Title :
3D non-rigid motion estimation using the improved simulated annealing algorithm
Author :
Huang, Wen-Qing ; Zhang, Yun-Hua ; Wang, Ya-Ming ; Cheng, Hong-Wei
Author_Institution :
Coll. of Biosystem Eng. & Food Sci., Zhejiang Univ., Hangzhou, China
Abstract :
An approach to 3D non-rigid motion estimation using improved simulated annealing algorithm (SA) from monocular image sequence is proposed. First, the affine motion model of non-rigid object is presented. Then, the energy function, which can reflect the joint probability distribution of motion parameters and the constraints relation of local 3D motion parameters, is established in Markov random field (MRF). After the limitations of classical SA and the features of motion-parameters estimation are analyzed, an improved SA is used to minimize the energy function. Experiment results from two synthetic image sequences demonstrate the robustness of solutions and the feasibility of our algorithm.
Keywords :
Markov processes; feature extraction; image sequences; least squares approximations; motion estimation; object recognition; random processes; simulated annealing; statistical distributions; 3D nonrigid motion estimation; Markov random field; constraint relation; energy function; feature analysis; joint probability distribution; least squared method; monocular image sequence; motion model; nonrigid object; simulated annealing; Deformable models; Educational institutions; Image motion analysis; Image sequences; Motion analysis; Motion estimation; Parametric statistics; Robustness; Shape; Simulated annealing; 3D non-rigid Motion; MRF; Simulated annealing algorithm; least squared method;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527885
