Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking | |
He, Jiawei; Huang, Zehao; Wang, Naiyan; Zhang, Zhaoxiang | |
2021-06 | |
会议日期 | 2021-6-19~2021-6-25 |
会议地点 | virtual |
英文摘要 | Data association across frames is at the core of Multiple Object Tracking (MOT) task. This problem is usually solved by a traditional graph-based optimization or directly learned via deep learning. Despite their popularity, we find some points worth studying in current paradigm: 1) Existing methods mostly ignore the context information among tracklets and intra-frame detections, which makes the tracker hard to survive in challenging cases like severe occlusion. 2) The end-to-end association methods solely rely on the data fitting power of deep neural networks, while they hardly utilize the advantage of optimization-based assignment methods. 3) The graph-based optimization methods mostly utilize a separate neural network to extract features, which brings the inconsistency between training and inference. Therefore, in this paper we propose a novel learnable graph matching method to address these issues. Briefly speaking, we model the relationships between tracklets and the intra-frame detections as a general undirected graph. Then the association problem turns into a general graph matching between tracklet graph and detection graph. Furthermore, to make the optimization end-to-end differentiable, we relax the original graph matching into continuous quadratic programming and then incorporate the training of it into a deep graph network with the help of the implicit function theorem. Lastly, our method GMTracker, achieves state-of-the-art performance on several standard MOT datasets. |
会议录出版者 | IEEE |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57425] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences 3.TuSimple 4.Centre for Artificial Intelligence and Robotics, HKISI_CAS |
推荐引用方式 GB/T 7714 | He, Jiawei,Huang, Zehao,Wang, Naiyan,et al. Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking[C]. 见:. virtual. 2021-6-19~2021-6-25. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论