Segmentations of through-the-wall radar images

Authors

C H. Seng, University of WollongongFollow
M G. Amin, Villanova UniversityFollow
F Ahmad, Villanova University
A Bouzerdoum, University of WollongongFollow

RIS ID

62395

Publication Details

C. H. Seng, M. G. Amin, F. Ahmad & A. Bouzerdoum, "Segmentations of through-the-wall radar images," in 2012 IEEE Radar Conference: Ubiquitous Radar, RADARCON 2012, 2012, pp. 647-652.

Abstract

In this paper, we examine the use of image segmentation approaches for target detection in TWRI. The betweenclass variance thresholding, entropy-based segmentation, and Kmeans clustering are applied to segment target and clutter regions. Real 2D polarimetric images are used to demonstrate that simple histogram-based segmentation methods produce either comparable or improved performance over the Likelihood Ratio Tests (LRT) detector. Specifically, the results show that, for the cases considered, the entropy-based segmentation outperforms the other image segmentation methods and the LRT detector.