Review of models for estimating 3D human pose using deep learning
Human pose estimation (HPE) is designed to detect and localize various parts of the human body and represent them as a kinematic structure based on input data like images and videos. Three-dimensional (3D) HPE involves determining the positions of articulated joints in 3D space. Given its wide-rangi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2574.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086434017705984 |
|---|---|
| author | Sani Salisu Kamaluddeen Usman Danyaro Maged Nasser Israa M. Hayder Hussain A. Younis |
| author_facet | Sani Salisu Kamaluddeen Usman Danyaro Maged Nasser Israa M. Hayder Hussain A. Younis |
| author_sort | Sani Salisu |
| collection | DOAJ |
| description | Human pose estimation (HPE) is designed to detect and localize various parts of the human body and represent them as a kinematic structure based on input data like images and videos. Three-dimensional (3D) HPE involves determining the positions of articulated joints in 3D space. Given its wide-ranging applications, HPE has become one of the fastest-growing areas in computer vision and artificial intelligence. This review highlights the latest advances in 3D deep-learning-based HPE models, addressing the major challenges such as accuracy, real-time performance, and data constraints. We assess the most widely used datasets and evaluation metrics, providing a comparison of leading algorithms in terms of precision and computational efficiency in tabular form. The review identifies key applications of HPE in industries like healthcare, security, and entertainment. Our findings suggest that while deep learning models have made significant strides, challenges in handling occlusion, real-time estimation, and generalization remain. This study also outlines future research directions, offering a roadmap for both new and experienced researchers to further develop 3D HPE models using deep learning. |
| format | Article |
| id | doaj-art-5c63e00e40e04cd4ae02423de82dd6d9 |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-5c63e00e40e04cd4ae02423de82dd6d92025-02-06T15:05:10ZengPeerJ Inc.PeerJ Computer Science2376-59922025-02-0111e257410.7717/peerj-cs.2574Review of models for estimating 3D human pose using deep learningSani Salisu0Kamaluddeen Usman Danyaro1Maged Nasser2Israa M. Hayder3Hussain A. Younis4Department of Information Technology, Federal University Dutse, Dutse, Jigawa, NigeriaComputer & Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar, MalaysiaComputer & Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar, MalaysiaDepartment of Computer Systems Techniques, Qurna Technique Institute, Southern Technical University, Basrah, IraqCollege of Education for Women, University of Basrah, Basrah, IraqHuman pose estimation (HPE) is designed to detect and localize various parts of the human body and represent them as a kinematic structure based on input data like images and videos. Three-dimensional (3D) HPE involves determining the positions of articulated joints in 3D space. Given its wide-ranging applications, HPE has become one of the fastest-growing areas in computer vision and artificial intelligence. This review highlights the latest advances in 3D deep-learning-based HPE models, addressing the major challenges such as accuracy, real-time performance, and data constraints. We assess the most widely used datasets and evaluation metrics, providing a comparison of leading algorithms in terms of precision and computational efficiency in tabular form. The review identifies key applications of HPE in industries like healthcare, security, and entertainment. Our findings suggest that while deep learning models have made significant strides, challenges in handling occlusion, real-time estimation, and generalization remain. This study also outlines future research directions, offering a roadmap for both new and experienced researchers to further develop 3D HPE models using deep learning.https://peerj.com/articles/cs-2574.pdfHuman pose estimationDeep learning3D imageSurveyNeural networkReview |
| spellingShingle | Sani Salisu Kamaluddeen Usman Danyaro Maged Nasser Israa M. Hayder Hussain A. Younis Review of models for estimating 3D human pose using deep learning PeerJ Computer Science Human pose estimation Deep learning 3D image Survey Neural network Review |
| title | Review of models for estimating 3D human pose using deep learning |
| title_full | Review of models for estimating 3D human pose using deep learning |
| title_fullStr | Review of models for estimating 3D human pose using deep learning |
| title_full_unstemmed | Review of models for estimating 3D human pose using deep learning |
| title_short | Review of models for estimating 3D human pose using deep learning |
| title_sort | review of models for estimating 3d human pose using deep learning |
| topic | Human pose estimation Deep learning 3D image Survey Neural network Review |
| url | https://peerj.com/articles/cs-2574.pdf |
| work_keys_str_mv | AT sanisalisu reviewofmodelsforestimating3dhumanposeusingdeeplearning AT kamaluddeenusmandanyaro reviewofmodelsforestimating3dhumanposeusingdeeplearning AT magednasser reviewofmodelsforestimating3dhumanposeusingdeeplearning AT israamhayder reviewofmodelsforestimating3dhumanposeusingdeeplearning AT hussainayounis reviewofmodelsforestimating3dhumanposeusingdeeplearning |