UM
Residential Collegefalse
Status已發表Published
Multi-Person Pose Estimation under Complex Environment Based on Progressive Rotation Correction and Multi-Scale Feature Fusion
Huang,Guoheng1; Chen,Xiaoping1; Chen,Junan1; Lin,Weida1; Ling,Wing Kuen2; Pun,Chi Man3; Cheng,Lianglun1; Wang,Zhuowei1
2020
Source PublicationIEEE Access
Volume8Pages:132514-132526
Abstract

The research of multi-person pose estimation has been largely improved recently. However, multi-person pose estimation in complex environments is still challenging. For example, the following two situations cannot be handled well by existing pose estimation methods: first, there are pedestrians that are not upright or even inverted in the image, and pedestrians of different scales appear in the same image. To solve these problems, the Progressive rotation correction module (PRCM) and Scale-invariance module (SIM) based on multi-scale feature fusion are proposed. First of all, the PRCM was proposed to address the situation where pedestrians appear rotated or even inverted in the image. This module is divided into three stages, with the aim of gradually correcting the inverted human to an upright one. Besides, SIM is designed to handle multi-scale problems. In this module, dilated convolutions with different receptive field are used to extract multi-scale information. Then, the extracted multi-scale features (different semantic information in different feature maps) will be fused to solve the multi-scale problem. The experimental results show that our algorithm can reach an AP value of 72.0% when tested on the COCO2017 dataset. Demonstrates that the proposed method is superior to state-of-the-art methods.

KeywordDilated Convolution Multi-scale Feature Fusion Pose Estimation Rotation Invariance
DOI10.1109/ACCESS.2020.3010257
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaComputer Science ; Engineering ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS IDWOS:000554364000001
Scopus ID2-s2.0-85089305093
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionUniversity of Macau
Corresponding AuthorLing,Wing Kuen; Pun,Chi Man; Cheng,Lianglun
Affiliation1.School of Computers,Guangdong University of Technology,Guangzhou,510006,China
2.School of Information Engineering,Guangdong University of Technology,Guangzhou,510006,China
3.Department of Computer and Information Science,University of Macau,Macau,999078,Macao
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Huang,Guoheng,Chen,Xiaoping,Chen,Junan,et al. Multi-Person Pose Estimation under Complex Environment Based on Progressive Rotation Correction and Multi-Scale Feature Fusion[J]. IEEE Access,2020,8:132514-132526.
APA Huang,Guoheng,Chen,Xiaoping,Chen,Junan,Lin,Weida,Ling,Wing Kuen,Pun,Chi Man,Cheng,Lianglun,&Wang,Zhuowei.(2020).Multi-Person Pose Estimation under Complex Environment Based on Progressive Rotation Correction and Multi-Scale Feature Fusion.IEEE Access,8,132514-132526.
MLA Huang,Guoheng,et al."Multi-Person Pose Estimation under Complex Environment Based on Progressive Rotation Correction and Multi-Scale Feature Fusion".IEEE Access 8(2020):132514-132526.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang,Guoheng]'s Articles
[Chen,Xiaoping]'s Articles
[Chen,Junan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang,Guoheng]'s Articles
[Chen,Xiaoping]'s Articles
[Chen,Junan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang,Guoheng]'s Articles
[Chen,Xiaoping]'s Articles
[Chen,Junan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.