Vehicle Counting without Background Modeling

In general, the vision-based methods for vehicle detection/tracking may face the problems of illumination variation, shadows, or swaying trees. In this study, we propose a novel vehicle detection method without background modeling to overcome the aforementioned problems. First, a modified block-based frame differential method is established to quickly detect the moving vehicles without the influences of rapid illumination variations. Second, the precise vehicles’ regions are extracted with the dual foregrounds fusion method. Third, a texture-based object segmentation method is proposed to segment each vehicle from the merged foreground image blob and remove the shadows. Fourth, based on the concept of motion entropy a false foreground filtering method is developed to remove the false object regions caused by the swaying trees or moving clouds. Finally, the texture-based target tracking method is proposed to track each detected target and then apply the virtual-loop detector to compute the traffic flow. Experimental results show that our proposed system can work with the computing rate above 20 fps and the average accuracy of vehicle counting can approach 86%.