Multi-view Appearance-based 3D Hand Pose Estimation

Haiying Guan, Jae Sik Chang, Longbin Chen, Rogério Schmidt Feris, Matthew TurkWorkshops @ CVPR 2006 · OpenReview

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.
BibTeX
@inproceedings{guan2006multi,
  author = {Haiying Guan and Jae Sik Chang and Longbin Chen and Rogério Schmidt Feris and Matthew Turk},
  title = {{Multi-view Appearance-based 3D Hand Pose Estimation}},
  booktitle = {Workshops @ CVPR},
  year = {2006},
  url = {https://openreview.net/forum?id=7NpTkFYOFL},
}

Loading related content...

Figure