CONF gatica02d-conf/IDIAP Audio-Visual Speaker Tracking with Importance Particle Filters Gatica-Perez, Daniel Lathoud, Guillaume McCowan, Iain A. Odobez, Jean-Marc Moore, Darren EXTERNAL https://publications.idiap.ch/attachments/reports/2002/rr02-37.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/gatica02d Related documents IEEE International Conference on Image Processing (ICIP) 2003 We present a probabilistic methodology for audio-visual (AV) speaker tracking, using an uncalibrated wide-angle camera and a microphone array. The algorithm fuses 2-D object shape and audio information via importance particle filters (I-PFs,',','), allowing for the asymmetrical integration of AV information in a way that efficiently exploits the complementary features of each modality. Audio localization information is used to generate an importance sampling (IS) function, which guides the random search process of a particle filter towards regions of the configuration space likely to contain the true configuration (a speaker). The measurement process integrates contour-based and audio observations, which results in reliable head tracking in realistic scenarios. We show that imperfect single modalities can be combined into an algorithm that automatically initializes and tracks a speaker, switches between multiple speakers, tolerates visual clutter, and recovers from total AV object occlusion, in the context of a multimodal meeting room. REPORT gatica02d/IDIAP Audio-Visual Speaker Tracking with Importance Particle Filters Gatica-Perez, Daniel Lathoud, Guillaume McCowan, Iain A. Odobez, Jean-Marc Moore, Darren EXTERNAL https://publications.idiap.ch/attachments/reports/2002/rr02-37.pdf PUBLIC Idiap-RR-37-2002 2002 IDIAP We present a probabilistic methodology for audio-visual (AV) speaker tracking, using an uncalibrated wide-angle camera and a microphone array. The algorithm fuses 2-D object shape and audio information via importance particle filters (I-PFs,',','), allowing for the asymmetrical integration of AV information in a way that efficiently exploits the complementary features of each modality. Audio localization information is used to generate an importance sampling (IS) function, which guides the random search process of a particle filter towards regions of the configuration space likely to contain the true configuration (a speaker). The measurement process integrates contour-based and audio observations, which results in reliable head tracking in realistic scenarios. We show that imperfect single modalities can be combined into an algorithm that automatically initializes and tracks a speaker, switches between multiple speakers, tolerates visual clutter, and recovers from total AV object occlusion, in the context of a multimodal meeting room.