Share Email Print

Proceedings Paper

Textural feature selection for enhanced detection of stationary humans in through-the-wall radar imagery
Author(s): A. Chaddad; F. Ahmad; M. G. Amin; P. Sevigny; D. DiFilippo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Feature-based methods have been recently considered in the literature for detection of stationary human targets in through-the-wall radar imagery. Specifically, textural features, such as contrast, correlation, energy, entropy, and homogeneity, have been extracted from gray-level co-occurrence matrices (GLCMs) to aid in discriminating the true targets from multipath ghosts and clutter that closely mimic the target in size and intensity. In this paper, we address the task of feature selection to identify the relevant subset of features in the GLCM domain, while discarding those that are either redundant or confusing, thereby improving the performance of feature-based scheme to distinguish between targets and ghosts/clutter. We apply a Decision Tree algorithm to find the optimal combination of co-occurrence based textural features for the problem at hand. We employ a K-Nearest Neighbor classifier to evaluate the performance of the optimal textural feature based scheme in terms of its target and ghost/clutter discrimination capability and use real-data collected with the vehicle-borne multi-channel through-the-wall radar imaging system by Defence Research and Development Canada. For the specific data analyzed, it is shown that the identified dominant features yield a higher classification accuracy, with lower number of false alarms and missed detections, compared to the full GLCM based feature set.

Paper Details

Date Published: 29 May 2014
PDF: 8 pages
Proc. SPIE 9077, Radar Sensor Technology XVIII, 90770F (29 May 2014); doi: 10.1117/12.2049416
Show Author Affiliations
A. Chaddad, Villanova Univ. (United States)
F. Ahmad, Villanova Univ. (United States)
M. G. Amin, Villanova Univ. (United States)
P. Sevigny, Defence Research and Development Canada (Canada)
D. DiFilippo, Defence Research and Development Canada (Canada)

Published in SPIE Proceedings Vol. 9077:
Radar Sensor Technology XVIII
Kenneth I. Ranney; Armin Doerry, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?