Occlusion robust vehicle tracking utilizing spatio-temporal Markov Random Field model.

It is very important to achieve reliable vehicle tracking in ITS applications such as accident detection. But the most difficult problem associated with vehicle tracking is the occlusion effect among vehicles. In order to resolve this problem the dedicated algorithm was applied which was defined as Spatio-Temporal Markov Random Field model to traffic images at an intersection. Spatio-Temporal MRF considers texture correlations between consecutive images as well as the correlation among neighbors within an image. This algorithm is generally applicable to traffic image, because it requires only gray scale images and does not assume any physical models of vehicles. This method was applied to 3214 vehicles in 25min 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. But the method was proved to be robust against such random occlusions. For the covering abstract see ITRD E114174.