Lane-Level and Full-Cycle Multivehicle Tracking Using Low-Channel Roadside LiDAR
Hui Liu, Ciyun Lin, Bowen Gong, Hongchao Liu
Abstract
The ability to track multiple objects is crucial for roadside units to provide high-precision, trajectory-based traffic data, especially for connected vehicles that require complementary and long-range traffic information to improve road safety. Occlusion and continuous tracking are major challenges that have hindered the achievement of obtaining accurate, uninterrupted, and consistent multi-object tracking using roadside LiDAR technology. This paper presents a lane-level and full-cycle multi-vehicle tracking (MVT) method that utilizes low-channel roadside LiDAR. Firstly, a lane-level map was created by analyzing multiple frames of traffic object detection results. Then, we introduced an association method based on a search process and a microscopic motion model, while considering the lane-level map as a constraint. The search process aims to identify all previous tracks that might be linked to the target vehicle, while the microscopic motion model ensures finding a correct historical track for association. Additionally, a detection optimization approach utilizing the lane-level map was also proposed to enhance the tracking performance. Lastly, we created a new roadside tracking dataset for experimental studies by using Velodyne VLP-16 LiDAR sensors. The results showed that our algorithm achieved the highest accuracy and the strongest anti-occlusion performance compared to other popular algorithms such as SORT, OC-SORT, and ByteTrack. It is therefore a very suitable method for obtaining complete vehicle tracks using roadside LiDAR technology. The dataset and source code are available at https://github.com/moxigual/LMAT.