PCNet: a human pose compensation network based on incremental learning for sports actions estimation
Abstract Human pose estimation has a wide range of applications. Existing methods perform well in conventional domains, but there are certain defects when they are applied to sports activities. The first is lack of estimation of the extremity posture, making it impossible to comprehensively evaluate...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01647-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571161194528768 |
|---|---|
| author | Jia-Hong Jiang Nan Xia |
| author_facet | Jia-Hong Jiang Nan Xia |
| author_sort | Jia-Hong Jiang |
| collection | DOAJ |
| description | Abstract Human pose estimation has a wide range of applications. Existing methods perform well in conventional domains, but there are certain defects when they are applied to sports activities. The first is lack of estimation of the extremity posture, making it impossible to comprehensively evaluate the movement posture; the second is insufficient occlusion handling. Therefore, we propose a human pose compensation network based on incremental learning, which obtains shared weights to extract detailed features under the premise of limited extremity training data. We propose a higher-order feature compensator (HOF-compensator) to embed the attributes of the extremity into the torso and limbs topology structure, building a complete higher-order feature. In addition, to improve the occlusion handling performance, we propose an occlusion feature enhancement attention mechanism (OFE-attention) that can identify occluded keypoints and enhance attention to occlusion areas. We design comparative experiments on three public datasets and a self-built sports dataset, achieving the highest mean accuracy among all comparative methods. In addition, we design a series of ablation analysis and visualization displays to verify that our method performs best in sports pose estimation. |
| format | Article |
| id | doaj-art-4634e20b6d1f4d2890a7b23f2769129a |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-4634e20b6d1f4d2890a7b23f2769129a2025-02-02T12:50:10ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111510.1007/s40747-024-01647-1PCNet: a human pose compensation network based on incremental learning for sports actions estimationJia-Hong Jiang0Nan Xia1School of Information Science and Engineering, Dalian Polytecnic UniversitySchool of Information Science and Engineering, Dalian Polytecnic UniversityAbstract Human pose estimation has a wide range of applications. Existing methods perform well in conventional domains, but there are certain defects when they are applied to sports activities. The first is lack of estimation of the extremity posture, making it impossible to comprehensively evaluate the movement posture; the second is insufficient occlusion handling. Therefore, we propose a human pose compensation network based on incremental learning, which obtains shared weights to extract detailed features under the premise of limited extremity training data. We propose a higher-order feature compensator (HOF-compensator) to embed the attributes of the extremity into the torso and limbs topology structure, building a complete higher-order feature. In addition, to improve the occlusion handling performance, we propose an occlusion feature enhancement attention mechanism (OFE-attention) that can identify occluded keypoints and enhance attention to occlusion areas. We design comparative experiments on three public datasets and a self-built sports dataset, achieving the highest mean accuracy among all comparative methods. In addition, we design a series of ablation analysis and visualization displays to verify that our method performs best in sports pose estimation.https://doi.org/10.1007/s40747-024-01647-1Human pose estimationSports activitiesKeypoints compensationOcclusion handlingFeature enhancementIncremental learning |
| spellingShingle | Jia-Hong Jiang Nan Xia PCNet: a human pose compensation network based on incremental learning for sports actions estimation Complex & Intelligent Systems Human pose estimation Sports activities Keypoints compensation Occlusion handling Feature enhancement Incremental learning |
| title | PCNet: a human pose compensation network based on incremental learning for sports actions estimation |
| title_full | PCNet: a human pose compensation network based on incremental learning for sports actions estimation |
| title_fullStr | PCNet: a human pose compensation network based on incremental learning for sports actions estimation |
| title_full_unstemmed | PCNet: a human pose compensation network based on incremental learning for sports actions estimation |
| title_short | PCNet: a human pose compensation network based on incremental learning for sports actions estimation |
| title_sort | pcnet a human pose compensation network based on incremental learning for sports actions estimation |
| topic | Human pose estimation Sports activities Keypoints compensation Occlusion handling Feature enhancement Incremental learning |
| url | https://doi.org/10.1007/s40747-024-01647-1 |
| work_keys_str_mv | AT jiahongjiang pcnetahumanposecompensationnetworkbasedonincrementallearningforsportsactionsestimation AT nanxia pcnetahumanposecompensationnetworkbasedonincrementallearningforsportsactionsestimation |