ML Anthology

Multi-View Appearance-Based 3D Hand Pose Estimation

Haiying Guan, Jae Sik Chang, Longbin Chen, Rogério Schmidt Feris, Matthew Turk
CVPRW 2006 pp. 154
doi:10.1109/CVPRW.2006.137 /cvprw/2006/guan2006cvprw-multiview/

Abstract

We describe a novel approach to appearance-based hand pose estimation which relies on multiple cameras to improve accuracy and resolve ambiguities caused by selfocclusions. Rather than estimating 3D geometry as most previous multi-view imaging systems, our approach uses multiple views to extend current exemplar-based methods that estimate hand pose by matching a probe image with a large discrete set of labeled hand pose images. We formulate the problem in a MAP (maximum a posteriori) framework, where the information from multiple cameras is fused to provide reliable hand pose estimation. Our quantitative experimental results show that correct estimation rate is much higher using our multi-view approach than using a single-view approach.

CVPRW Semantic Scholar

Cite

Text

Guan et al. "Multi-View Appearance-Based 3D Hand Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006. doi:10.1109/CVPRW.2006.137

Markdown

[Guan et al. "Multi-View Appearance-Based 3D Hand Pose Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006.](https://mlanthology.org/cvprw/2006/guan2006cvprw-multiview/) doi:10.1109/CVPRW.2006.137

BibTeX

@inproceedings{guan2006cvprw-multiview,
  title     = {{Multi-View Appearance-Based 3D Hand Pose Estimation}},
  author    = {Guan, Haiying and Chang, Jae Sik and Chen, Longbin and Feris, Rogério Schmidt and Turk, Matthew},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2006},
  pages     = {154},
  doi       = {10.1109/CVPRW.2006.137},
  url       = {https://mlanthology.org/cvprw/2006/guan2006cvprw-multiview/}
}