Automatic vehicle classification and tracking method for vehicle movements at signalized intersections

This paper presents an automatic vehicle classification and tracking method to estimate the traffic parameters of vehicle movements at signalized intersections. Different from traditional methods, this classification and tracking system is based on a projective transformation of video frames. The proposed method has a good ability to classify detected vehicles and calculate parameters of vehicle movements at intersection area. Experimental results show the proposed method is more accurate and powerful than feature-based detection algorithm to tackle the problem of changing shape and size of vehicles due to turning movements. Based on tracking results, vehicle movements, including turning paths and speed profile are analyzed. The proposed method is a valuable tool for building path and speed control strategy of intelligent vehicles.