Texture Feature Selection for Buried Mine Detection in Airborne Multispectral Imagery

In this paper, a methodology for the detection of buried mines in airborne multispectral imagery is explored. The approach is based on utilizing the color texture information in the buried mine signatures, which is extracted using the cross-co-occurrence texture features. A systematic two-stage approach, using Bhattacharya coefficient-based analysis and principal feature analysis, is developed for the selection of a small subset of discriminatory features. Detection results from actual airborne data from two different sites are presented. The performances are compiled for four different feature-based detectors, and are compared with the conventional multiband RX anomaly detector, to validate the feature selection approach and demonstrate buried mine detection performance based on texture features.