Relay dueling network for visual tracking with broad field-of-view
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jiang, Yifan | - |
dc.contributor.author | Han, David K. | - |
dc.contributor.author | Ko, Hanseok | - |
dc.date.accessioned | 2021-09-01T04:58:11Z | - |
dc.date.available | 2021-09-01T04:58:11Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-10 | - |
dc.identifier.issn | 1751-9632 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/62664 | - |
dc.description.abstract | A deep reinforcement-learning-based method is presented for visual object tracking tasks. The key objective is to generate a sequence of actions which can move or scale the bounding box in the previous frame to track the target in the current frame. Two intelligent agents are trained to accomplish the above task with a special dueling deep Q-learning network (Dueling DQN), referred to as a relay dueling network. The proposed model is divided into two agents: the movement agent and the scaling agent. The former performs horizontal or vertical movements and the latter generates scaling actions to change the size of the bounding box. The model has multiple inputs that cover both the bounding box region and the enlarged search region to improve the agents' perception of the surroundings. The proposed method has a broader field of vision than other similar trackers and its distribution of actions makes it easy to train and improve its tracking performance. The proposed network is tested on popular standard tracker benchmarks and its performance is compared with state-of-the-art trackers. The proposed network is found to be competitive in tracking accuracy and execution effectiveness when compared to conventional methods. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | INST ENGINEERING TECHNOLOGY-IET | - |
dc.title | Relay dueling network for visual tracking with broad field-of-view | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Ko, Hanseok | - |
dc.identifier.doi | 10.1049/iet-cvi.2018.5546 | - |
dc.identifier.scopusid | 2-s2.0-85074809418 | - |
dc.identifier.wosid | 000498074500001 | - |
dc.identifier.bibliographicCitation | IET COMPUTER VISION, v.13, no.7, pp.615 - 622 | - |
dc.relation.isPartOf | IET COMPUTER VISION | - |
dc.citation.title | IET COMPUTER VISION | - |
dc.citation.volume | 13 | - |
dc.citation.number | 7 | - |
dc.citation.startPage | 615 | - |
dc.citation.endPage | 622 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordAuthor | object tracking | - |
dc.subject.keywordAuthor | object detection | - |
dc.subject.keywordAuthor | tracking | - |
dc.subject.keywordAuthor | learning (artificial intelligence) | - |
dc.subject.keywordAuthor | computer vision | - |
dc.subject.keywordAuthor | relay dueling network | - |
dc.subject.keywordAuthor | visual tracking | - |
dc.subject.keywordAuthor | field-of-view | - |
dc.subject.keywordAuthor | deep reinforcement-learning-based method | - |
dc.subject.keywordAuthor | visual object tracking tasks | - |
dc.subject.keywordAuthor | previous frame | - |
dc.subject.keywordAuthor | intelligent agents | - |
dc.subject.keywordAuthor | special dueling deep Q-learning network | - |
dc.subject.keywordAuthor | Dueling DQN | - |
dc.subject.keywordAuthor | movement agent | - |
dc.subject.keywordAuthor | scaling agent | - |
dc.subject.keywordAuthor | vertical movements | - |
dc.subject.keywordAuthor | bounding box region | - |
dc.subject.keywordAuthor | enlarged search region | - |
dc.subject.keywordAuthor | tracking performance | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.