1st Place Solutions for Waymo Open Dataset Challenges - 2D and 3D Tracking

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.

[1]  Dragomir Anguelov,et al.  Scalability in Perception for Autonomous Driving: Waymo Open Dataset , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Xingyi Zhou,et al.  Objects as Points , 2019, ArXiv.

[3]  Vladlen Koltun,et al.  Tracking Objects as Points , 2020, ECCV.

[4]  Volker Eiselein,et al.  High-Speed tracking-by-detection without using image information , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[5]  Deng Cai,et al.  Training-Time-Friendly Network for Real-Time Object Detection , 2020, AAAI.

[6]  Zhichao Lu,et al.  RetinaTrack: Online Single Stage Joint Detection and Tracking , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yu Wang,et al.  AFDet: Anchor Free One Stage 3D Object Detection , 2020, ArXiv.

[8]  Xinggang Wang,et al.  A Simple Baseline for Multi-Object Tracking , 2020, ArXiv.

[9]  Rainer Stiefelhagen,et al.  Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics , 2008, EURASIP J. Image Video Process..

[10]  Jie Li,et al.  Probabilistic 3D Multi-Object Tracking for Autonomous Driving , 2020, ArXiv.

[11]  Dietrich Paulus,et al.  Simple online and realtime tracking with a deep association metric , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[12]  Fabio Tozeto Ramos,et al.  Simple online and realtime tracking , 2016, 2016 IEEE International Conference on Image Processing (ICIP).