SIA OpenIR  > 机器人学研究室
Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
Ren WH(任卫红)1; Wang, Xinchao2; Tian JD(田建东)3,4; Tang YD(唐延东)3,4; Chan, Antoni B.1
Department机器人学研究室
Source PublicationIEEE Transactions on Image Processing
ISSN1057-7149
2021
Volume30Pages:1439-1452
Indexed BySCI ; EI
EI Accession number20210209755770
WOS IDWOS:000604831700005
Contribution Rank3
Funding OrganizationResearch Grants Council of the Hong Kong Special Administrative Region, China, under Project T32-101/15-R and Project CityU 11212518 ; Strategic Research Grant from the City University of Hong Kong under Project 7004887 ; Natural Science Foundation of China under Grant 61991413
KeywordPeople tracking crowd density map multiple people tracking flow tracking
Abstract

State-of-the-art multi-object tracking (MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to obtain accurate detections due to heavy occlusions and high crowd density. In this paper, we propose a new MOT paradigm, tracking-by-counting, tailored for crowded scenes. Using crowd density maps, we jointly model detection, counting, and tracking of multiple targets as a network flow program, which simultaneously finds the global optimal detections and trajectories of multiple targets over the whole video. This is in contrast to prior MOT methods that either ignore the crowd density and thus are prone to errors in crowded scenes, or rely on a suboptimal two-step process using heuristic density-aware point-tracks for matching targets. Our approach yields promising results on public benchmarks of various domains including people tracking, cell tracking, and fish tracking.

Language英语
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS KeywordMULTITARGET TRACKING ; MODEL
WOS Research AreaComputer Science ; Engineering
Funding ProjectResearch Grants Council of the Hong Kong Special Administrative Region, China[T32-101/15-R] ; Research Grants Council of the Hong Kong Special Administrative Region, China[CityU 11212518] ; City University of Hong Kong[7004887] ; Natural Science Foundation of China[61991413]
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28136
Collection机器人学研究室
Corresponding AuthorChan, Antoni B.
Affiliation1.Department of Computer Science, City University of Hong, Kowloon, Hong Kong.
2.Department of Computer Science, Stevens Institute of Technology, New Jersey, United States.
3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China
4.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016 China
Recommended Citation
GB/T 7714
Ren WH,Wang, Xinchao,Tian JD,et al. Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets[J]. IEEE Transactions on Image Processing,2021,30:1439-1452.
APA Ren WH,Wang, Xinchao,Tian JD,Tang YD,&Chan, Antoni B..(2021).Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets.IEEE Transactions on Image Processing,30,1439-1452.
MLA Ren WH,et al."Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets".IEEE Transactions on Image Processing 30(2021):1439-1452.
Files in This Item:
File Name/Size DocType Version Access License
Tracking-by-Counting(5208KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ren WH(任卫红)]'s Articles
[Wang, Xinchao]'s Articles
[Tian JD(田建东)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ren WH(任卫红)]'s Articles
[Wang, Xinchao]'s Articles
[Tian JD(田建东)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ren WH(任卫红)]'s Articles
[Wang, Xinchao]'s Articles
[Tian JD(田建东)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Tracking-by-Counting_ Using Network Flows on Crowd Density Maps for Tracking Multiple Targets.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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