Automatic visual recognition for metro surveillance

We propose in this paper an approach for recognizing either isolated individual, group of people or crowd behaviors in the context of visual surveillance of metro scenes using multiple cameras. In this context, a behavior recognition module relies on a vision module composed of three tasks: (a) motion detection and frame to frame tracking, (b) multiple cameras combination and (c) long term tracking of individuals, groups of people and crowd evolving in the scene. For each tracked actor, the behavior recognition module performs three levels of reasoning: states, events and scenarios. We have also defined a general framework to easily combine and tune various recognition methods (e.g. automaton, Bayesian network or AND/OR tree) dedicated to the analysis of specific situations (e.g. mono/multi actors activities, numerical/symbolic actions or temporal scenarios). Validation results on different methods used to recognize specific behaviors are described.