CONF ba-icpr-2004/IDIAP A probabilistic framework for joint head tracking and pose estimation Ba, Silèye O. Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/reports/2004/odobez_2004_icpr2.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/odobez-rr-03-78 Related documents 17th Int. Conf. Pattern Recognition (ICPR) 4 2004 Cambridge, UK August 2004 Similar to RR-03-78. Head Tracking and pose estimation are usually considered as two sequential and separate problems: pose is estimated on the head patch provided by a tracking module. However, precision in head pose estimation is dependent on tracking accuracy which itself could benefit from the head orientation knowledge. Therefore, this work considers head tracking and pose estimation as two coupled problems in a probabilistic setting. Head pose models are learned and incorporated into a mixed-state particle filter framework for joint head tracking and pose estimation. Experimental results on real sequences show the effectiveness of the method in estimating more stable and accurate pose values. REPORT odobez-rr-03-78/IDIAP A Probabilistic Framework for Joint Head Tracking and Pose Estimation Ba, Silèye O. Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/reports/2003/rr03-78.pdf PUBLIC Idiap-RR-78-2003 2003 IDIAP Martigny, Switzerland Published in International Conference on Pattern Recognition (ICPR,',','), 2004 Head Tracking and pose estimation are usually considered as two sequential and separate problems: pose is estimated on the head patch provided by a tracking module. However, precision in head pose estimation is dependent on tracking accuracy which itself could benefit from the head orientation knowledge. Therefore, this work considers head tracking and pose estimation as two coupled problems in a probabilistic setting. Head pose models are learned and incorporated into a mixed-state particle filter framework for joint head tracking and pose estimation. Experimental results on real sequences show the effectiveness of the method in estimating more stable and accurate pose values.