Traffic data collected at intersections are essential information for traffic signal operations, traffic control, and intersection design and planning. Compared with highway traffic detections, traffic surveillance at intersections has more challenges due to the variety of road users and weaving caused by traffic conflicts. One of these problems is the detection failure of stopping road users. The other challenge is to track objects during occlusion caused by traffic conflicts. In this study, a real time video surveillance system is developed to detect, track and classify road users at intersections. At first, an improved Gaussian Mixture Model (GMM) is utilized to detect road users, including temporary stopping objects due to traffic conflicts. Then, a motion estimation approach is used to get the trajectories of road users. Finally, the Back Propagation Neural Network (BPNN) is employed to classify pedestrians, bicycles, and vehicles. Experimental results show that the proposed traffic surveillance system is effective and successful for road user detection, tracking and identification at intersections.