CONF odobez-bmvc-03/IDIAP An Implicit Motion Likelihood for Tracking with Particle Filters Odobez, Jean-Marc Ba, Silèye O. Gatica-Perez, Daniel EXTERNAL http://publications.idiap.ch/attachments/reports/2003/odobez_2003_bmvc.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/odobez-rr-03-15 Related documents British Machine Vision Conference (BMVC) Lecture Notes in Computer Science 2003 Springer Verlag Norwich, UK Similar to RR-03-15. Particle filters are now established as the most popular method for visual tracking. Within this framework, it is generally assumed that the data are temporally independent given the sequence of object states. In this paper, we argue that in general the data are correlated, and that modeling such dependency should improve tracking robustness. To take data correlation into account, we propose a new model which can be interpreted as introducing a likelihood on implicit motion measurements. The proposed model allows to filter out visual distractors when tracking objects with generic models based on shape or color distribution representations, as shown by the reported experiments. REPORT odobez-rr-03-15/IDIAP An Implicit Motion Likelihood for Tracking with Particle Filters Odobez, Jean-Marc Ba, Silèye O. Gatica-Perez, Daniel EXTERNAL http://publications.idiap.ch/attachments/reports/2003/rr03-15.pdf PUBLIC Idiap-RR-15-2003 2003 IDIAP Martigny, Switzerland Published in British Machine Vision Conference (BMVC,',','), Norwich, 2003. Particle filters are now established as the most popular method for visual tracking. Within this framework, it is generally assumed that the data are temporally independent given the sequence of object states. In this paper, we argue that in general the data are correlated, and that modeling such dependency should improve tracking robustness. To take data correlation into account, we propose a new model which can be interpreted as introducing a likelihood on implicit motion measurements. The proposed model allows to filter out visual distractors when tracking objects with generic models based on shape or color distribution representations, as shown by the reported experiments.