Classification via the shadow region in SAR imagery

Scott Papson, Ram M. Narayanan

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

The use of a target's shadow in synthetic aperture radar (SAR) imaging has garnered much attention for automated target recognition (ATR) applications. A technique of hidden Markov modeling (HMM) of the shadow profile is developed here. The basic HMM technique is refined using ensemble averaging, mission-based model selection criteria, multi-look scenarios, and data fusion. The algorithms are tested using DARPA's moving and stationary target acquisition and recognition (MSTAR) data. One of the drawbacks of using SAR shadows is that there exist certain, yet limited, target-radar configurations where the shadow simply does not robustly provide discriminatory target information. This limitation, however, can be easily overcome by imaging a target at multiple poses. With two orthogonal looks, the shadow-only classifier was seen to have an average classification performance of over 90% for a five target system. Additionally, the output of the shadow-only classifier is illustrated to be independent of a scattering center based classifier. All of the results indicate that the shadows provide useful discriminatory information that can be used to advance recognition capabilities in SAR ATR applications.

Original languageEnglish (US)
Article number6178042
Pages (from-to)969-980
Number of pages12
JournalIEEE Transactions on Aerospace and Electronic Systems
Volume48
Issue number2
DOIs
StatePublished - Apr 1 2012

Fingerprint

Synthetic aperture radar
Classifiers
Radar imaging
Data fusion
Radar
Scattering
Imaging techniques

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Electrical and Electronic Engineering

Cite this

@article{e63c374642104ddda85f20de8243272c,
title = "Classification via the shadow region in SAR imagery",
abstract = "The use of a target's shadow in synthetic aperture radar (SAR) imaging has garnered much attention for automated target recognition (ATR) applications. A technique of hidden Markov modeling (HMM) of the shadow profile is developed here. The basic HMM technique is refined using ensemble averaging, mission-based model selection criteria, multi-look scenarios, and data fusion. The algorithms are tested using DARPA's moving and stationary target acquisition and recognition (MSTAR) data. One of the drawbacks of using SAR shadows is that there exist certain, yet limited, target-radar configurations where the shadow simply does not robustly provide discriminatory target information. This limitation, however, can be easily overcome by imaging a target at multiple poses. With two orthogonal looks, the shadow-only classifier was seen to have an average classification performance of over 90{\%} for a five target system. Additionally, the output of the shadow-only classifier is illustrated to be independent of a scattering center based classifier. All of the results indicate that the shadows provide useful discriminatory information that can be used to advance recognition capabilities in SAR ATR applications.",
author = "Scott Papson and Narayanan, {Ram M.}",
year = "2012",
month = "4",
day = "1",
doi = "10.1109/TAES.2012.6178042",
language = "English (US)",
volume = "48",
pages = "969--980",
journal = "IEEE Transactions on Aerospace and Electronic Systems",
issn = "0018-9251",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Classification via the shadow region in SAR imagery. / Papson, Scott; Narayanan, Ram M.

In: IEEE Transactions on Aerospace and Electronic Systems, Vol. 48, No. 2, 6178042, 01.04.2012, p. 969-980.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification via the shadow region in SAR imagery

AU - Papson, Scott

AU - Narayanan, Ram M.

PY - 2012/4/1

Y1 - 2012/4/1

N2 - The use of a target's shadow in synthetic aperture radar (SAR) imaging has garnered much attention for automated target recognition (ATR) applications. A technique of hidden Markov modeling (HMM) of the shadow profile is developed here. The basic HMM technique is refined using ensemble averaging, mission-based model selection criteria, multi-look scenarios, and data fusion. The algorithms are tested using DARPA's moving and stationary target acquisition and recognition (MSTAR) data. One of the drawbacks of using SAR shadows is that there exist certain, yet limited, target-radar configurations where the shadow simply does not robustly provide discriminatory target information. This limitation, however, can be easily overcome by imaging a target at multiple poses. With two orthogonal looks, the shadow-only classifier was seen to have an average classification performance of over 90% for a five target system. Additionally, the output of the shadow-only classifier is illustrated to be independent of a scattering center based classifier. All of the results indicate that the shadows provide useful discriminatory information that can be used to advance recognition capabilities in SAR ATR applications.

AB - The use of a target's shadow in synthetic aperture radar (SAR) imaging has garnered much attention for automated target recognition (ATR) applications. A technique of hidden Markov modeling (HMM) of the shadow profile is developed here. The basic HMM technique is refined using ensemble averaging, mission-based model selection criteria, multi-look scenarios, and data fusion. The algorithms are tested using DARPA's moving and stationary target acquisition and recognition (MSTAR) data. One of the drawbacks of using SAR shadows is that there exist certain, yet limited, target-radar configurations where the shadow simply does not robustly provide discriminatory target information. This limitation, however, can be easily overcome by imaging a target at multiple poses. With two orthogonal looks, the shadow-only classifier was seen to have an average classification performance of over 90% for a five target system. Additionally, the output of the shadow-only classifier is illustrated to be independent of a scattering center based classifier. All of the results indicate that the shadows provide useful discriminatory information that can be used to advance recognition capabilities in SAR ATR applications.

UR - http://www.scopus.com/inward/record.url?scp=84859830841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859830841&partnerID=8YFLogxK

U2 - 10.1109/TAES.2012.6178042

DO - 10.1109/TAES.2012.6178042

M3 - Article

AN - SCOPUS:84859830841

VL - 48

SP - 969

EP - 980

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

SN - 0018-9251

IS - 2

M1 - 6178042

ER -