Affiliation:
1. Key Laboratory of Digital Performance and Simulation Technology Beijing Institute of Technology Beijing China
Abstract
AbstractTo address the issue of trajectory fragments and ID switches caused by occlusion in dense crowds, we propose a space‐time trajectory encoding method and a point‐line‐group division method to construct Trajectory‐BERT in this paper. Leveraging the spatiotemporal context‐dependent features of trajectories, we introduce pre‐training and fine‐tuning Trajectory‐BERT tasks to repair occluded trajectories. Experimental results show that data augmented with Trajectory‐BERT outperforms raw annotated data on the MOTA metric and reduces ID switches in raw labeled data, demonstrating the feasibility of our method.
Funder
National Key Research and Development Program of China
Subject
Computer Graphics and Computer-Aided Design,Software
Reference25 articles.
1. MkB SamiaI KawaakibHK et al.Multiple object tracking in recent times: a literature review. arXiv preprint arXiv:2209.04796.2022.
2. TransCenter: Transformers With Dense Representations for Multiple-Object Tracking
3. PatrickD HamidR AntonM et al.Mot20: a benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003.2020.
4. JacobD Ming‐WeiC LeeK KristinaT.Bert: pre‐training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.2018.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献