Gaussian Mixture Modeling Approach for Stationary Human Identification in Through-the-Wall Radar Imagery

PDF

Authors
  1. Sévigny, P.
  2. Kilaru, V.
  3. Amin, M.
  4. Ahmad, F.
  5. Sévigny, P.
  6. DiFilippo, D.
Corporate Authors
Defence Research and Development Canada, Ottawa Research Centre, Ottawa ON (CAN)
Abstract
We propose a Gaussian mixture model (GMM)-based approach to discriminate stationary humans from their ghosts and clutter in through-the-wall radar images. More specifically, we use a mixture of Gaussian distributions to model the image intensity histograms corresponding to target and ghost/clutter regions. The mixture parameters, namely the means, variances, and weights of the component distributions, are used as features and a K-nearest neighbor classifier is employed. The performance of the proposed method is evaluated using real-data measurements of multiple humans standing or sitting at different locations in a small room. Experimental results show that the nature of the targets and ghosts/clutter in the image allows successful application of the GMM feature-based classifier to distinguish between target and ghost/clutter regions.
Keywords
target classification;clutter;GMM;through-the-wall rada
Report Number
DRDC-RDDC-2015-P005 — External Literature
Date of publication
17 Feb 2015
Number of Pages
12
DSTKIM No
CA040904
CANDIS No
802004
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: