Robust Human Pose Estimation for Rotation via Self-Supervised Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yun K. | - |
dc.contributor.author | Park J. | - |
dc.contributor.author | Cho J. | - |
dc.date.available | 2020-04-06T06:44:08Z | - |
dc.date.created | 2020-04-02 | - |
dc.date.issued | 2020-02 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/26349 | - |
dc.description.abstract | The detection of abnormal postures, such as that of a reclining person, is a crucial part of visual surveillance. Further, even regular poses can appear rotated because of incongruity between the image and the angle of a pre-installed camera. However, most existing human pose estimation methods focus on small rotational changes, i.e., those less than 50 degrees, and they seldom consider robust human pose estimation for more drastic rotational changes. To the best of our knowledge, there have been no reports on the robustness of human pose estimation for rotational changes through large angles. In this study, we propose a robust human pose estimation method by creating a path for learning new rotational changes based on a self-supervised method and by combining the results with those obtained from a path based on a supervised method. Furthermore, a combination module composed of a convolutional layer is trained complementarily by both paths of the network to produce robust results for various rotational changes. We demonstrate the robustness of the proposed method with extensive experiments on images generated by rotating the elements of standard benchmark datasets. We fully analyze the rotational characteristics of the state-of-the-art human pose estimators and the proposed method. On the COCO Keypoint Detection dataset, the proposed method attains more than 15% improvement in the mean of average precision compared to the state-of-the-art method, and the standard deviation of the performance is improved by more than 4.7 times. © 2013 IEEE. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.relation.isPartOf | IEEE Access | - |
dc.title | Robust Human Pose Estimation for Rotation via Self-Supervised Learning | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000525419100058 | - |
dc.identifier.doi | 10.1109/ACCESS.2020.2973390 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.8, pp.32502 - 32517 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85081096670 | - |
dc.citation.endPage | 32517 | - |
dc.citation.startPage | 32502 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 8 | - |
dc.contributor.affiliatedAuthor | Cho J. | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | human pose estimation | - |
dc.subject.keywordAuthor | rotation | - |
dc.subject.keywordAuthor | self-supervised learning | - |
dc.subject.keywordPlus | Rotation | - |
dc.subject.keywordPlus | Supervised learning | - |
dc.subject.keywordPlus | Benchmark datasets | - |
dc.subject.keywordPlus | Human pose estimations | - |
dc.subject.keywordPlus | Keypoint detection | - |
dc.subject.keywordPlus | Standard deviation | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Supervised methods | - |
dc.subject.keywordPlus | Visual surveillance | - |
dc.subject.keywordPlus | Deep learning | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon 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.