Real time recognition and tracking system of multiple vehicles

This paper proposed a real-time system to recognize and track multiple vehicles. The occlusion problem is solved by the occlusion segmentation method and then each vehicle is recognized according to their outlines and tracked by a tracking algorithm. The proposed recognition method uses the visual length, visual width, roof, windshield, and hood of vehicles to classify the vehicles to vans, utility vehicles, sedans, mini trucks, or large vehicles. Experiments obtained by using complex road scenes are reported, which demonstrate the validity of the method in terms of robustness, accuracy, and time responses.