Skip to main content

Physics-based detection of targets in SAR imagery usingsupport vector machines

Publication ,  Journal Article
Krishnapuram, B; Sichina, J; Carin, L
Published in: IEEE Sensors Journal
April 1, 2003

Radar scattering from an illuminated object is often highly dependent on the target-sensor orientation. In conjunction with physics based feature extraction, the exploitation of aspect-dependent information has led to successful improvements in the detection of tactical targets in synthetic aperture radar (SAR) imagery. While prior work has attempted to design detectors by matching them to images from a training set, the generalization capability of these detectors beyond the training database can be significantly improved by using the principle of structural risk minimization. In this paper, we propose a detector based on support vector machines that explicitly incorporates this principle in its design, yielding improved detection performance. We also introduce a probabilistic feature-parsing scheme that improves the robustness of detection using features obtained from a two-dimensional matching-pursuits feature extractor. Performance is assessed by considering the detection of tactical targets concealed in foliage, using measured foliage-penetrating SAR data.

Duke Scholars

Published In

IEEE Sensors Journal

DOI

ISSN

1530-437X

Publication Date

April 1, 2003

Volume

3

Issue

2

Start / End Page

147 / 157

Related Subject Headings

  • Analytical Chemistry
  • 40 Engineering
  • 0913 Mechanical Engineering
  • 0906 Electrical and Electronic Engineering
  • 0205 Optical Physics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Krishnapuram, B., Sichina, J., & Carin, L. (2003). Physics-based detection of targets in SAR imagery usingsupport vector machines. IEEE Sensors Journal, 3(2), 147–157. https://doi.org/10.1109/JSEN.2002.805552
Krishnapuram, B., J. Sichina, and L. Carin. “Physics-based detection of targets in SAR imagery usingsupport vector machines.” IEEE Sensors Journal 3, no. 2 (April 1, 2003): 147–57. https://doi.org/10.1109/JSEN.2002.805552.
Krishnapuram B, Sichina J, Carin L. Physics-based detection of targets in SAR imagery usingsupport vector machines. IEEE Sensors Journal. 2003 Apr 1;3(2):147–57.
Krishnapuram, B., et al. “Physics-based detection of targets in SAR imagery usingsupport vector machines.” IEEE Sensors Journal, vol. 3, no. 2, Apr. 2003, pp. 147–57. Scopus, doi:10.1109/JSEN.2002.805552.
Krishnapuram B, Sichina J, Carin L. Physics-based detection of targets in SAR imagery usingsupport vector machines. IEEE Sensors Journal. 2003 Apr 1;3(2):147–157.

Published In

IEEE Sensors Journal

DOI

ISSN

1530-437X

Publication Date

April 1, 2003

Volume

3

Issue

2

Start / End Page

147 / 157

Related Subject Headings

  • Analytical Chemistry
  • 40 Engineering
  • 0913 Mechanical Engineering
  • 0906 Electrical and Electronic Engineering
  • 0205 Optical Physics