Maximum Intensity Block Code for Action Recognition in Video Using Tree-based Classifiers

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 325)


Human action recognition is a broad research area in computer vision community. Human actions are identified by connotation of body movements. In this paper, an action recognition approach based on maximum motion identification is proposed. Maximum Intensity Block Code (MIBC) is extracted as features. The experiments were carried out using Weizmann action dataset considering nine activities viz (walking, running, jumping, side, bend, waving one hand, waving both hands, jump-in-place-on-two-legs or pjump and skip) and the various tree based classifier like Random Forest, Naive Bayes, Random Tree, and Decision Tree (J48) utilized. In the experimental results, random forest classifier showed the best performance with an overall accuracy rate of 95.3 % which outperforms other algorithms.


Video surveillance Action recognition Frame difference Random forest Naive Bayes Random tree Decision tree 



The authors gratefully acknowledge University Grants Commission of India [F. No. 41-636/2012 (SR)], for funding this work.


  1. 1.
    R. Poppe, Vision-based human motion analysis: an overview. Comput. Vis. Image Underst. (CVIU) 108(1–2), 4–18 (2007)CrossRefGoogle Scholar
  2. 2.
    R. Poppe, A survey on vision-based human action recognition. IVC 28, 976–990 (2010)Google Scholar
  3. 3.
    P. Turaga, R. Chellappa, S. Venkatramana Subrahmanian, O. Octavian Udrea, Machine recognition of human activities: a survey. IEEE Trans. Circ. Syst. Video Technol. 18(11), 1473–1488 (2008)CrossRefGoogle Scholar
  4. 4.
    L. Wang, Y. Wang, T. Jiang, D. Zhao, W. Gao, Learning discriminative features for fast frame-based action recognition. Pattern Recogn. 46(7), 1832–1840 (2013)Google Scholar
  5. 5.
    K. Reddy, J. Liu, M. Shah, Incremental action recognition using feature-tree, in International Conference on Computer Vision (2009)Google Scholar
  6. 6.
    Z. Lin, Z. Jian, L. Davis, Recognizing actions by shape motion prototype trees, in International Conference on Computer Vision (2009)Google Scholar
  7. 7.
    F. Zhu, Ling Shao, Mingxiu Lin.: Multi-view action recognition using local similarity random forests and sensor fusion. Pattern Recogn. Lett. 34(1), 20–24 (2013)CrossRefGoogle Scholar
  8. 8.
    H. Zhao, Z. Liu, Human action recognition based on non-linear SVM decision tree. J. Computat. Infor. Syst. 7, 2461–2468 (2011)Google Scholar
  9. 9.
    D. Wu, L. Shao, Silhouette analysis-based action recognition via exploiting human poses. IEEE Trans. Circuits Syst. Video Techn. 23(2), 236–243 (2013)Google Scholar
  10. 10.
    W. Zhang, Y. Zhang, C. Gao, J. Zhou, Action recognition by joint spatial-temporal motion feature. J. Appl. Math. (2013)Google Scholar
  11. 11.
    L. Wang, Y. Wang, T. Jiang, D. Zhao, W. Gao, Learning discriminative features for fast frame based action recognition. Pattern Recogn. 46(7), 1832–1840 (2013)CrossRefGoogle Scholar
  12. 12.
    M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri, Actions as space-time shapes, in Proceedings of IEEE International Conferences on Computer Vision (2005), pp. 1395–1402Google Scholar
  13. 13.
    L. Breiman, Random forest. Mach. Learn. 45(1), 5–32 (2001)CrossRefMATHGoogle Scholar
  14. 14.
    P. Langley, W. Iba, K. Thompson, An analysis of bayesian classifiers, in Proceedings of the Tenth National Conference on Artificial Intelligence (1992), pp. 223–228Google Scholar
  15. 15.
    J.R. Quinlan, C4.5: Programs for Machine Learning (Morgan Kaufmann Publishers, Burlington, 1993)Google Scholar
  16. 16.
    I.H. Witten, E. Frank, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations (Morgan Kaufmann Publishers, Burlington, 1999)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringAnnamalai UniversityCuddaloreIndia

Personalised recommendations