作者:Jiaxin Li,Yan Ding(丁艳),Hua-Liang Wei

作者单位:北京理工大学,英国谢菲尔德大学

发布时间:2022

发布期刊/会议:Arxiv

出版商:

论文全称:SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

论文地址:

SimpleTrack: Rethinking and Improving the JDE Approach for...

论文代码:

https://github.com/1vpmaster/SimpleTrack

地位:

个人理解

一、摘要

Joint detection and embedding (JDE) based methods usually estimate bounding boxes and embedding features of objects with a single network in Multi-Object Tracking (MOT). In the tracking stage, JDE-based methods fuse the target motion information and appearance information by applying the same rule, which could fail when the target is briefly lost or blocked. To overcome this problem, we propose a new association matrix, the Embedding and Giou matrix, which combines embedding cosine distance and Giou distance of objects. To further improve the performance of data association, we develop a simple, effective tracker named SimpleTrack, which designs a bottom-up fusion method for Re-identity and proposes a new tracking strategy based on our EG matrix. The experimental results indicate that SimpleTrack has powerful data association capability, e.g., 61.6 HOTA and 76.3 IDF1 on MOT17. In addition, we apply the EG matrix to 5 different state-of-the-art JDE-based methods and achieve significant improvements in IDF1, HOTA and IDsw metrics, and increase the tracking speed of these methods by about 20%.