Topic: Visual Hand Tracking Using Nonparametric Belief Propagation
By: Erik B. Sudderth (MIT), Michael I. Mandel (Columbia), William T. Freeman (MIT), Alan S. Willsky (MIT)
We have developed a three-dimensional geometric hand model suitable for visual tracking applications. The kinematic constraints implied by the model\\\'s joints have a probabilistic structure which is well described by a graphical model. Inference in this model is complicated by the hand\\\'s many degrees of freedom, as well as multimodal likelihoods caused by ambiguous image measurements. We use nonparametric belief propagation (NBP) to develop a tracking algorithm which exploits the graph\\\'s structure to control complexity, while avoiding costly discretization. NBP allows us to accurately model the multimodal uncertainties arising from ambiguous image observations, and provides the flexibility to capture complex interactions such as self-occlusions.
Questions and comments to the webmaster. This page is copyrighted by the Massachusetts Institute of Technology.