TY - CONF T1 - Multimodal Tracking for Smart Videoconferencing and Video Surveillance T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on Y1 - 2007 A1 - Zotkin,Dmitry N A1 - Raykar,V.C. A1 - Duraiswami, Ramani A1 - Davis, Larry S. KW - (numerical KW - 3D KW - algorithm;smart KW - analysis;least KW - approximations;particle KW - arrays;nonlinear KW - cameras;multiple KW - Carlo KW - estimator;multimodal KW - filter;self-calibration KW - Filtering KW - least KW - likelihood KW - methods);teleconferencing;video KW - methods;image KW - microphone KW - MOTION KW - motion;Monte-Carlo KW - problem;particle KW - processing;video KW - signal KW - simulations;maximum KW - squares KW - surveillance; KW - surveillance;Monte KW - tracking;multiple KW - videoconferencing;video AB - Many applications require the ability to track the 3-D motion of the subjects. We build a particle filter based framework for multimodal tracking using multiple cameras and multiple microphone arrays. In order to calibrate the resulting system, we propose a method to determine the locations of all microphones using at least five loudspeakers and under assumption that for each loudspeaker there exists a microphone very close to it. We derive the maximum likelihood (ML) estimator, which reduces to the solution of the non-linear least squares problem. We verify the correctness and robustness of the multimodal tracker and of the self-calibration algorithm both with Monte-Carlo simulations and on real data from three experimental setups. JA - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on M3 - 10.1109/CVPR.2007.383525 ER -