Segmentation-based detection of targets in foliage penetrating SAR images

Amit Banerjee, Philippe Burlina

Research output: Contribution to journalConference articlepeer-review


Segmentation and labeling algorithms for foliage penetrating (FOPEN) ultra-wideband Synthetic Aperture Radar (UWB SAR) images are critical components in providing local context in automatic target recognition algorithms. We develop a statistical estimation-theoretic approach to segmenting and labeling the FOPEN images into foliage and non-foliage regions. The labeled maps enable the use of region-adaptive detectors, such as a constant false-alarm rate detector with region-dependent parameters. Segmentation of the images is achieved by performing a maximum a posteriori (MAP) estimate of the pixel labels. By modeling the conditional distribution with a Symmetric Alpha-Stable density and assuming a Markov random field model for the pixel labels, the resulting posterior probability density function is maximized by using simulated annealing to yield the MAP estimate.

Original languageEnglish (US)
Pages (from-to)143-152
Number of pages10
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - Dec 1 1997
EventRadar Sensor Technology II - Orlando, FL, United States
Duration: Apr 24 1997Apr 24 1997


  • ATR
  • Focus of Attention
  • Foliage penetrating SAR
  • MAP segmentation
  • Region-adaptive CFAR

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Segmentation-based detection of targets in foliage penetrating SAR images'. Together they form a unique fingerprint.

Cite this