Radar-Informed 3D Multi-Object Tracking under Adverse Conditions
For autonomous driving systems, this work addresses the problem of tracking robustness in adverse weather and at long distances, where existing multimodal methods degrade.
RadarMOT improves 3D multi-object tracking under adverse conditions by explicitly using radar point clouds to refine state estimation and recover missed objects, achieving 12.7% AMOTA improvement at long range and up to 10.3% in adverse weather on the MAN-TruckScenes dataset.
The challenge of 3D multi-object tracking is achieving robustness in real-world applications, for example under adverse conditions and maintaining consistency as distance increases. To overcome these challenges, sensor fusion approaches that combine LiDAR, cameras, and radar have emerged. However, existing multimodal methods usually treat radar as another learned feature inside the network. When the overall model degrades in difficult environments, the robustness advantages that radar could provide are also reduced. In this paper we propose RadarMOT, a radar-informed 3D multi-object tracking framework that explicitly uses radar point clouds as additional observations to refine state estimation and recover objects missed by the detector at long ranges. Evaluations on the MAN-TruckScenes dataset show that RadarMOT consistently improves the Average Multi-Object Tracking Accuracy (AMOTA) by 12.7\% at long range and up to 10.3\% in adverse weather. The code will be available at https://github.com/bingxue-xu/radarmot