CONF sba:mmmp:2005/IDIAP A Rao-Blackwellized Mixed State Particle Filter for Head Pose Tracking Ba, Silèye O. Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/papers/2005/sba-mmmp-2005.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/sba:rr05-35 Related documents ACM ICMI Workshop on Multimodal Multiparty Meeting Processing (MMMP) 2005 IDIAP-RR 05-35 This paper presents a Rao-Blackwellized mixed state particle filter for joint head tracking and pose estimation. Rao-Blackwellizing a particle filter consists of marginalizing some of the variables of the state space in order to exactly compute their posterior probability density function. Marginalizing variables reduces the dimension of the configuration space and makes the particle filter more efficient and requires a lower number of particles. Experiments were conducted on our head pose ground truth video database consisting of people engaged in meeting discussions. Results from these experiments demonstrated benefits of the Rao-Blackwellized particle filter model with fewer particles over the mixed state particle filter model. REPORT sba:rr05-35/IDIAP A Rao-Blackwellized Mixed State Particle Filter for Head Pose Tracking Ba, Silèye O. Odobez, Jean-Marc EXTERNAL http://publications.idiap.ch/attachments/reports/2005/sba-idiap-rr-05-35.pdf PUBLIC Idiap-RR-35-2005 2005 IDIAP Published in ACM ICMI Workshop on Multimodal Multiparty Meeting Processing (MMMP,',','), 2005 This paper presents a Rao-Blackwellized mixed state particle filter for joint head tracking and pose estimation. Rao-Blackwellizing a particle filter consists of marginalizing some of the variables of the state space in order to exactly compute their posterior probability density function. Marginalizing variables reduces the dimension of the configuration space and makes the particle filter more efficient and requires a lower number of particles. Experiments were conducted on our head pose ground truth video database consisting of people engaged in meeting discussions. Results from these experiments demonstrated benefits of the Rao-Blackwellized particle filter model with fewer particles over the mixed state particle filter model.