CONF gatica05b-conf/IDIAP Tracking People in Meetings with Particles Gatica-Perez, Daniel Odobez, Jean-Marc Ba, Silèye O. Smith, Kevin C. Lathoud, Guillaume EXTERNAL https://publications.idiap.ch/attachments/reports/2004/rr-04-71.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/gatica05b Related documents Proc. Int. Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS,',','), invited paper 2005 Automatic meeting analysis is an emerging research field. In this paper, we present stochastic algorithms for tracking people in multi-sensor meeting rooms, for a number of relevant tasks, including tracking multiple people, tracking head pose towards analysis of visual focus-of-attention, and tracking speaker activity using audio-visual information. A Bayesian framework based on Sequential Monte Carlo methods is used in all cases. We discuss the advantages and limitations of our approach, illustrate it with results, and highlight a number of open issues. REPORT gatica05b/IDIAP Tracking People in Meetings with Particles Gatica-Perez, Daniel Odobez, Jean-Marc Ba, Silèye O. Smith, Kevin C. Lathoud, Guillaume EXTERNAL https://publications.idiap.ch/attachments/reports/2004/rr-04-71.pdf PUBLIC Idiap-RR-71-2004 2004 IDIAP Martigny, Switzerland in Proc. Int. Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS,',','), invited paper, Montreux, Apr. 2005. Automatic meeting analysis is an emerging research field. In this paper, we present stochastic algorithms for tracking people in multi-sensor meeting rooms, for a number of relevant tasks, including tracking multiple people, tracking head pose towards analysis of visual focus-of-attention, and tracking speaker activity using audio-visual information. A Bayesian framework based on Sequential Monte Carlo methods is used in all cases. We discuss the advantages and limitations of our approach, illustrate it with results, and highlight a number of open issues.