SegDQ: Segmentation assisted multi-object tracking with dynamic query-based transformers
Liu, Yating1,2; Bai, Tianxiang1,2; Tian, Yonglin3; Wang, Yutong1; Wang, Jiangong1,2; Wang, Xiao1,4; Wang, Fei-Yue1
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2022-04-07
Volume481Pages:91-101
Abstract

Multi-Object Tracking (MOT) has been one of the most important topics in computer vision. The tradi-tional tracking-by-detection framework of MOT is severely suffered from the poor detection results. In this paper, based on Transformer, we introduce the tracking-by-query MOT framework, and propose to apply semantic segmentation as an auxiliary task to optimize the training of MOT trackers, which addresses more on extracted foreground features. In addition, a feature-dependent dynamic object query (DOQ), instead of a fixed-learned object query (LOQ), is put forward to retrieve the new detections, improving the flexibility and constringency of the framework. We tested our SegDQ method on various scenarios including MOTChallenge 15, 16 and 17 datasets. The experimental results show that it obvi-ously improves the MOTA and IDF1 indexes of tracking results. (c) 2022 Published by Elsevier B.V.

KeywordMulti-object tracking Transformer Semantic task Dynamic query
DOI10.1016/j.neucom.2022.01.073
WOS KeywordONLINE TRACKING
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[62173329] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV)
Funding OrganizationNational Natural Science Foundation of China ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000761785300009
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48036
Collection复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
Corresponding AuthorWang, Fei-Yue
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China
4.Qingdao Acad Intelligent Ind, Qingdao 266000, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Liu, Yating,Bai, Tianxiang,Tian, Yonglin,et al. SegDQ: Segmentation assisted multi-object tracking with dynamic query-based transformers[J]. NEUROCOMPUTING,2022,481:91-101.
APA Liu, Yating.,Bai, Tianxiang.,Tian, Yonglin.,Wang, Yutong.,Wang, Jiangong.,...&Wang, Fei-Yue.(2022).SegDQ: Segmentation assisted multi-object tracking with dynamic query-based transformers.NEUROCOMPUTING,481,91-101.
MLA Liu, Yating,et al."SegDQ: Segmentation assisted multi-object tracking with dynamic query-based transformers".NEUROCOMPUTING 481(2022):91-101.
Files in This Item: Download All
File Name/Size DocType Version Access License
1-s2.0-S092523122200(2635KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Yating]'s Articles
[Bai, Tianxiang]'s Articles
[Tian, Yonglin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Yating]'s Articles
[Bai, Tianxiang]'s Articles
[Tian, Yonglin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Yating]'s Articles
[Bai, Tianxiang]'s Articles
[Tian, Yonglin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1-s2.0-S0925231222000923-main.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.