Share Email Print

Proceedings Paper

Unsupervised SAR image segmentation using recursive partitioning
Author(s): Vidya Venkatachalam; Robert D. Nowak; Richard G. Baraniuk; Mario A. T. Figueiredo
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a new approach to SAR image segmentation based on a Poisson approximation to the SAR amplitude image. It has been established that SAR amplitude images are well approximated using Rayleigh distributions. We show that, with suitable modifications, we can model piecewise homogeneous regions (such as tanks, roads, scrub, etc.) within the SAR amplitude image using a Poisson model that bears a known relation to the underlying Rayleigh distribution. We use the Poisson model to generate an efficient tree-based segmentation algorithm guided by the minimum description length (MDL) criteria. We present a simple fixed tree approach, and a more flexible adaptive recursive partitioning scheme. The segmentation is unsupervised, requiring no prior training, and very simple, efficient, and effective for identifying possible regions of interest (targets). We present simulation results on MSTAR clutter data to demonstrate the performance obtained with this parsing technique.

Paper Details

Date Published: 24 August 2000
PDF: 9 pages
Proc. SPIE 4053, Algorithms for Synthetic Aperture Radar Imagery VII, (24 August 2000); doi: 10.1117/12.396323
Show Author Affiliations
Vidya Venkatachalam, Rice Univ. (United States)
Robert D. Nowak, Rice Univ. (United States)
Richard G. Baraniuk, Rice Univ. (United States)
Mario A. T. Figueiredo, Instituto de Telecomunicacoes and Instituto Superior Tecnico (Portugal)

Published in SPIE Proceedings Vol. 4053:
Algorithms for Synthetic Aperture Radar Imagery VII
Edmund G. Zelnio, Editor(s)

© SPIE. Terms of Use
Back to Top