Encoding Pose Features to Images With Data Augmentation for 3-D Action Recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huynh-The, Thien | - |
dc.contributor.author | Hua, Cam-Hao | - |
dc.contributor.author | Kim, Dong-Seong | - |
dc.date.available | 2020-06-17T05:50:03Z | - |
dc.date.created | 2020-06-16 | - |
dc.date.issued | 2020-05 | - |
dc.identifier.issn | 1551-3203 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/17607 | - |
dc.description.abstract | Recently, numerous methods have been introduced for three-dimensional (3-D) action recognition using handcrafted feature descriptors coupled traditional classifiers. However, they cannot learn high-level features of a whole skeleton sequence exhaustively. In this paper, a novel encoding technique-namely, pose feature to image (PoF2I), is introduced to transform the pose features of joint-joint distance and orientation to color pixels. By concatenating the features of all skeleton frames in a sequence, a color image is generated to depict spatial joint correlations and temporal pose dynamics of an action appearance. The strategy of end-to-end fine-tuning a pretrained deep convolutional neural network, which completely capture multiple high-level features at multiscale action representation, is implemented for learning recognition models. We further propose an efficient data augmentation mechanism for informative enrichment and overfitting prevention. The experimental results on six challenging 3-D action recognition datasets demonstrate that the proposed method outperforms state-of-the-art approaches. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Encoding Pose Features to Images With Data Augmentation for 3-D Action Recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Dong-Seong | - |
dc.identifier.doi | 10.1109/TII.2019.2910876 | - |
dc.identifier.wosid | 000519588700021 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v.16, no.5, pp.3100 - 3111 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS | - |
dc.citation.title | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS | - |
dc.citation.volume | 16 | - |
dc.citation.number | 5 | - |
dc.citation.startPage | 3100 | - |
dc.citation.endPage | 3111 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Automation & Control Systems | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Automation & Control Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications | - |
dc.relation.journalWebOfScienceCategory | Engineering, Industrial | - |
dc.subject.keywordAuthor | Data augmentation | - |
dc.subject.keywordAuthor | deep convolutional neural networks (DCNNs) | - |
dc.subject.keywordAuthor | human action recognition | - |
dc.subject.keywordAuthor | pose feature to image (PoF2I) encoding technique | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
350-27, Gumi-daero, Gumi-si, Gyeongsangbuk-do, Republic of Korea (39253)054-478-7170
COPYRIGHT 2020 Kumoh 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.