Crowd behavior analysis under cameras network fusion using probabilistic methods

The use of cameras in surveillance is increasing in the last years due to the low cost of the sensor and the requirement by surveillance in public places. However, the manual analysis of this data is impracticable. Thus, automatic and robust methods to processing this high quantity of data are required. This paper proposes a framework to address this problem. The crowd analysis is achieved in camera networks information by using the optical flow. The Hidden Markov models and Bayesian Networks are compared to understand the agents behavior in the scene. The experimental results are obtained for several sequences where fight and robbery occurs. Results are promise in order to get an automatic system to find abnormal events.