Vehicles Behavior Analysis for Abnormality detection by Multi-View Monitoring

This paper proposes an unsupervised abnormality detection method using a distributed video surveillance system in an intersection. Among the most important researches in intelligent transportation systems, especially in field of urban traffic management, automatically intersection flow monitoring is one of the critical and challenging tasks. The main focus of this paper is to analyse activities at intersection in number of traffic zones for detecting and classifying vehicles and then tracking to extract traffic flows which assists in abnormality detection. Traffic zones definition in intersection video, based on trajectories clustering; greatly reduce the time and volume of computations. The proposed work addresses abnormality detection by means of vehicles trajectory analysis based on support vector machine (SVM). In surveillance systems, trajectories analysis helps to extract abnormal behaviours. By using multiple views of cameras, uniform tracking configuration is suited approach to remove occlusion and extract abnormal vehicles behaviour more accurately and can enhances the capability and performance of behaviour analysis.