ML Anthology

Silhouette Lookup for Automatic Pose Tracking

Nicholas R. Howe
CVPR 2004 pp. 15-22
doi:10.1109/CVPR.2004.438 /cvpr/2004/howe2004cvpr-silhouette/

Abstract

Computers should be able to detect and track the articulated 3-D pose of a human being moving through a video sequence. Current tracking methods often prove slow and unreliable, and many must be initialized by a human operator before they can track a sequence. This paper introduces a simple yet effective algorithm for tracking articulated pose, based upon looking up observed silhouettes in a collection of known poses. The new algorithm runs quickly, can initialize itself without human intervention, and can automatically recover from critical tracking errors made while tracking previous frames in a video sequence.

PDF CVPR Semantic Scholar

Cite

Text

Howe. "Silhouette Lookup for Automatic Pose Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.438

Markdown

[Howe. "Silhouette Lookup for Automatic Pose Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/howe2004cvpr-silhouette/) doi:10.1109/CVPR.2004.438

BibTeX

@inproceedings{howe2004cvpr-silhouette,
  title     = {{Silhouette Lookup for Automatic Pose Tracking}},
  author    = {Howe, Nicholas R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {15-22},
  doi       = {10.1109/CVPR.2004.438},
  url       = {https://mlanthology.org/cvpr/2004/howe2004cvpr-silhouette/}
}