Vehicle ’ s Tracking and Recognition Using a Distributed Surveillance System for Urban Traffic Management

This paper proposes an unsupervised vehicle’s tracking and recognition methods for urban Traffic surveillance in a distributed cooperative manner. Vehicle’s matching in a multi-camera surveillance system is a fundamental issue for increasing the accuracy of recognition. In intelligent transportation systems (ITS), especially in field of urban traffic management, intersections monitoring is one of the critical and challenging tasks. In multi-camera traffic surveillance system, videos have different characteristics such as pose, scale and illumination. Therefore it is necessary to use a hybrid scheme of scale invariant feature transform (SIFT) to detection and recognition vehicle’s behavior in multi view more accurately and conveniently. The main focus of this paper is to analyze activities at intersection by a distributed cooperative system for tracking and recognition vehicles to extract traffic flows which assists in regulating traffic lights for using in smart cameras. Extracting the trajectories help to detect abnormal behavior which may be occluded in singlecamera surveillance. Distributed cooperative’s fundamental purpose is to efficiently reduce the transmission rate and also analyze an intersection scene and report statics and information of interest.