Title :
Tracking articulated body by dynamic Markov network
Author :
Wu, Ying ; Hua, Gang ; Yu, Ting
Author_Institution :
Dept. of Electr. & Comput. Eng., Northwestern Univ., Evanston, IL, USA
Abstract :
A new method for visual tracking of articulated objects is presented. Analyzing articulated motion is challenging because the dimensionality increase potentially demands tremendous increase of computation. To ease this problem, we propose an approach that analyzes subparts locally while reinforcing the structural constraints at the mean time. The computational model of the proposed approach is based on a dynamic Markov network, a generative model which characterizes the dynamics and the image observations of each individual subpart as well as the motion constraints among different subparts. Probabilistic variational analysis of the model reveals a mean field approximation to the posterior densities of each subparts given visual evidence, and provides a computationally efficient way for such a difficult Bayesian inference problem. In addition, we design mean field Monte Carlo (MFMC) algorithms, in which a set of low dimensional particle filters interact with each other and solve the high dimensional problem collaboratively. Extensive experiments on tracking human body parts demonstrate the effectiveness, significance and computational efficiency of the proposed method.
Keywords :
Bayes methods; Markov processes; Monte Carlo methods; computer vision; maximum likelihood estimation; object detection; optical tracking; Bayesian inference problem; articulated body tracking; automatic video footage; dynamic Markov network; mean field Monte Carlo algorithms; mean time structural constraints; object tracking; particle filters; perceptual interfaces; smart video surveillance; visual tracking; Algorithm design and analysis; Bayesian methods; Character generation; Computational modeling; Computer networks; Inference algorithms; Markov random fields; Monte Carlo methods; Motion analysis; Subspace constraints;
Conference_Titel :
Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on
Conference_Location :
Nice, France
Print_ISBN :
0-7695-1950-4
DOI :
10.1109/ICCV.2003.1238471