A decentralized probabilistic approach to articulated body tracking

We present a novel decentralized probabilistic approach to visual tracking of articulated objects. Analyzing articulated motion is challenging because (1) the high degrees of freedom potentially demands tremendous computation, and (2) the solution is confronted by the numerous local optima existed in a high dimensional parametric space. To ease these problems, we propose a decentralized approach that analyzes limbs locally and reinforces the spatial coherence among them at the same time. The computational model of the proposed approach is based on a dynamic Markov network, a generative model which characterizes the dynamics, the image observations of each individual limb, as well as the spatial coherence among them. Probabilistic mean field variational analysis provides an efficient computational diagram to obtain the approximate inference of the motion posteriors. We thus design the mean field Monte Carlo (MFMC) algorithm, where a set of low dimensional particle filters interact with one another and solve the high dimensional problem collaboratively. We also present a variational maximum a posteriori (MAP) algorithm, which has a rigorous theoretic foundation, to approach to the optimal MAP estimate of the articulated motion. Both algorithms achieve linear complexity w.r.t. the number of articulated subparts and have the potential of parallel computing. Experiments on human body tracking demonstrate the significance, effectiveness and efficiency of the proposed methods.