Vision based vehicle detection and traffic parameter extraction

Various shadows are one of main factors that cause errors in vision based v ehicle detection. In this paper, two simple methods, land mark based method and BS & Edge method, are proposed for vehicle detection and shadow reject ion. In the experiments, the accuracy of vehicle detection is higher than 9 8%, during which the shadows arisen from roadside buildings grew considerab ly. Based on these two methods, vehicle counting, tracking, classification, and speed estimation are achieved so that real-time traffic parameters con cerning traffic flow can be extracted to describe the load of each lane.