Survey on depth and RGB image-based 3D hand shape and pose estimation
The field of vision-based human hand three-dimensional (3D) shape and pose estimation has attracted significant attention recently owing to its key role in various applications, such as natural humancomputer interactions. With the availability of large-scale annotated hand datasets and the rapid dev...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2021-06-01
|
| Series: | Virtual Reality & Intelligent Hardware |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2096579621000280 |
| _version_ | 1818624242645729280 |
|---|---|
| author | Lin Huang Boshen Zhang Zhilin Guo Yang Xiao Zhiguo Cao Junsong Yuan |
| author_facet | Lin Huang Boshen Zhang Zhilin Guo Yang Xiao Zhiguo Cao Junsong Yuan |
| author_sort | Lin Huang |
| collection | DOAJ |
| description | The field of vision-based human hand three-dimensional (3D) shape and pose estimation has attracted significant attention recently owing to its key role in various applications, such as natural humancomputer interactions. With the availability of large-scale annotated hand datasets and the rapid developments of deep neural networks (DNNs), numerous DNN-based data-driven methods have been proposed for accurate and rapid hand shape and pose estimation. Nonetheless, the existence of complicated hand articulation, depth and scale ambiguities, occlusions, and finger similarity remain challenging. In this study, we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras. Related RGB-D cameras, hand datasets, and a performance analysis are also discussed to provide a holistic view of recent achievements. We also discuss the research potential of this rapidly growing field. |
| first_indexed | 2024-12-16T18:53:51Z |
| format | Article |
| id | doaj.art-1f9cace2c44a4108a179d1ea5b8df247 |
| institution | Directory Open Access Journal |
| issn | 2096-5796 |
| language | English |
| last_indexed | 2024-12-16T18:53:51Z |
| publishDate | 2021-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Virtual Reality & Intelligent Hardware |
| spelling | doaj.art-1f9cace2c44a4108a179d1ea5b8df2472022-12-21T22:20:35ZengKeAi Communications Co., Ltd.Virtual Reality & Intelligent Hardware2096-57962021-06-0133207234Survey on depth and RGB image-based 3D hand shape and pose estimationLin Huang0Boshen Zhang1Zhilin Guo2Yang Xiao3Zhiguo Cao4Junsong Yuan5Department of Computer Science and Engineering, State University of New York at Buffalo, NY 14260, USAYouTu Lab, Tencent, Shanghai 201101, ChinaDepartment of Computer Science, Fu Foundation School of Engineering and Applied Science, Columbia University, NY 10027, USANational Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China; Corresponding author.National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaDepartment of Computer Science and Engineering, State University of New York at Buffalo, NY 14260, USAThe field of vision-based human hand three-dimensional (3D) shape and pose estimation has attracted significant attention recently owing to its key role in various applications, such as natural humancomputer interactions. With the availability of large-scale annotated hand datasets and the rapid developments of deep neural networks (DNNs), numerous DNN-based data-driven methods have been proposed for accurate and rapid hand shape and pose estimation. Nonetheless, the existence of complicated hand articulation, depth and scale ambiguities, occlusions, and finger similarity remain challenging. In this study, we present a comprehensive survey of state-of-the-art 3D hand shape and pose estimation approaches using RGB-D cameras. Related RGB-D cameras, hand datasets, and a performance analysis are also discussed to provide a holistic view of recent achievements. We also discuss the research potential of this rapidly growing field.http://www.sciencedirect.com/science/article/pii/S2096579621000280Hand survey3D hand pose estimationHand shape reconstructionHand-object interactionsRGB-D cameras |
| spellingShingle | Lin Huang Boshen Zhang Zhilin Guo Yang Xiao Zhiguo Cao Junsong Yuan Survey on depth and RGB image-based 3D hand shape and pose estimation Virtual Reality & Intelligent Hardware Hand survey 3D hand pose estimation Hand shape reconstruction Hand-object interactions RGB-D cameras |
| title | Survey on depth and RGB image-based 3D hand shape and pose estimation |
| title_full | Survey on depth and RGB image-based 3D hand shape and pose estimation |
| title_fullStr | Survey on depth and RGB image-based 3D hand shape and pose estimation |
| title_full_unstemmed | Survey on depth and RGB image-based 3D hand shape and pose estimation |
| title_short | Survey on depth and RGB image-based 3D hand shape and pose estimation |
| title_sort | survey on depth and rgb image based 3d hand shape and pose estimation |
| topic | Hand survey 3D hand pose estimation Hand shape reconstruction Hand-object interactions RGB-D cameras |
| url | http://www.sciencedirect.com/science/article/pii/S2096579621000280 |
| work_keys_str_mv | AT linhuang surveyondepthandrgbimagebased3dhandshapeandposeestimation AT boshenzhang surveyondepthandrgbimagebased3dhandshapeandposeestimation AT zhilinguo surveyondepthandrgbimagebased3dhandshapeandposeestimation AT yangxiao surveyondepthandrgbimagebased3dhandshapeandposeestimation AT zhiguocao surveyondepthandrgbimagebased3dhandshapeandposeestimation AT junsongyuan surveyondepthandrgbimagebased3dhandshapeandposeestimation |