ML Anthology

Online Learning of Robust Facial Feature Trackers

Tim Sheerman-Chase, Eng-Jon Ong, Richard Bowden
ICCVW 2009 pp. 1386-1392
doi:10.1109/ICCVW.2009.5457450 /iccvw/2009/sheermanchase2009iccvw-online/

Abstract

This paper presents a head pose and facial feature estimation technique that works over a wide range of pose variations without a priori knowledge of the appearance of the face. Using simple LK trackers, head pose is estimated by Levenberg-Marquardt (LM) pose estimation using the feature tracking as constraints. Factored sampling and RANSAC are employed to both provide a robust pose estimate and identify tracker drift by constraining outliers in the estimation process. The system provides both a head pose estimate and the position of facial features and is capable of tracking over a wide range of head poses.

PDF ICCVW Semantic Scholar

Cite

Text

Sheerman-Chase et al. "Online Learning of Robust Facial Feature Trackers." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457450

Markdown

[Sheerman-Chase et al. "Online Learning of Robust Facial Feature Trackers." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/sheermanchase2009iccvw-online/) doi:10.1109/ICCVW.2009.5457450

BibTeX

@inproceedings{sheermanchase2009iccvw-online,
  title     = {{Online Learning of Robust Facial Feature Trackers}},
  author    = {Sheerman-Chase, Tim and Ong, Eng-Jon and Bowden, Richard},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {1386-1392},
  doi       = {10.1109/ICCVW.2009.5457450},
  url       = {https://mlanthology.org/iccvw/2009/sheermanchase2009iccvw-online/}
}