A Real-Time System for Head Tracking and Pose Estimation
Abstract
Driver’s visual attention provides important clues about his/ her activities and awareness. To monitor driver’s awareness, this paper proposes a real-time person-independent head tracking and pose estimation system using a monochromatic camera. The tracking and head-pose estimation tasks are formulated as regression problems. Three regression methods are proposed: (i) individual mapping on images for head tracking, (ii) direct mapping to subspace for head tracking, which predicts a subspace from one sample, and (iii) semantic piecewise regression for head-pose estimation. The approaches are evaluated on standard databases, and on several videos collected in vehicle environments.
Cite
Text
Zhang et al. "A Real-Time System for Head Tracking and Pose Estimation." European Conference on Computer Vision Workshops, 2010. doi:10.1007/978-3-642-35749-7_26Markdown
[Zhang et al. "A Real-Time System for Head Tracking and Pose Estimation." European Conference on Computer Vision Workshops, 2010.](https://mlanthology.org/eccvw/2010/zhang2010eccvw-realtime/) doi:10.1007/978-3-642-35749-7_26BibTeX
@inproceedings{zhang2010eccvw-realtime,
title = {{A Real-Time System for Head Tracking and Pose Estimation}},
author = {Zhang, Zengyin and Kim, Minyoung and De la Torre, Fernando and Zhang, Wende},
booktitle = {European Conference on Computer Vision Workshops},
year = {2010},
pages = {329-341},
doi = {10.1007/978-3-642-35749-7_26},
url = {https://mlanthology.org/eccvw/2010/zhang2010eccvw-realtime/}
}