SAR ATR performance using a conditionally Gaussian model

J. A. O'sullivan; M. D. DeVore; V. Kedia; M. I. Miller

doi:10.1109/7.913670

SAR ATR performance using a conditionally Gaussian model

J. A. O'sullivan
, M. D. DeVore
, V. Kedia
, M. I. Miller

Research output: Contribution to journal › Article › peer-review

182 Scopus citations

Abstract

A family of conditionally Gaussian signal models for synthetic aperture radar (SAR) imagery is presented, extending a related class of models developed for high resolution radar range profiles. This signal model is robust with respect to the variations of the complex-valued radar signals due to the coherent combination of returns from scatterers as those scatterers move through relative distances on the order of a wavelength of the transmitted signal (target speckle). The target type and the relative orientations of the sensor, target, and ground plane parameterize the conditionally Gaussian model. Based upon this model, algorithms to jointly estimate both the target type and pose are developed. Performance results for both target pose estimation and target recognition are presented for publicly released data from the MSTAR program.

Original language	English
Pages (from-to)	91-108
Number of pages	18
Journal	IEEE Transactions on Aerospace and Electronic Systems
Volume	37
Issue number	1
DOIs	https://doi.org/10.1109/7.913670
State	Published - Jan 2001

Access to Document

10.1109/7.913670

Cite this

@article{4a38051e7f0d40cc9b6b9f6446684996,

title = "SAR ATR performance using a conditionally Gaussian model",

abstract = "A family of conditionally Gaussian signal models for synthetic aperture radar (SAR) imagery is presented, extending a related class of models developed for high resolution radar range profiles. This signal model is robust with respect to the variations of the complex-valued radar signals due to the coherent combination of returns from scatterers as those scatterers move through relative distances on the order of a wavelength of the transmitted signal (target speckle). The target type and the relative orientations of the sensor, target, and ground plane parameterize the conditionally Gaussian model. Based upon this model, algorithms to jointly estimate both the target type and pose are developed. Performance results for both target pose estimation and target recognition are presented for publicly released data from the MSTAR program.",

author = "O'sullivan, \{J. A.\} and DeVore, \{M. D.\} and V. Kedia and Miller, \{M. I.\}",

year = "2001",

month = jan,

doi = "10.1109/7.913670",

language = "English",

volume = "37",

pages = "91--108",

journal = "IEEE Transactions on Aerospace and Electronic Systems",

issn = "0018-9251",

number = "1",

}

TY - JOUR

T1 - SAR ATR performance using a conditionally Gaussian model

AU - O'sullivan, J. A.

AU - DeVore, M. D.

AU - Kedia, V.

AU - Miller, M. I.

PY - 2001/1

Y1 - 2001/1

N2 - A family of conditionally Gaussian signal models for synthetic aperture radar (SAR) imagery is presented, extending a related class of models developed for high resolution radar range profiles. This signal model is robust with respect to the variations of the complex-valued radar signals due to the coherent combination of returns from scatterers as those scatterers move through relative distances on the order of a wavelength of the transmitted signal (target speckle). The target type and the relative orientations of the sensor, target, and ground plane parameterize the conditionally Gaussian model. Based upon this model, algorithms to jointly estimate both the target type and pose are developed. Performance results for both target pose estimation and target recognition are presented for publicly released data from the MSTAR program.

AB - A family of conditionally Gaussian signal models for synthetic aperture radar (SAR) imagery is presented, extending a related class of models developed for high resolution radar range profiles. This signal model is robust with respect to the variations of the complex-valued radar signals due to the coherent combination of returns from scatterers as those scatterers move through relative distances on the order of a wavelength of the transmitted signal (target speckle). The target type and the relative orientations of the sensor, target, and ground plane parameterize the conditionally Gaussian model. Based upon this model, algorithms to jointly estimate both the target type and pose are developed. Performance results for both target pose estimation and target recognition are presented for publicly released data from the MSTAR program.

UR - https://www.scopus.com/pages/publications/0035040063

U2 - 10.1109/7.913670

DO - 10.1109/7.913670

M3 - Article

AN - SCOPUS:0035040063

SN - 0018-9251

VL - 37

SP - 91

EP - 108

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

IS - 1

ER -

SAR ATR performance using a conditionally Gaussian model

Abstract

Access to Document

Other files and links

Fingerprint

Cite this