ML Anthology

Full Body Tracking from Multiple Views Using Stochastic Sampling

Roland Kehl, Matthieu Bray, Luc Van Gool
CVPR 2005 pp. 129-136
doi:10.1109/CVPR.2005.165 /cvpr/2005/kehl2005cvpr-full/

Abstract

We present a novel approach for full body pose tracking using stochastic sampling. A volumetric reconstruction of a person is extracted from silhouettes in multiple video images. Then, an articulated body model is fitted to the data with stochastic meta descent (SMD) optimization. By comparing even a simplified version of SMD to the commonly used Levenberg-Marquardt method, we demonstrate the power of stochastic compared to deterministic sampling, especially in cases of noisy and incomplete data. Moreover, color information is added to improve the speed and robustness of the tracking. Results are shown for several challenging sequences, with tracking of 24 degrees of freedom in less than 1 second per frame.

CVPR Semantic Scholar

Cite

Text

Kehl et al. "Full Body Tracking from Multiple Views Using Stochastic Sampling." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.165

Markdown

[Kehl et al. "Full Body Tracking from Multiple Views Using Stochastic Sampling." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/kehl2005cvpr-full/) doi:10.1109/CVPR.2005.165

BibTeX

@inproceedings{kehl2005cvpr-full,
  title     = {{Full Body Tracking from Multiple Views Using Stochastic Sampling}},
  author    = {Kehl, Roland and Bray, Matthieu and Van Gool, Luc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {129-136},
  doi       = {10.1109/CVPR.2005.165},
  url       = {https://mlanthology.org/cvpr/2005/kehl2005cvpr-full/}
}