Title :
3D motion estimation of human by genetic algorithm
Author :
Pan, Chunhong ; Ma, Songde
Author_Institution :
Nat. Lab. of Pattern Recognition, Acad. of Sci., Beijing, China
Abstract :
In this paper we show that based on coplanar constraint the motion and structure of the articulated object can be determined within a scale factor from a monocular sequence of images. By genetic algorithm we achieve the unique robust numerical solution to motion estimation of the coplanar links. Then we apply the techniques to human motion analysis, and obtain the 3D motion data of joints, reanimate successfully the data. The experiments with simulated data and real images are included to demonstrate the validity of the theoretic results
Keywords :
biomechanics; genetic algorithms; image sequences; motion estimation; 3D human motion estimation; GA; coplanar constraint; coplanar links; genetic algorithm; human motion analysis; monocular image sequence; real images; scale factor; simulated data; unique robust numerical solution; Animation; Automation; Cameras; Genetic algorithms; Humans; Joints; Laboratories; Leg; Motion analysis; Motion estimation;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.905295
