1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2020
- DOI:
- 10.48550/arXiv.2006.15506
- arXiv:
- arXiv:2006.15506
- Bibcode:
- 2020arXiv200615506W
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition