Human Motion Capture Data Segmentation Based on LLE Algorithm

Article Preview

Abstract:

In this paper, we propose the motion sequence segmentation based on LLE (Locally Linear Embedding) algorithm. The method is to reduce the dimension of the high dimension motion sequence to obtain one-dimension feature curve. Then we use the feature curve to achieve motion sequence segmentation. Simulation results demonstrate that this method can achieve motion sequences segmentation and improve the accuracy rate greatly compared with the traditional algorithm.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

481-485

Citation:

Online since:

April 2014

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] J. Barbic, A. Safonova and J.Y. Pan: Proceedings of Graphics Interface 2004, Canada, Vol. 62 (2004), pp.185-194.

Google Scholar

[2] S. Qu, R.H. Yu and L.D. Wu: Application Research of Computers. Vol. 28 (2011), pp.3128-3130.

Google Scholar

[3] S.X. Jing, Z. Wu, Z.Y. Huang: 2009 WRI World Congress on Computer Science and Information Engineering, Los Angeles (2009), pp.85-89.

Google Scholar

[4] Y.D. Yang, L.L. Wang: Journal of System Simulation. Vol. 19 (2007), pp.2229-2234, In Chinese.

Google Scholar

[5] J. Xiao, Y.T. Zhuang and F. Wu: Journal of Software. Vol. 19 (2008), pp.1995-2003, In Chinese.

Google Scholar

[6] J. Xiao, Y.T. Zhuang and F. Wu: Multimedia Tools and Applications. Vol. 47 (2010), pp.379-408.

Google Scholar

[7] S.J. Peng: International Conference on Computational Intelligence and Security, USA (2010), pp.223-226.

Google Scholar

[8] S.T. Roweis, L.K. Saul: Science, Vol. 290 (2000), pp.2323-2326.

Google Scholar

[9] S.J. Peng, X. Liu: Computer Science, Vol. 40 (2013), pp.303-308, In Chinese.

Google Scholar