Tracking-by-Counting : Using Network Flows on Crowd Density Maps for Tracking Multiple Targets

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...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 07., Seite 1439-1452
Auteur principal: Ren, Weihong (Auteur)
Autres auteurs: Wang, Xinchao, Tian, Jiandong, Tang, Yandong, Chan, Antoni B
Format: Article en ligne
Langue:English
Publié: 2021
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM318973022
003 DE-627
005 20250228140526.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2020.3044219  |2 doi 
028 5 2 |a pubmed25n1063.xml 
035 |a (DE-627)NLM318973022 
035 |a (NLM)33332271 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ren, Weihong  |e verfasserin  |4 aut 
245 1 0 |a Tracking-by-Counting  |b Using Network Flows on Crowd Density Maps for Tracking Multiple Targets 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 30.12.2020 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 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 
650 4 |a Journal Article 
700 1 |a Wang, Xinchao  |e verfasserin  |4 aut 
700 1 |a Tian, Jiandong  |e verfasserin  |4 aut 
700 1 |a Tang, Yandong  |e verfasserin  |4 aut 
700 1 |a Chan, Antoni B  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 30(2021) vom: 07., Seite 1439-1452  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:30  |g year:2021  |g day:07  |g pages:1439-1452 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2020.3044219  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 30  |j 2021  |b 07  |h 1439-1452