1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
About
This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges. An efficient and pragmatic online tracking-by-detection framework named HorizonMOT is proposed for camera-based 2D tracking in the image space and LiDAR-based 3D tracking in the 3D world space. Within the tracking-by-detection paradigm, our trackers leverage our high-performing detectors used in the 2D/3D detection challenges and achieved 45.13% 2D MOTA/L2 and 63.45% 3D MOTA/L2 in the 2D/3D tracking challenges.
Yu Wang, Sijia Chen, Li Huang, Runzhou Ge, Yihan Hu, Zhuangzhuang Ding, Jie Liao• 2020
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Multi-Object Tracking | Waymo Open Dataset 3D Tracking (Leaderboard) | MOTA L263.45 | 10 | |
| 3D Tracking | Waymo Open Dataset Vehicle Level 2 (test) | MOTA64.07 | 8 | |
| 3D Object Detection | Waymo Open Vehicle Level 2 (test) | mAPH0.7783 | 4 |
Showing 3 of 3 rows