RobMOT: 3D Multi-Object Tracking Enhancement Through Observational Noise and State Estimation Drift Mitigation in LiDAR Point Clouds

This paper addresses key limitations in recent 3D tracking-by-detection methods, focusing on the challenges of identifying legitimate trajectories and mitigating state estimation drift in the Kalman filter. Current methods rely heavily on threshold-based detection score filtering approaches to reduce false positives and prevent ghost trajectories. However, these approaches fail for distant and partially occluded objects, where detection scores drop, and false positives surpass that threshold. Additionally, many existing methods assume that detections provide precise localization, overlooking the inherent noise that affects localization accuracy and causes state drift for occluded objects, as demonstrated in this work. To this end, a novel track validity mechanism, combined with a multi-stage observational gating process, is proposed that significantly reduces ghost tracks and improves tracking performance. Our method achieves 29.47% enhancement in Multi-Object tracking accuracy (MOTA) on the KITTI validation dataset with the Second detector. Furthermore, a refined Kalman filter term mitigates localization noise, ensuring robust state estimation for objects that are occluded and superior recovery during prolonged occlusions. This results in higher-order tracking accuracy (HOTA) improving by 4.8% on the KITTI validation dataset with the PV-RCNN detector. The proposed online framework, RobMOT, outperforms state-of-the-art methods, including deep learning approaches, across multiple detectors, with HOTA improvements of up to 3.92% on the KITTI testing dataset and 8.7% on the KITTI validation dataset while achieving the lowest identity switch (IDSW) scores of 7 and 0, respectively. RobMOT excels under challenging scenarios, such as tracking distant objects and handling prolonged occlusions, surpassing state-of-the-art methods on the Waymo Open testing dataset with a 1.77% improvement in MOTA for objects at distances exceeding 50 meters. RobMOT achieves a groundbreaking runtime of 3221 FPS using a single CPU, establishing itself as a highly efficient and scalable solution for real-time multi-object tracking.