Modeling of target shadows for SAR image classification

Scott Papson, Ram Mohan Narayanan

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

12 Citations (Scopus)

Abstract

A recent thrust of non-cooperative target recognition (NCTR) using synthetic aperture radar (SAR) has been to complement the extraction of scattering centers by incorporating information contained in the target shadow. When classifying targets based on the shadow region alone, it is essential that an image be well clustered into its respective shadow, highlight, and background regions. To obtain the segmentation, the intensity and spatial location of a pixel are modeled as a mixture of Gaussian distributions. Expectation- maximization (EM) is used to obtain the corresponding distributions for the three regions within a given image. Anisotropic smoothing is applied to smooth the input image as well as the posterior probabilities. A representation of the shadow boundary is developed in conjunction with a Hidden Markov Model (HMM) ensemble to obtain target classification. A variety of targets from the MSTAR database are used to test the performance of both the segmentation algorithm and classification structure.

Original languageEnglish (US)
Title of host publication35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006
DOIs
StatePublished - 2006
Event35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006 - Washington, DC, United States
Duration: Oct 11 2006Oct 13 2006

Other

Other35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006
CountryUnited States
CityWashington, DC
Period10/11/0610/13/06

Fingerprint

Image classification
Synthetic aperture radar
Gaussian distribution
Hidden Markov models
Pixels
Scattering

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Papson, S., & Narayanan, R. M. (2006). Modeling of target shadows for SAR image classification. In 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006 [4133945] https://doi.org/10.1109/AIPR.2006.27
Papson, Scott ; Narayanan, Ram Mohan. / Modeling of target shadows for SAR image classification. 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006. 2006.
@inproceedings{dcb8bd6e4e914c259b3085134f513e81,
title = "Modeling of target shadows for SAR image classification",
abstract = "A recent thrust of non-cooperative target recognition (NCTR) using synthetic aperture radar (SAR) has been to complement the extraction of scattering centers by incorporating information contained in the target shadow. When classifying targets based on the shadow region alone, it is essential that an image be well clustered into its respective shadow, highlight, and background regions. To obtain the segmentation, the intensity and spatial location of a pixel are modeled as a mixture of Gaussian distributions. Expectation- maximization (EM) is used to obtain the corresponding distributions for the three regions within a given image. Anisotropic smoothing is applied to smooth the input image as well as the posterior probabilities. A representation of the shadow boundary is developed in conjunction with a Hidden Markov Model (HMM) ensemble to obtain target classification. A variety of targets from the MSTAR database are used to test the performance of both the segmentation algorithm and classification structure.",
author = "Scott Papson and Narayanan, {Ram Mohan}",
year = "2006",
doi = "10.1109/AIPR.2006.27",
language = "English (US)",
isbn = "0769527396",
booktitle = "35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006",

}

Papson, S & Narayanan, RM 2006, Modeling of target shadows for SAR image classification. in 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006., 4133945, 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006, Washington, DC, United States, 10/11/06. https://doi.org/10.1109/AIPR.2006.27

Modeling of target shadows for SAR image classification. / Papson, Scott; Narayanan, Ram Mohan.

35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006. 2006. 4133945.

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

TY - GEN

T1 - Modeling of target shadows for SAR image classification

AU - Papson, Scott

AU - Narayanan, Ram Mohan

PY - 2006

Y1 - 2006

N2 - A recent thrust of non-cooperative target recognition (NCTR) using synthetic aperture radar (SAR) has been to complement the extraction of scattering centers by incorporating information contained in the target shadow. When classifying targets based on the shadow region alone, it is essential that an image be well clustered into its respective shadow, highlight, and background regions. To obtain the segmentation, the intensity and spatial location of a pixel are modeled as a mixture of Gaussian distributions. Expectation- maximization (EM) is used to obtain the corresponding distributions for the three regions within a given image. Anisotropic smoothing is applied to smooth the input image as well as the posterior probabilities. A representation of the shadow boundary is developed in conjunction with a Hidden Markov Model (HMM) ensemble to obtain target classification. A variety of targets from the MSTAR database are used to test the performance of both the segmentation algorithm and classification structure.

AB - A recent thrust of non-cooperative target recognition (NCTR) using synthetic aperture radar (SAR) has been to complement the extraction of scattering centers by incorporating information contained in the target shadow. When classifying targets based on the shadow region alone, it is essential that an image be well clustered into its respective shadow, highlight, and background regions. To obtain the segmentation, the intensity and spatial location of a pixel are modeled as a mixture of Gaussian distributions. Expectation- maximization (EM) is used to obtain the corresponding distributions for the three regions within a given image. Anisotropic smoothing is applied to smooth the input image as well as the posterior probabilities. A representation of the shadow boundary is developed in conjunction with a Hidden Markov Model (HMM) ensemble to obtain target classification. A variety of targets from the MSTAR database are used to test the performance of both the segmentation algorithm and classification structure.

UR - http://www.scopus.com/inward/record.url?scp=48649109267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48649109267&partnerID=8YFLogxK

U2 - 10.1109/AIPR.2006.27

DO - 10.1109/AIPR.2006.27

M3 - Conference contribution

SN - 0769527396

SN - 9780769527390

BT - 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006

ER -

Papson S, Narayanan RM. Modeling of target shadows for SAR image classification. In 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006. 2006. 4133945 https://doi.org/10.1109/AIPR.2006.27