KEYWORDS: Radar, 3D image processing, 3D acquisition, Feature extraction, Detection and tracking algorithms, Expectation maximization algorithms, Antennas, 3D modeling, Synthetic aperture radar, Data modeling
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.