Crowd Behaviors Analysis and Abnormal Detection based on Surveilliance Data

Crowd analysis and abnormal trajectories detection are the hot topics in computer vision and pattern recognition. As more and more video monitoring equipments are installed in public places for public safety and public management, researches become urgent to learn the crowd behavior patterns through the trajectories obtained by the intelligent video surveillance technology. In this paper, the FCM (Fuzzy c-means) algorithm is adopted to cluster the source points and sink points of trajectories that are deemed as critical points into several groups. Naturally, the trajectory clusters can be acquired. After refining them, the feature information statistical histogram for each one which contains the motion information will be built after refining the trajectory clusters with Hausdorff distances. Eventually, the local motion coherence between test trajectories and refined trajectory clusters will be used to judge whether they are abnormal.