Multi-object tracking with hard-soft attention network and group-based cost minimization
Liu, Yating1,2; Li, Xuesong3; Bai, Tianxiang1,2; Wang, Kunfeng4; Wang, Fei-Yue1
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2021-08-04
Volume447Pages:80-91
Corresponding AuthorWang, Kunfeng(wangkf@mail.buct.edu.cn)
AbstractMulti-object tracking (MOT) has received constant attention from researchers with the development of deep learning and person re-identification (ReID). However, the occlusion caused tracking failure is still far from solved. In this paper, we propose a Hard-Soft Attention Network (HSAN) to improve the ReID performance and get robust appearance features of different targets. The pose information and attention mechanism are combined to distinguish between challenging targets. Besides, the unary and binary costs are constructed to ensure consistency and long-term tracking, which consider not only the appearance motion affinity of single tracks, but also the interactions between neighboring tracks. For that we cluster the tracks into different groups and choose reliable tracks as anchors to establish the two types of costs. Our HSAN appearance model is evaluated on the Market-1501, DUKE and CUHK03 ReID datasets and the MOT tracking method is conducted on MOTChallenge 15, 16 and 17. The experimental results demonstrate that our method can improve tracking accuracy and reduce fragments. (c) 2021 Elsevier B.V. All rights reserved.
KeywordMulti-object tracking Attention mechanism Unary and binary costs Appearance-motion affinity
DOI10.1016/j.neucom.2021.02.084
WOS KeywordPEOPLE
Indexed BySCI
Language英语
Funding ProjectIntel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRIIACV) ; National Natural Science Foundation of China[62076020] ; National Natural Science Foundation of China[U1811463]
Funding OrganizationIntel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRIIACV) ; National Natural Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000656962800007
PublisherELSEVIER
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/45305
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, Kunfeng
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.Key Lab Informat Syst Engn, Nanjing 210007, Peoples R China
4.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Liu, Yating,Li, Xuesong,Bai, Tianxiang,et al. Multi-object tracking with hard-soft attention network and group-based cost minimization[J]. NEUROCOMPUTING,2021,447:80-91.
APA Liu, Yating,Li, Xuesong,Bai, Tianxiang,Wang, Kunfeng,&Wang, Fei-Yue.(2021).Multi-object tracking with hard-soft attention network and group-based cost minimization.NEUROCOMPUTING,447,80-91.
MLA Liu, Yating,et al."Multi-object tracking with hard-soft attention network and group-based cost minimization".NEUROCOMPUTING 447(2021):80-91.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Yating]'s Articles
[Li, Xuesong]'s Articles
[Bai, Tianxiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Yating]'s Articles
[Li, Xuesong]'s Articles
[Bai, Tianxiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Yating]'s Articles
[Li, Xuesong]'s Articles
[Bai, Tianxiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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