1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 0; 2023: 1.
5 papers.
- 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
- 2021Monocular Quasi-Dense 3D Object Trackingcited by 80
- 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
- 2021Local Metrics for Multi-Object Trackingcited by 8
- 2021Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awarenesscited by 4
- 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds9 Jun 2023
- 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds16 Dec 2021
- 2021Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness29 Jul 2021
- 2021Local Metrics for Multi-Object Tracking6 Apr 2021
- 2021Monocular Quasi-Dense 3D Object Tracking12 Mar 2021