler MD, Yamazaki T. Invariant histograms and deformable template matching for SAR target recognition. 1996. Paper presented at Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, .
Ikeuchi, Katsushi ; Shakunaga, Takeshi ; Wheeler, M. D. ; Yamazaki, Taku. / Invariant histograms and deformable template matching for SAR target recognition. Paper presented at Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, .6 p.
@conference{4bb0be958ef84af3bb2de9db8b7723a0,
title = "Invariant histograms and deformable template matching for SAR target recognition",
abstract = "Recognizing a target in synthetic-aperture radar (SAR) images is an important, yet challenging, application of the model-based vision technique. 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 invariants are sufficient to recognize a target, we use a histogram of all invariant values given by all possible target feature pairs. This redundant histogram enables robust recognition under severe occlusions typical in 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 synthesized model signatures and real SAR background signatures.",
author = "Katsushi Ikeuchi and Takeshi Shakunaga and Wheeler, {M. D.} and Taku Yamazaki",
year = "1996",
language = "English",
pages = "100--105",
note = "Proceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 18-06-1996 Through 20-06-1996",

}

TY - CONF

T1 - Invariant histograms and deformable template matching for SAR target recognition

AU - Ikeuchi, Katsushi

AU - Shakunaga, Takeshi

AU - Wheeler, M. D.

AU - Yamazaki, Taku

PY - 1996

Y1 - 1996

N2 - Recognizing a target in synthetic-aperture radar (SAR) images is an important, yet challenging, application of the model-based vision technique. 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 invariants are sufficient to recognize a target, we use a histogram of all invariant values given by all possible target feature pairs. This redundant histogram enables robust recognition under severe occlusions typical in 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 synthesized model signatures and real SAR background signatures.

AB - Recognizing a target in synthetic-aperture radar (SAR) images is an important, yet challenging, application of the model-based vision technique. 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 invariants are sufficient to recognize a target, we use a histogram of all invariant values given by all possible target feature pairs. This redundant histogram enables robust recognition under severe occlusions typical in 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 synthesized model signatures and real SAR background signatures.

UR - http://www.scopus.com/inward/record.url?scp=0029702946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029702946&partnerID=8YFLogxK

M3 - Paper

SP - 100

EP - 105

ER -