Robust Motion Detection with Color-texture Feature Fuzzy Approach

Motion detection is a fundamental and important part of many visual tracking systems and of other computer vision applications. In this paper, we present a robust and effective motion detection method for detecting foreground moving objects even with quick lighting changes and shadows in scenes. The proposed approach integrates YCbCr color features with texture by a fuzzy method based on Choquet integral.Numerous experiments on complex video sequences show that the proposed approach, compared with GMM method, can achieve better performance.