Mono versus Multi-view tracking-based model for automatic scene activity modeling and anomaly detection

In this paper, we present a novel method able to automatically discover recurrent activities occurring in a video scene, and to identify the temporal relations between these activities, which can be used either in mono-view or in multi-view context (for example, to discover the different flows of passengers inside a subway station and identify the rules that govern these flows). The proposed method is based on particle-based trajectories, analyzed through a cascade of HMM and HDP-HMM models. We experiment our model for scene activity recognition task on a subway dataset using both mono-view and multi-view analysis. We last show that our model is also able to perform on the fly and in real-time abnormal events detection (by identifying activities or relations that do not fit in the usual/learnt ones).