Title
Tracklet Proposal Network for Multi-Object Tracking on Point Clouds
Document Type
Conference Proceeding
Publication Date
1-1-2021
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, the 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.
Publication Source (Journal or Book title)
IJCAI International Joint Conference on Artificial Intelligence
First Page
1165
Last Page
1171
Recommended Citation
Wu, H., Li, Q., Wen, C., Li, X., Fan, X., & Wang, C. (2021). Tracklet Proposal Network for Multi-Object Tracking on Point Clouds. IJCAI International Joint Conference on Artificial Intelligence, 1165-1171. Retrieved from https://repository.lsu.edu/eecs_pubs/685