Motion-based unusual event detection in human crowds

Analyzing human crowds is an important issue in video surveillance and is a challenging task due to their nature of non-rigid shapes. In this paper, optical flows are first estimated and then used for a clue to cluster human crowds into groups in unsupervised manner using our proposed method of adjacency-matrix based clustering (AMC). While the clusters of human crowds are obtained, their behaviors with attributes, orientation, position and crowd size, are characterized by a model of force field. Finally, we can predict the behaviors of human crowds based on the model and then detect if any anomalies of human crowd(s) present in the scene. Experimental results obtained by using extensive dataset show that our system is effective in detecting anomalous events for uncontrolled environment of surveillance videos.

Research highlights
► In this paper, optical flows are first estimated and then used for a clue to cluster human crowds into groups in an unsupervised manner.
► While the clusters of human crowds are obtained, their behaviors are characterized by a force field model.
► Experimental results show that our approach is competitive when comparing with the state-of-the-art approaches.