Real-Time and Robust System for Counting Movement-Specific Vehicle at Crowded Intersections

Vu-Hoang Tran, Le-Hoai-Hieu Dang, Chinh-Nghiep Nguyen, Ngoc-Hoang-Lam Le, Khanh-Phong Bui, Lam-Truong Dam, Quang-Thang Le, Dinh-Hiep Huynh; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 4228-4235

In order to reduce traffic congestion and improve the efficiency of traffic light signals, intelligent traffic systems are being developed by researchers, and vehicle counting is one of the key techniques in the system. The traditional methods mostly focus on increasing the vehicle counting effectiveness without regard to the program execution efficiency. The practical value of these systems will be reduced if they cannot be operated in real-time on compact IoT device. Therefore, in this paper, we mainly focus on designing a real-time and robust system for the problem of counting specific-movement vehicles. The system is able to detect and track objects in the area of interest, then count those tracked trajectories using the movements. To improve performance of tracking multiple objects, a high recall detection method and an efficient feature matching strategy were proposed. Moreover, to minimize the wrong direction of movement prediction and improve the results of vehicle counting, a cosine similarity-based vehicle counting scheme is applied. Experiments are conducted on AI City 2021 Track-1 dataset. Our method is evaluated on both sides of efficiency and effectiveness.