Title :
Viewpoint Invariant Reconstruction of 3D Human Skeleton from Monocular Images
Author :
Htike, Zaw Zaw ; Egerton, Simon ; Chow, Kuang Ye
Author_Institution :
Sch. of Inf. Technol., Monash Unversity, Malaysia
Abstract :
We present a fast, robust, fault-tolerant and nonparametric approach to reconstruct 3D human skeleton model from single images, regardless of the viewpoint of the camera relative to the observed person. The system achieves high degree of tolerance using search-based inference and probabilistic joint labeling. The system achieves 100% view invariance using a pruning-based parallel search algorithm.
Keywords :
bone; fault tolerance; image reconstruction; inference mechanisms; probability; search problems; solid modelling; 3D Human Skeleton; fault-tolerant approach; image reconstruction; monocular images; nonparametric approach; probabilistic joint labeling; pruning-based parallel search algorithm; search-based inference; viewpoint invariant reconstruction; Cameras; Humans; Joints; Mathematical model; Solid modeling; Three dimensional displays; 3D human skeleton; Viewpoint invariant; pose reconstruction;
Conference_Titel :
Intelligent Environments (IE), 2010 Sixth International Conference on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-7836-1
Electronic_ISBN :
978-0-7695-4149-5
