Tracklet Proposal Network for Multi-Object Tracking on Point Clouds
Abstract
This paper proposes the first tracklet proposal network, named PC-TCNN, for Multi-Object Tracking (MOT) on point clouds. Our pipeline first generates tracklet proposals, then refines these tracklets and associates them to generate long trajectories. Specifically, object proposal generation and motion regression are first performed on a point cloud sequence to generate tracklet candidates. Then, spatial-temporal features of each tracklet are exploited and their consistency is used to refine the tracklet proposal. Finally, the refined tracklets across multiple frames are associated to perform MOT on the point cloud sequence. The PC-TCNN significantly improves the MOT performance by introducing the tracklet proposal design. On the KITTI tracking benchmark, it attains an MOTA of 91.75%, outperforming all submitted results on the online leaderboard.
Cite
Text
Wu et al. "Tracklet Proposal Network for Multi-Object Tracking on Point Clouds." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/161Markdown
[Wu et al. "Tracklet Proposal Network for Multi-Object Tracking on Point Clouds." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/wu2021ijcai-tracklet/) doi:10.24963/IJCAI.2021/161BibTeX
@inproceedings{wu2021ijcai-tracklet,
title = {{Tracklet Proposal Network for Multi-Object Tracking on Point Clouds}},
author = {Wu, Hai and Li, Qing and Wen, Chenglu and Li, Xin and Fan, Xiaoliang and Wang, Cheng},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2021},
pages = {1165-1171},
doi = {10.24963/IJCAI.2021/161},
url = {https://mlanthology.org/ijcai/2021/wu2021ijcai-tracklet/}
}