Loading...

3D hand pose estimation using RGBD images and hybrid deep learning networks

Mofarreh Bonab, M ; Sharif University of Technology | 2022

100 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/s00371-021-02263-7
  3. Publisher: Springer Science and Business Media Deutschland GmbH , 2022
  4. Abstract:
  5. Hand pose estimation is one of the most attractive research areas for image processing. Among the human body parts, hands are particularly important for human–machine interactions. The advent of commercial depth cameras along with the rapid growth of deep learning has made great progress in all image processing fields, especially in hand pose estimation. In this study, using depth data, we introduce two hybrid deep neural networks to estimate 3D hand poses with fewer computations and higher accuracy compared with their counterparts. Due to the fact that the dimensions of data are reduced while passing through successive layers of networks, which causes data to be lost, we use the concept of residual network to compensate this phenomenon. By incorporating data from several views, the estimated poses are more robust in the occlusions. Evaluation results show the superiority of the proposed networks in terms of accuracy and implementation complexity. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature
  6. Keywords:
  7. 3D Hand pose estimation ; Deep learning ; Depth data ; Residual networks ; RGBD images ; Deep neural networks ; Image processing ; Network layers ; 3D hand pose estimations ; Depth camera ; Evaluation results ; Hand pose estimations ; Human bodies ; Implementation complexity ; Learning network ; Rapid growth ; Deep learning
  8. Source: Visual Computer ; Volume 38, Issue 6 , 2022 , Pages 2023-2032 ; 01782789 (ISSN)
  9. URL: https://link.springer.com/article/10.1007/s00371-021-02263-7