Simulation of Human Motion for Learning and Recognition

  • Gang Zheng
  • Wanqing Li
  • Philip Ogunbona
  • Liju Dong
  • Igor Kharitonenko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4304)


Acquisition of good quality training samples is becoming a major issue in machine learning based human motion analysis. This paper presents a method to simulate human body motion with the intention to establish a human motion corpus for learning and recognition. The simulation is achieved by a unique temporal-spatial-temporal decomposition of human body motion into actions, joint actions and actionlets based on the human kinematic model. The actionlet models the primitive moving phase of a joint and can be simulated based on the kinesiological study. A joint action is formed by proper concatenation of actionlets and an action is a group of synchronized joint actions. Methods for concatenation and synchronization are proposed in this paper for realistic simulation of human motion. Results on simulating ”running” verifies the feasibility of the proposed method.


Joint Action Action Recognition Human Motion Euler Angle Kinematic Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hu, W., Tan, T., Wang, L., Maybank, S.: A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems, Man and Cybernetics, Part C 34(3), 334–352 (2004)CrossRefGoogle Scholar
  2. 2.
    Zhang, X., Liu, Y., Huang, T.S.: Motion analysis of articulated objects from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(4), 625–636 (2006)CrossRefGoogle Scholar
  3. 3.
    Green, R.D., Guan, L.: Quantifying and recognizing human movement patterns from monocular video images – Part I: A new framework for modelling human motion. IEEE Trans. Circuits and Systems for Video Technology 14(2), 179–190 (2004)CrossRefGoogle Scholar
  4. 4.
    Boulic, R., Thalmann, N.M., Thalmann, D.: A global human walking model with real-time kinematic personification. The Visual Computer 6(6), 344–358 (1990)CrossRefGoogle Scholar
  5. 5.
    Xiao, Z., Yang, X., Zhang, J.J.: Motion data correction and extrapolation using physical constraints. In: IEEE Proceedings of the 9th International Conference on Information Visualisation (IV 2005), vol. 00, pp. 571–576 (2005)Google Scholar
  6. 6.
    Fang, A.C., Pollard, N.S.: Efficient synthesis of physically valid human motion. Proceedings of ACM Transactions on Graphics 22(3), 417–426 (2003)CrossRefGoogle Scholar
  7. 7.
    Faraway, J.: Human animation using nonparametric regression. Department of Statistics University of Michigan, Tech. Rep. 382 (2002)Google Scholar
  8. 8.
    Ijspeert, A., Nakanishi, J., Schaal, S.: Movement imitation with nonlinear dynamical systems in humanoid robots. In: Proceedings of the IEEE International Conference on Robotics and Automation, Washington, DC, May 2002, vol. 2, pp. 1398–1403 (2002)Google Scholar
  9. 9.
    Pettre, J., Simeon, T., Laumond, J.: Planning human walk in virtual environments, Lausanne, Switzerland, vol. 3, pp. 3048–3053 (September 2002)Google Scholar
  10. 10.
    Zatsiorsky, V.M.: Kinematics of Human Motion, 1st edn., Human Kinetics (1998)Google Scholar
  11. 11.
    Soderberg, G.L.: Kinesiology application to pathological motion, 1st edn. Williams & Wilkins (1986)Google Scholar
  12. 12.
    Tözeren, A.: Human Body Dynamics. Springer, Heidelberg (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gang Zheng
    • 1
  • Wanqing Li
    • 1
  • Philip Ogunbona
    • 1
  • Liju Dong
    • 1
    • 2
  • Igor Kharitonenko
    • 1
  1. 1.School of Information Technology and Computer ScienceUniversity of WollongongAustralia
  2. 2.College of Information EngineeringShenyang UniversityP.R. of China

Personalised recommendations