Crowd event detection in computer vision

One of video surveillance applications is crowd analysis. Video surveillance application uses crowd analysis for automatic detection of anomalies and alarms. Behavior of the crowd attracts many researchers interest because of its complexity and abstract. Several obstacles, such as, occlusion, illumination changes, and any other obstacles that could influence detecting process, also there are some difficulties in analyzing crowd event. This paper is intended to analyze crowd behavior through video surveillance for detecting normal and abnormal pattern. In addition, two basic methods in segmentation from sequence images are compared.