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 language | English (US) |
|---|---|
| Title of host publication | 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006 |
| DOIs | |
| State | Published - Dec 1 2006 |
| Event | 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006 - Washington, DC, United States Duration: Oct 11 2006 → Oct 13 2006 |
Publication series
| Name | Proceedings - Applied Imagery Pattern Recognition Workshop |
|---|---|
| ISSN (Print) | 1550-5219 |
Other
| Other | 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006 |
|---|---|
| Country | United States |
| City | Washington, DC |
| Period | 10/11/06 → 10/13/06 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
Cite this
}
Modeling of target shadows for SAR image classification. / Papson, Scott; Narayanan, Ram.
35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006. 2006. 4133945 (Proceedings - Applied Imagery Pattern Recognition Workshop).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Modeling of target shadows for SAR image classification
AU - Papson, Scott
AU - Narayanan, Ram
PY - 2006/12/1
Y1 - 2006/12/1
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
AN - SCOPUS:48649109267
SN - 0769527396
SN - 9780769527390
T3 - Proceedings - Applied Imagery Pattern Recognition Workshop
BT - 35th Applied Imagery and Pattern Recognition Workshop, AIPR 2006
ER -