Motion Silhouette-Based Real Time Action Recognition

  • Marlon F. de Alcântara
  • Thierry P. Moreira
  • Helio Pedrini
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8259)


Most of the action recognition methods presented in the literature cannot be applied to real life situations. Some of them demand expensive feature extraction or classification processes, some require previous knowledge about starting and ending action times, others are just not scalable. In this paper, we present a real time action recognition method that uses information about the variation of the silhouette shape, which can be extracted and processed with little computational effort, and we apply a fast configuration of lightweight classifiers. The experiments are conducted on theWeizmann dataset and show that our method achieves the state-of-the-art accuracy in real time and can be scaled to work on different conditions and be applied several times simultaneously.


Action Recognition Video Stream Interest Point Human Action Recognition Slow Feature Analysis 
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.


  1. 1.
    Bregonzio, M., Xiang, T., Gong, S.: Fusing Appearance and Distribution Information of Interest Points for Action Recognition. Pattern Recognition 45(3), 1220–1234 (2012)CrossRefGoogle Scholar
  2. 2.
    Chaaraoui, A.A., Climent-Pérez, P., Flórez-Revuelta, F.: Silhouette-based Human Action Recognition using Sequences of Key Poses. Pattern Recognition Letters (2013)Google Scholar
  3. 3.
    Cortes, C., Vapnik, V.: Support-Vector Networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  4. 4.
    Cover, T., Hart, P.: Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory 13(1), 21–27 (1967)CrossRefzbMATHGoogle Scholar
  5. 5.
    Fathi, A., Mori, G.: Action Recognition by Learning Mid-Level Motion Features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  6. 6.
    Guo, K., Ishwar, P., Konrad, J.: Action Recognition From Video Using Feature Covariance Matrices. IEEE Transactions on Image Processing 22(6), 2479–2494 (2013)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Hsieh, C., Huang, P., Tang, M.: The Recognition of Human Action Using Silhouette Histogram. In: Reynolds, M. (ed.) Proceedings of Australasian Computer Science Conference, vol. 113, pp. 11–16. ACS, Perth (2011)Google Scholar
  8. 8.
    Junejo, I.N., Aghbari, Z.A.: Using SAX Representation for Human Action Recognition. Journal of Visual Communication and Image Representation 23(6), 853–861 (2012)CrossRefGoogle Scholar
  9. 9.
    KTH Royal Institute of Technology: KTH Action Dataset (2004),
  10. 10.
    Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. International Journal of Computer Vision 79(3), 299–318 (2008)CrossRefGoogle Scholar
  11. 11.
    Pearson, K.: Principal Component Analysis. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 6(2), 559 (1901)CrossRefGoogle Scholar
  12. 12.
    Saghafi, B., Rajan, D.: Human Action Recognition using Pose-based Discriminant Embedding. Image Communications 27(1), 96–111 (2012)Google Scholar
  13. 13.
    Sun, X., Chen, M., Hauptmann, A.: Action Recognition via Local Descriptors and Holistic Features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 58–65 (2009)Google Scholar
  14. 14.
    Ta, A.P., Wolf, C., Lavoue, G., Baskurt, A., Jolion, J.M.: Pairwise Features for Human Action Recognition. In: Proceedings of the 20th International Conference on Pattern Recognition, pp. 3224–3227. IEEE Computer Society, Washington, DC (2010)Google Scholar
  15. 15.
    Wang, S., Huang, K., Tan, T.: A Compact Optical Flowbased Motion Representation for Real-Time Action Recognition in Surveillance Scenes. In: Proceedings of the IEEE International Conference on Image Processing, Cairo, Egypt, pp. 1121–1124 (November 2009)Google Scholar
  16. 16.
    Weizmann Institute of Science: Weizmann Classification Database (2005),
  17. 17.
    Yi, S., Krim, H.: Capturing Human Activity by a Curve. In: Proceedings of the IEEE International Conference on Image Processing, Cairo, Egypt, pp. 3561–3564 (November 2009)Google Scholar
  18. 18.
    Zhang, Z., Tao, D.: Slow feature analysis for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(3), 436–450 (2012)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Marlon F. de Alcântara
    • 1
  • Thierry P. Moreira
    • 1
  • Helio Pedrini
    • 1
  1. 1.Institute of ComputingUniversity of CampinasCampinasBrazil

Personalised recommendations