Open Science Research Excellence
%0 Journal Article
%A Sanghyeok Oh and  Keechul Jung
%D 2009 
%J  International Journal of Computer, Electrical, Automation, Control and Information Engineering
%B World Academy of Science, Engineering and Technology
%I International Science Index 36, 2009
%T View-Point Insensitive Human Pose Recognition using Neural Network and CUDA
%U http://waset.org/publications/5347
%V 36
%X Although lots of research work has been done for
human pose recognition, the view-point of cameras is still critical
problem of overall recognition system. In this paper, view-point
insensitive human pose recognition is proposed. The aims of the
proposed system are view-point insensitivity and real-time processing.
Recognition system consists of feature extraction module, neural
network and real-time feed forward calculation. First, histogram-based
method is used to extract feature from silhouette image and it is
suitable for represent the shape of human pose. To reduce the
dimension of feature vector, Principle Component Analysis(PCA) is
used. Second, real-time processing is implemented by using Compute
Unified Device Architecture(CUDA) and this architecture improves
the speed of feed-forward calculation of neural network. We
demonstrate the effectiveness of our approach with experiments on
real environment.
%P 2911 - 2914