AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
Xinshuo Weng, Jianren Wang, David Held, Kris Kitani
TL;DR
The paper addresses the need for a simple, efficient baseline for 3D MOT in autonomous driving by proposing AB3DMOT, a baseline that combines 3D LiDAR detections with a 3D Kalman filter and Hungarian data association, expanding the state to 3D. To enable fair comparisons, it introduces a 3D MOT evaluation tool and three integral metrics (sAMOTA, AMOTA, AMOTP) to assess performance across confidence thresholds. Experiments on KITTI demonstrate strong 3D MOT performance, competitive 2D MOT results when projected, and state-of-the-art speed (~$207.4$ FPS) without GPU. The work provides a reproducible baseline and standardized evaluation to accelerate progress in 3D MOT.
Abstract
3D multi-object tracking (MOT) is essential to applications such as autonomous driving. Recent work focuses on developing accurate systems giving less attention to computational cost and system complexity. In contrast, this work proposes a simple real-time 3D MOT system with strong performance. Our system first obtains 3D detections from a LiDAR point cloud. Then, a straightforward combination of a 3D Kalman filter and the Hungarian algorithm is used for state estimation and data association. Additionally, 3D MOT datasets such as KITTI evaluate MOT methods in 2D space and standardized 3D MOT evaluation tools are missing for a fair comparison of 3D MOT methods. We propose a new 3D MOT evaluation tool along with three new metrics to comprehensively evaluate 3D MOT methods. We show that, our proposed method achieves strong 3D MOT performance on KITTI and runs at a rate of $207.4$ FPS on the KITTI dataset, achieving the fastest speed among modern 3D MOT systems. Our code is publicly available at http://www.xinshuoweng.com/projects/AB3DMOT.