Recognition of abnormal behaviors using a cognitive vision approach

F. Bremond

INRIA, Sophia Antipolis, France

‘The ADVISOR behavior recognition system

We present in this work an approach for recognizing the behavior of either isolated individuals, groups of people or crowds 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:

1. Motion detection and frame to frame tracking.
2. Multiple camera combination.
3. 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.

Paper presented at Measuring Behavior 2005 , 5^th International Conference on Methods and Techniques in Behavioral Research, 30 August - 2 September 2005, Wageningen, The Netherlands.

© 2005 Noldus Information Technology bv