Robust and Fast Vehicle Turn-Counts at Intersections via an Integrated Solution From Detection, Tracking and Trajectory Modeling

Zhihui Wang, Bing Bai, Yujun Xie, Tengfei Xing, Bineng Zhong, Qinqin Zhou, Yiping Meng, Bin Xu, Zhichao Song, Pengfei Xu, Runbo Hu, Hua Chai; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 610-611

In this paper, we address the problem of vehicle turn- counts by class at multiple intersections, which is greatly challenged by inaccurate detection and tracking results caused by heavy weather, occlusion, illumination variations, background clutter, etc. Therefore, the complexity of the problem calls for an integrated solution that robustly ex- tracts as much visual information as possible and efficiently combines it through sequential feedback cycles. We pro- pose such an algorithm, which effectively combines detection, background modeling, tracking, trajectory modeling and matching in a sequential manner. Firstly, to improve detection performances, we design a GMM like background modeling method to detect moving objects. Then, the pro- posed GMM like background modeling method is combined with an effective yet efficiency deep learning based detector to achieve high-quality vehicle detection. Based on the detection results, a simple yet effective multi-object tracking method is proposed to generate each vehicle's movement trajectory. Conditioned on each vehicle's trajectory, we then propose a trajectory modeling and matching schema which leverages the direction and speed of a local vehicle's trajectory to improve the robustness and accuracy of vehicle turn-counts. Our method is validated on the AICity Track1 dataset A, and has achieved 91.40% in effectiveness, 95.4% in efficiency, and 92.60% S1-score, respectively. The experimental results show that our method is not only effective and efficient, but also can achieve robust counting performance in real-world scenes.