An Image Tracking Method Based on Color Co-Occurrence Histograms

Aiming at the result of Mean-Shift tracking method is not satisfactory when color of the target is similar to the back ground or another similar object is close to the target, a real- time target tracking method combined with Mean shift and color co-occurrence histograms (CCH) was proposed in this paper. The method used CCH to represent target model of the Mean-Shift. And then the Mean-Shift was used to locate the target position. Moreover, the studied model updating strategy based on multi-scale CCH and the similarity measure of Bhattacharyya value is constructed in the method. Experiments in the complex environment were done. The results show that the proposed method has more accurate target locating and better robustness than the traditional Mean-Shift.