Title: A novel automatic motion capture data recognition method based on statistics learning and subspace
Authors: Jian Xiang, Hongli Zhu
Addresses: School of Information and Electronic Engineering, ZheJiang University of Science and Technology, Hangzhou 310023, China. ' College of Information and Electrical Engineering, ZheJiang University City College, Hangzhou 310015, China
Abstract: In this paper, we propose a motion recognition method based on motion capture data. To recognise motion type, a generalised Isomap non-linear dimension reduction based on Radius Basis Function (RBF) networks and feature extraction is used to project original motion data into low-dimensional subspace. Then, some motion-type classifiers are learned for each human|s joint in subspace. Then, we use ensemble reinforcement learning to enhance learning results. Experimental results show that our methods are effective for 3D human motion recognition and control.
Keywords: motion control; RBF networks; feature extraction; reinforcement learning; motion capture data; motion recognition; neural networks; motion classification; human joints.
International Journal of Computer Applications in Technology, 2010 Vol.38 No.1/2/3, pp.49 - 54
Available online: 16 Jul 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article