Feature Space Analysis of Human Gait Dynamics in Single View Video

  • Sin, Bong-Kee (Dept. of IT Convergence and Applications Eng., Pukyong National University) ;
  • Kwon, Ki-Ryong (Dept. of IT Convergence and Applications Eng., Pukyong National University)
  • 투고 : 2010.11.30
  • 심사 : 2010.12.28
  • 발행 : 2010.12.30

초록

This paper proposes a new video-based method of analyzing human gait which is a highly variable dynamic process. It captures a human gait of varying directions as a trajectory in the phase space. The proposed method includes two options of a stochastic process model and a self-organizing feature map as the tool of feature space representation and analysis. Test results show that the model is highly intuitive and we believe it can contribute to our understanding of human activity as well as gait behavior.

키워드

참고문헌

  1. J. Aggarwal and Q. Cai, "Human motion analysis–a review," Computer Vision and Image Understanding, Vol. 73, No. 3, pp. 428-440, 1999. https://doi.org/10.1006/cviu.1998.0744
  2. H.-I. Suk and B.-K. Sin, "HMM-Based Gait Recognition with Human Profiles," In Proc. of Joint IAPR SSPR 2006 / SPR2006, Hong Kong, pp. 596–603, 2006.
  3. Z. Ghahramani and M. Jordan, "Factorial Hidden Markov Models," Machine Learning, Vol.29, pp. 245-275, 1997. https://doi.org/10.1023/A:1007425814087
  4. T. Kohonen, Self-Organizing Maps, Springer, Berlin, Heidelberg, 1995.
  5. C.-Y. Kim and B.-K. Sin, "Human Gait Analysis using Self-Organizing Map," In Proc. of China, Japan and Korea Joint Workshop on Pattern Recognition 2009, Nanjing, China, 2009.
  6. K. Murphy, Dynamic Bayesian network: Representation, Inference and Learning, Ph.D. Dissertation, University of California, Berkeley, 2002.
  7. Bong-Kee Sin, "DP-based inference algorithms for Factorial HMMs," In Proc. of Korea Multimedia Society Spring Conference, Cheongju, Korea, May 2010. (in Korean)