Estimation of 3D human hand poses with structured pose prior
Here, the authors present multistage estimation model embedding with structured pose prior (SPP), a novel coarse‐to‐fine framework for real‐time 3D hand estimation from single depth image. Authors’ main contributions can be summarised as follows: (i) The authors proposed SPP to enforce constraints o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5480 |
| _version_ | 1797684082401869824 |
|---|---|
| author | Fangtai Guo Zaixing He Shuyou Zhang Xinyue Zhao |
| author_facet | Fangtai Guo Zaixing He Shuyou Zhang Xinyue Zhao |
| author_sort | Fangtai Guo |
| collection | DOAJ |
| description | Here, the authors present multistage estimation model embedding with structured pose prior (SPP), a novel coarse‐to‐fine framework for real‐time 3D hand estimation from single depth image. Authors’ main contributions can be summarised as follows: (i) The authors proposed SPP to enforce constraints of canonical hand pose instead of original hand pose. (ii) The authors are the first to adopt under‐complete stacked denoising auto‐encoder (SDA) to construct pose prior by mapping canonical hand pose to latent representation. In the case of enforcing constraints of canonical hand pose, the authors empirically validate that under‐complete SDA outperforms over‐complete SDA in improving the hand estimation accuracy. (iii) The authors propose candidate keypoints patches (CKP) as intermediate data to conduct further hand pose refinement. Experimental evaluation on two publically available datasets shows that authors’ model is competitive both in accuracy and computation time. Especially, authors’ method placed first in the location of palm key‐point on both two datasets, and the high accuracy of hand palm key‐point plays an important role in many applications, such as that manipulator can grasp objects to specific coordinates with the guiding of human hand palm. |
| first_indexed | 2024-03-12T00:25:20Z |
| format | Article |
| id | doaj.art-903a5a02985741c992a72eab7e294b92 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:25:20Z |
| publishDate | 2019-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-903a5a02985741c992a72eab7e294b922023-09-15T10:41:12ZengWileyIET Computer Vision1751-96321751-96402019-12-0113868369010.1049/iet-cvi.2018.5480Estimation of 3D human hand poses with structured pose priorFangtai Guo0Zaixing He1Shuyou Zhang2Xinyue Zhao3The State Key Lab of Fluid Power & Mechatronic Systems, School of Mechanical Engineering, Zhejiang UniversityHangzhouPeople's Republic of ChinaThe State Key Lab of Fluid Power & Mechatronic Systems, School of Mechanical Engineering, Zhejiang UniversityHangzhouPeople's Republic of ChinaThe State Key Lab of Fluid Power & Mechatronic Systems, School of Mechanical Engineering, Zhejiang UniversityHangzhouPeople's Republic of ChinaThe State Key Lab of Fluid Power & Mechatronic Systems, School of Mechanical Engineering, Zhejiang UniversityHangzhouPeople's Republic of ChinaHere, the authors present multistage estimation model embedding with structured pose prior (SPP), a novel coarse‐to‐fine framework for real‐time 3D hand estimation from single depth image. Authors’ main contributions can be summarised as follows: (i) The authors proposed SPP to enforce constraints of canonical hand pose instead of original hand pose. (ii) The authors are the first to adopt under‐complete stacked denoising auto‐encoder (SDA) to construct pose prior by mapping canonical hand pose to latent representation. In the case of enforcing constraints of canonical hand pose, the authors empirically validate that under‐complete SDA outperforms over‐complete SDA in improving the hand estimation accuracy. (iii) The authors propose candidate keypoints patches (CKP) as intermediate data to conduct further hand pose refinement. Experimental evaluation on two publically available datasets shows that authors’ model is competitive both in accuracy and computation time. Especially, authors’ method placed first in the location of palm key‐point on both two datasets, and the high accuracy of hand palm key‐point plays an important role in many applications, such as that manipulator can grasp objects to specific coordinates with the guiding of human hand palm.https://doi.org/10.1049/iet-cvi.2018.54803D human handmultistage estimation modelSPPnovel coarse-to-fine frameworksingle depth imageauthors |
| spellingShingle | Fangtai Guo Zaixing He Shuyou Zhang Xinyue Zhao Estimation of 3D human hand poses with structured pose prior IET Computer Vision 3D human hand multistage estimation model SPP novel coarse-to-fine framework single depth image authors |
| title | Estimation of 3D human hand poses with structured pose prior |
| title_full | Estimation of 3D human hand poses with structured pose prior |
| title_fullStr | Estimation of 3D human hand poses with structured pose prior |
| title_full_unstemmed | Estimation of 3D human hand poses with structured pose prior |
| title_short | Estimation of 3D human hand poses with structured pose prior |
| title_sort | estimation of 3d human hand poses with structured pose prior |
| topic | 3D human hand multistage estimation model SPP novel coarse-to-fine framework single depth image authors |
| url | https://doi.org/10.1049/iet-cvi.2018.5480 |
| work_keys_str_mv | AT fangtaiguo estimationof3dhumanhandposeswithstructuredposeprior AT zaixinghe estimationof3dhumanhandposeswithstructuredposeprior AT shuyouzhang estimationof3dhumanhandposeswithstructuredposeprior AT xinyuezhao estimationof3dhumanhandposeswithstructuredposeprior |