Occlusion robust vehicle tracking for behavior analysis utilizing spatio-temporal Markov random field model

It is very important to achieve reliable vehicle tracking for the sake of individual behavior analysis of vehicles. But the most difficult problem associated with vehicle tracking is the occlusion effect among vehicles. Such occlusion effects usually occur at intersections and the effects prevent us from individual behavior analysis of vehicles. In order to resolve this problem we applied the dedicated algorithm which we defined as spatio-temporal Markov random field model (MRF) to traffic images at an intersection. Spatio-temporal MRF considers texture correlations between consecutive images as well as the correlation among neighbors within a image. This algorithm is generally applicable to traffic image, because it requires only gray scaled images and does not assume any shape models of vehicles. We applied this method to 3214 vehicles in 25 minute traffic images at an intersection. As a result, the method was able to track separated vehicles that do not cause occlusions at over 99% success rate, and the method was able to segment and track occluded vehicles at about 95% success rate. Because vehicles appear in various kinds of shapes and they move in random manners at the intersection, occlusions occur in such complicated manners. The method was proved to be robust against such random occlusions