Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose
Abstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-10-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-023-00351-1 |
| _version_ | 1797636721982046208 |
|---|---|
| author | Datian Liu Haitao Yang Zhang Lei |
| author_facet | Datian Liu Haitao Yang Zhang Lei |
| author_sort | Datian Liu |
| collection | DOAJ |
| description | Abstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer. The improved Transformer removes noise between human motion RGB and depth images, addressing orientation correlation in 3D models. Two-dimensional (2D) pose features are extracted from de-noised RGB images using a kernel generation module in a graph convolutional network (GCN). Depth features are extracted from de-noised depth images. The 2D pose features and depth features are fused using a regression module in the GCN to obtain 3D pose recognition results. The results demonstrate that the proposed method captures RGB and depth images, achieving high recognition accuracy and fast speed. The proposed method demonstrates good accuracy in 3D human motion pose recognition. |
| first_indexed | 2024-03-11T12:38:12Z |
| format | Article |
| id | doaj.art-f220d0cbe58b4008a58545c5bdb3f332 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-03-11T12:38:12Z |
| publishDate | 2023-10-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-f220d0cbe58b4008a58545c5bdb3f3322023-11-05T12:29:16ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832023-10-0116111110.1007/s44196-023-00351-1Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion PoseDatian Liu0Haitao Yang1Zhang Lei2Physical Education Department, Northeastern UniversityPhysical Education Department, Beijing University of TechnologyInstitute of Physical Education and Training, Capital University of Physical Education and SportsAbstract Three-dimensional (3D) human pose recognition techniques based on spatial data have gained attention. However, existing models and algorithms fail to achieve desired precision. We propose a 3D human motion pose recognition method using deep contrastive learning and an improved Transformer. The improved Transformer removes noise between human motion RGB and depth images, addressing orientation correlation in 3D models. Two-dimensional (2D) pose features are extracted from de-noised RGB images using a kernel generation module in a graph convolutional network (GCN). Depth features are extracted from de-noised depth images. The 2D pose features and depth features are fused using a regression module in the GCN to obtain 3D pose recognition results. The results demonstrate that the proposed method captures RGB and depth images, achieving high recognition accuracy and fast speed. The proposed method demonstrates good accuracy in 3D human motion pose recognition.https://doi.org/10.1007/s44196-023-00351-1Pose recognitionThree-dimensional human motionDeep contrastive learningImproved transformerDepth imagePose feature |
| spellingShingle | Datian Liu Haitao Yang Zhang Lei Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose International Journal of Computational Intelligence Systems Pose recognition Three-dimensional human motion Deep contrastive learning Improved transformer Depth image Pose feature |
| title | Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose |
| title_full | Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose |
| title_fullStr | Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose |
| title_full_unstemmed | Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose |
| title_short | Recognition Method with Deep Contrastive Learning and Improved Transformer for 3D Human Motion Pose |
| title_sort | recognition method with deep contrastive learning and improved transformer for 3d human motion pose |
| topic | Pose recognition Three-dimensional human motion Deep contrastive learning Improved transformer Depth image Pose feature |
| url | https://doi.org/10.1007/s44196-023-00351-1 |
| work_keys_str_mv | AT datianliu recognitionmethodwithdeepcontrastivelearningandimprovedtransformerfor3dhumanmotionpose AT haitaoyang recognitionmethodwithdeepcontrastivelearningandimprovedtransformerfor3dhumanmotionpose AT zhanglei recognitionmethodwithdeepcontrastivelearningandimprovedtransformerfor3dhumanmotionpose |