Traffic Abnormality Detection through Directional Motion Behavior Map

Automatic traffic abnormality detection through visual surveillance is one of the critical requirements for Intelligent Transportation Systems (ITS). In this paper, we present a novel algorithm to detect abnormal traffic events in crowded scenes. Our algorithm can be deployed with few setup steps to automatically monitor traffic status. Different from other approaches, we don't need to define region of interests (ROI) or tripwires nor to configure object detection and tracking parameters. A novel object behavior descriptor directional motion behavior descriptors are proposed. The directional motion behavior descriptors collect foreground objects' direction and speed information from a video sequence with normal traffic events, and then these descriptors are accumulated to generate a directional motion behavior map which models the normal traffic status. During detection steps, we first extract the directional motion behavior map from the newly observed video and then measure the differences between the normal behavior map and the new map. If new direction motion behaviors are very different from the descriptors in the normal behavior map, then the corresponding regions in the observed video contain traffic abnormalities. Our proposed algorithm has been tested using both synthesized and real surveillance videos. Experimental results demonstrated that our algorithm is effective and efficient for practical real-time traffic surveillance applications.