Head Pose Estimation via Probabilistic High-Dimensional Regression
Best Student Paper Award (2nd place)
V. Drouard, S. Ba, G. Evangelidis, A. Deleforge, and R. Horaud
IEEE International Conference on Image Processing (ICIP’15)
Extended version published in IEEE Transactions on Image Processing, available on HAL
Also, please visit our High-dimensional regression webpage
| We address the problem of head pose estimation with three degrees of freedom (pitch, yaw, roll) from a single image. Pose estimation is formulated as a high-dimensional to low-dimensional mixture of linear regression problem. We propose a method that maps HOG-based descriptors, extracted from face bounding boxes, to corresponding head poses. To account for errors in the observed bounding-box position, we learn regression parameters such that a HOG descriptor is mapped onto the union of a head pose and an offset, such that the latter optimally shifts the bounding box towards the actual position of the face in the image. The performance of the proposed method is assessed on publicly available datasets. The experiments that we carried out show that a relatively small number of locally-linear regression functions is sufficient to deal with the non-linear mapping problem at hand. Comparisons with state-of-the-art methods show that our method outperforms several other techniques. |  |
Publication
 Download PDF |
Head Pose Estimation via Probabilistic High-Dimensional Regression V. Drouard, S. Ba, G. Evangelidis, A. Deleforge, R. Horaud IEEE ICIP, 2015Bibtex: @inproceedings{drouard2015head,
TITLE = {{Head Pose Estimation via Probabilistic High-Dimensional Regression}},
AUTHOR = {Drouard, Vincent and Ba, Sil{\`e}ye and Evangelidis, Georgios and Deleforge, Antoine and Horaud, Radu},
BOOKTITLE = {{IEEE International Conference on Image Processing}},
ADDRESS = {Quebec City, QC, Canada},
SERIES = {Proceedings of the IEEE International Conference on Image Processing},
NUMBER = {4624 - 4628},
YEAR = {2015},
MONTH = Sep,
DOI = {10.1109/ICIP.2015.7351683}
}
article{drouard2017head,
TITLE = {Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions},
AUTHOR = {Drouard, Vincent and Horaud, Radu and Deleforge, Antoine and Ba, Sil{\`e}ye and Evangelidis, Georgios},
JOURNAL = {{IEEE Transactions on Image Processing}},
VOLUME = {26},
NUMBER = {3},
PAGES = {1428 - 1440},
YEAR = {2017},
MONTH = Jan,
DOI = {10.1109/TIP.2017.2654165}
}
|
Results on Head Pose Estimation
Code
A package containing Matlab code can be found here. The code contains a trained model on the Prima Head Pose database that can be found here.
Acknowledgement
Support from both the EU-FP7 ERC Advanced Grant VHIA (\#340113) and STREP project EARS (\#609645) is greatly acknowledged.
