Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method
To address the problem of low accuracy in joint point estimation in hand pose estimation methods due to the self-similarity of fingers and easy self-obscuration of hand joints, a hand pose estimation method based on coordinate correction and graph convolution is proposed. First, the standard coordin...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/22/7289 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267005814308864 |
|---|---|
| author | Dang Rong Feng Gang |
| author_facet | Dang Rong Feng Gang |
| author_sort | Dang Rong |
| collection | DOAJ |
| description | To address the problem of low accuracy in joint point estimation in hand pose estimation methods due to the self-similarity of fingers and easy self-obscuration of hand joints, a hand pose estimation method based on coordinate correction and graph convolution is proposed. First, the standard coordinate encoding is improved by generating an unbiased heat map, and the distribution-aware method is used for decoding coordinates to reduce the error in decoding the coordinate encoding of joints. Then, the complex dependency relationship between the joints and the relationship between pixels and joints of the hand are modeled by using graph convolution, and the feature information of the hand joints is enhanced by determining the relationship between the hand joints. Finally, the skeletal constraint loss function is used to impose constraints on the joints, and a natural and undistorted hand skeleton structure is generated. Training tests are conducted on the public gesture interaction dataset STB, and the experimental results show that the method in this paper can reduce errors in hand joint point detection and improve the estimation accuracy. |
| format | Article |
| id | doaj-art-bee499d8e6e44a688ca2d63dc6645f5c |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-bee499d8e6e44a688ca2d63dc6645f5c2025-08-20T01:53:57ZengMDPI AGSensors1424-82202024-11-012422728910.3390/s24227289Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation MethodDang Rong0Feng Gang1School of Architecture, Tianjin University, Tianjin 300073, ChinaSchool of Architecture, Tianjin University, Tianjin 300073, ChinaTo address the problem of low accuracy in joint point estimation in hand pose estimation methods due to the self-similarity of fingers and easy self-obscuration of hand joints, a hand pose estimation method based on coordinate correction and graph convolution is proposed. First, the standard coordinate encoding is improved by generating an unbiased heat map, and the distribution-aware method is used for decoding coordinates to reduce the error in decoding the coordinate encoding of joints. Then, the complex dependency relationship between the joints and the relationship between pixels and joints of the hand are modeled by using graph convolution, and the feature information of the hand joints is enhanced by determining the relationship between the hand joints. Finally, the skeletal constraint loss function is used to impose constraints on the joints, and a natural and undistorted hand skeleton structure is generated. Training tests are conducted on the public gesture interaction dataset STB, and the experimental results show that the method in this paper can reduce errors in hand joint point detection and improve the estimation accuracy.https://www.mdpi.com/1424-8220/24/22/7289hand pose estimationgraph convolutional networksfeature reconstructioncoordinate correctiondistributional sensing |
| spellingShingle | Dang Rong Feng Gang Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method Sensors hand pose estimation graph convolutional networks feature reconstruction coordinate correction distributional sensing |
| title | Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method |
| title_full | Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method |
| title_fullStr | Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method |
| title_full_unstemmed | Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method |
| title_short | Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method |
| title_sort | coordinate corrected and graph convolution based hand pose estimation method |
| topic | hand pose estimation graph convolutional networks feature reconstruction coordinate correction distributional sensing |
| url | https://www.mdpi.com/1424-8220/24/22/7289 |
| work_keys_str_mv | AT dangrong coordinatecorrectedandgraphconvolutionbasedhandposeestimationmethod AT fenggang coordinatecorrectedandgraphconvolutionbasedhandposeestimationmethod |