A color texture based visual monitoring system for automated surveillance

Abstract

A complete visual monitoring system that performs segmentation and classification based on color and texture information is presented. Color information is combined with texture and corresponding segmentation and classification algorithms are developed. Emphasis is given to the segmentation part of the proposed system whose function is to detect and measure changes (loss/gain) that occur in a given environment over a period of time. The xyY color space is used. The two chromaticity coordinates are combined into one, thus, providing the chrominance (spectral) part of the image, while Y describes the luminance (intensity) image information. The proposed color texture segmentation system processes luminance and chrominance separately. Luminance is processed in four stages: filtering/smoothing, similarities computation, and boundary detection. Chrominance processing is performed in two stages: histogram multithresholding and region growing. Two or more images may be combined at the end in order to detect possible changes, where the exclusive-OR (XOR) operator is utilized. Results in both the xyY and HIS color spaces are presented.