ML Anthology

Conditional Random People: Tracking Humans with CRFs and Grid Filters

Leonid Taycher, David Demirdjian, Trevor Darrell, Gregory Shakhnarovich
CVPR 2006 pp. 222-229
doi:10.1109/CVPR.2006.83 /cvpr/2006/taycher2006cvpr-conditional/

Abstract

We describe a state-space tracking approach based on a Conditional Random Field (CRF) model, where the observation potentials are learned from data. We find functions that embed both state and observation into a space where similarity corresponds to L1 distance, and define an observation potential based on distance in this space. This potential is extremely fast to compute and in conjunction with a grid-filtering framework can be used to reduce a continuous state estimation problem to a discrete one. We show how a state temporal prior in the grid-filter can be computed in a manner similar to a sparse HMM, resulting in real-time system performance. The resulting system is used for human pose tracking in video sequences.

CVPR Semantic Scholar

Cite

Text

Taycher et al. "Conditional Random People: Tracking Humans with CRFs and Grid Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.83

Markdown

[Taycher et al. "Conditional Random People: Tracking Humans with CRFs and Grid Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/taycher2006cvpr-conditional/) doi:10.1109/CVPR.2006.83

BibTeX

@inproceedings{taycher2006cvpr-conditional,
  title     = {{Conditional Random People: Tracking Humans with CRFs and Grid Filters}},
  author    = {Taycher, Leonid and Demirdjian, David and Darrell, Trevor and Shakhnarovich, Gregory},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {222-229},
  doi       = {10.1109/CVPR.2006.83},
  url       = {https://mlanthology.org/cvpr/2006/taycher2006cvpr-conditional/}
}