Behavior Analysis and Dynamic Crowd Management in Video Surveillance System

A concept and practical implementation of a crowd management system which acquires input data by the set of monitoring cameras is presented. Two leading threads are considered. First concerns the crowd behavior analysis. Second thread focuses on detection of a hold-ups in the doorway. The optical flow combined with soft computing methods (neural network) is employed to evaluate the type of crowd behavior, and fuzzy logic aids detection of the hold-ups. The experiments with the behavior classification algorithm were performed employing prepared repository of typical and untypical behavior recordings. The effectiveness of the analysis was assessed by comparing algorithmic processing results to a set of prepared reference data, which provides a description of behavior type occurring in each video frame. Application of parallel image processing and influence of parallelization on achieved performance is explained. Apart from the crowd management the behavior analysis may be used in automatic surveillance system deployed in a city area.