Fuzzy chromatic co-occurrence matrices for tracking objects

Tracking objects is an important field for many applications like driving assistance and video surveillance. Every tracking system should be able to track objects in complex scenes. One of the most challenging problems is tracking of objects undergoing an occlusion. Indeed, several tracking systems suffer from lack of information to accomplish the tracking task when two or many objects are in occlusion. To address this issue, this paper presents a novel approach combining fuzzy logic with chromatic co-occurrence matrices in order to develop a robust tracking method that is able to determine the target position more accurately during an illumination variation or an occlusion situation. The qualitative and quantitative studies on challenging sequences demonstrate that the results obtained by the proposed algorithm are very competitive in comparison with several state-of-the-art methods.