Cargando…

Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning

Effective multi-object tracking is still challenging due to the trade-off between tracking accuracy and speed. Because the recent multi-object tracking (MOT) methods leverage object appearance and motion models so as to associate detections between consecutive frames, the key for effective multi-obj...

Descripción completa

Detalles Bibliográficos
Autores principales: Yoo, Yong-Sang, Lee, Seong-Ho, Bae, Seung-Hwan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609386/
https://www.ncbi.nlm.nih.gov/pubmed/36298293
http://dx.doi.org/10.3390/s22207943
_version_ 1784819005802938368
author Yoo, Yong-Sang
Lee, Seong-Ho
Bae, Seung-Hwan
author_facet Yoo, Yong-Sang
Lee, Seong-Ho
Bae, Seung-Hwan
author_sort Yoo, Yong-Sang
collection PubMed
description Effective multi-object tracking is still challenging due to the trade-off between tracking accuracy and speed. Because the recent multi-object tracking (MOT) methods leverage object appearance and motion models so as to associate detections between consecutive frames, the key for effective multi-object tracking is to reduce the computational complexity of learning both models. To this end, this work proposes global appearance and motion models to discriminate multiple objects instead of learning local object-specific models. In concrete detail, it learns a global appearance model using contrastive learning between object appearances. In addition, we learn a global relation motion model using relative motion learning between objects. Moreover, this paper proposes object constraint learning for improving tracking efficiency. This study considers the discriminability of the models as a constraint, and learns both models when inconsistency with the constraint occurs. Therefore, object constraint learning differs from the conventional online learning for multi-object tracking which updates learnable parameters per frame. This work incorporates global models and object constraint learning into the confidence-based association method, and compare our tracker with the state-of-the-art methods on public available MOT Challenge datasets. As a result, we achieve 64.5% MOTA (multi-object tracking accuracy) and 6.54 Hz tracking speed on the MOT16 test dataset. The comparison results show that our methods can contribute to improve tracking accuracy and tracking speed together.
format Online
Article
Text
id pubmed-9609386
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96093862022-10-28 Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning Yoo, Yong-Sang Lee, Seong-Ho Bae, Seung-Hwan Sensors (Basel) Article Effective multi-object tracking is still challenging due to the trade-off between tracking accuracy and speed. Because the recent multi-object tracking (MOT) methods leverage object appearance and motion models so as to associate detections between consecutive frames, the key for effective multi-object tracking is to reduce the computational complexity of learning both models. To this end, this work proposes global appearance and motion models to discriminate multiple objects instead of learning local object-specific models. In concrete detail, it learns a global appearance model using contrastive learning between object appearances. In addition, we learn a global relation motion model using relative motion learning between objects. Moreover, this paper proposes object constraint learning for improving tracking efficiency. This study considers the discriminability of the models as a constraint, and learns both models when inconsistency with the constraint occurs. Therefore, object constraint learning differs from the conventional online learning for multi-object tracking which updates learnable parameters per frame. This work incorporates global models and object constraint learning into the confidence-based association method, and compare our tracker with the state-of-the-art methods on public available MOT Challenge datasets. As a result, we achieve 64.5% MOTA (multi-object tracking accuracy) and 6.54 Hz tracking speed on the MOT16 test dataset. The comparison results show that our methods can contribute to improve tracking accuracy and tracking speed together. MDPI 2022-10-18 /pmc/articles/PMC9609386/ /pubmed/36298293 http://dx.doi.org/10.3390/s22207943 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yoo, Yong-Sang
Lee, Seong-Ho
Bae, Seung-Hwan
Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title_full Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title_fullStr Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title_full_unstemmed Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title_short Effective Multi-Object Tracking via Global Object Models and Object Constraint Learning
title_sort effective multi-object tracking via global object models and object constraint learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9609386/
https://www.ncbi.nlm.nih.gov/pubmed/36298293
http://dx.doi.org/10.3390/s22207943
work_keys_str_mv AT yooyongsang effectivemultiobjecttrackingviaglobalobjectmodelsandobjectconstraintlearning
AT leeseongho effectivemultiobjecttrackingviaglobalobjectmodelsandobjectconstraintlearning
AT baeseunghwan effectivemultiobjecttrackingviaglobalobjectmodelsandobjectconstraintlearning