AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics
Xinshuo Weng, Jianren Wang, David Held, Kris Kitani

TL;DR
This paper introduces a simple, real-time 3D multi-object tracking system using LiDAR data, along with new evaluation metrics and tools, achieving high accuracy and speed on the KITTI dataset.
Contribution
Proposes a lightweight 3D MOT system with strong performance and introduces new evaluation metrics and tools for fair comparison.
Findings
Achieves 207.4 FPS on KITTI dataset
Outperforms existing methods in speed and accuracy
Provides publicly available code for reproducibility
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 FPS on…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Robotics and Sensor-Based Localization · Advanced Vision and Imaging
