Human Action Classification Using SVM_2K Classifier on Motion Features

  • Hongying Meng
  • Nick Pears
  • Chris Bailey
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


In this paper, we study the human action classification problem based on motion features directly extracted from video. In order to implement a fast classification system, we select simple features that can be obtained from non-intensive computation. We also introduce the new SVM_2K classifier that can achieve improved performance over a standard SVM by combining two types of motion feature vector together. After learning, classification can be implemented very quickly because SVM_2K is a linear classifier. Experimental results demonstrate the method to be efficient and may be used in real-time human action classification systems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aggarwal, J.K., Cai, Q.: Human motion analysis: A review. Computer Vision and Image Understanding 73, 428–440 (1999)CrossRefGoogle Scholar
  2. 2.
    Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intell. 23, 257–267 (2001)CrossRefGoogle Scholar
  3. 3.
    Ogata, T., Tan, J.K., Ishikawa, S.: High-Speed Human Motion Recognition Based on a Motion History Image and an Eigenspace. IEICE Transactions on Information and Systems E89, 281–289 (2006)CrossRefGoogle Scholar
  4. 4.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proc. Int. Conf. Pattern Recognition (ICPR 2004), Cambridge, UK (2004)Google Scholar
  5. 5.
    Ke, Y., Sukthankar, R., Hebert, M.: Efficient visual event detection using volumetric features. In: Proceedings of International Conference on Computer Vision, Beijing, China, October 15-21, pp. 166–173 (2005)Google Scholar
  6. 6.
    Weinland, D., Ronfard, R., Boyer, E.: Motion history volumes for free viewpoint action recognition. In: IEEE International Workshop on Modeling People and Human Interaction (PHI 2005) (2005)Google Scholar
  7. 7.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines (and other kernel-based learning methods). Cambridge University Press, Cambridge (2000)Google Scholar
  8. 8.
    Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)Google Scholar
  9. 9.
    Wong, S.F., Cipolla, R.: Real-time adaptive hand motion recognition using a sparse bayesian classifier. In: ICCV-HCI, pp. 170–179 (2005)Google Scholar
  10. 10.
    Wong, S.-F., Cipolla, R.: Real-time interpretation of hand motions using a sparse bayesian classifier on motion gradient orientation images. In: Proceedings of the British Machine Vision Conference, Oxford, UK, vol. 1, pp. 379–388 (2005)Google Scholar
  11. 11.
    Meng, H., Shawe-Taylor, J., Szedmak, S., Farquhar, J.D.R.: Support vector machine to synthesise kernels. In: Winkler, J.R., Niranjan, M., Lawrence, N.D. (eds.) Deterministic and Statistical Methods in Machine Learning. LNCS, vol. 3635, pp. 242–255. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Farquhar, J.D.R., Hardoon, D.R., Meng, H., Shawe-Taylor, J., Szedmak, S.: Two view learning: SVM-2K, Theory and Practice. In: NIPS (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hongying Meng
    • 1
  • Nick Pears
    • 1
  • Chris Bailey
    • 1
  1. 1.Department of Computer ScienceThe University of YorkYorkUK

Personalised recommendations