Abstract | ||
---|---|---|
Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras. Recently, the tracking performance of MTMCT is significantly enhanced with the employment of re-identification (Re-ID) model. However, the appearance feature usually becomes unreliable due to the occlusion and orientation variance of the targets. Directly applying Re-ID model in MTMCT will encounter the problem of identity switches (IDS) and tracklet fragment caused by occlusion. To solve these problems, we propose a novel tracking framework in this paper. In this framework, the occlusion status and orientation information are utilized in Re-ID model with human pose information considered. In addition, the tracklet association using the proposed fused tracking feature is adopted to handle the fragment problem. The proposed tracker achieves 81.3% IDFI on the multiple-camera hard sequence, which outperforms all other reference methods by a large margin. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPRW.2019.00192 | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
DocType | Volume | ISSN |
Conference | abs/1906.01357 | 2160-7508 |
Citations | PageRank | References |
2 | 0.36 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peng Li | 1 | 81 | 11.75 |
Jiabin Zhang | 2 | 5 | 1.43 |
Zheng Zhu | 3 | 67 | 13.15 |
Yanwei Li | 4 | 3 | 2.74 |
Jiang Lu | 5 | 10 | 3.70 |
Guan Huang | 6 | 23 | 3.41 |