Title :
A multi-objective immune algorithm for human motion tracking
Author :
Han, Hong ; Feng, Guangjie ; Gou, Jingxiang ; Wang, Rui
Author_Institution :
Key Lab. of Intell. Perception & Image Understanding of Minist. of Educ. of China, Xidian Univ., Xi´´an, China
Abstract :
A crucial challenge in human body tracking is the high degrees of freedom (up to around 40) to be recovered. A method based on multi-objective optimization algorithm is presented here to tackle this problem. In our multi-objective optimization based human body tracking framework, tracking is considered as two functions´ co-optimization problem where the aim is to optimize the matching functions between the model projection and the image observation. Experiments on 3D human motion tracking demonstrate the effectiveness and computational efficiency of the proposed tracking method.
Keywords :
image matching; motion estimation; object tracking; optimisation; solid modelling; 3D human motion tracking; computational efficiency; cooptimization problem; human body tracking; image observation; matching functions; model projection; multiobjective immune optimization algorithm; Biological system modeling; Humans; Immune system; Joints; Optimization; Three dimensional displays; Tracking; body tracking; immune algorithm; multi-objective optimization algorithm;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6002110
