View-Invariant Human Action Detection Using Component-Wise HMM of Body Parts

  • Bhaskar Chakraborty
  • Marco Pedersoli
  • Jordi Gonzàlez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5098)


This paper presents a framework for view-invariant action recognition in image sequences. Feature-based human detection becomes extremely challenging when the agent is being observed from different viewpoints. Besides, similar actions, such as walking and jogging, are hardly distinguishable by considering the human body as a whole. In this work, we have developed a system which detects human body parts under different views and recognize similar actions by learning temporal changes of detected body part components. Firstly, human body part detection is achieved to find separately three components of the human body, namely the head, legs and arms. We incorporate a number of sub-classifiers, each for a specific range of view-point, to detect those body parts. Subsequently, we have extended this approach to distinguish and recognise actions like walking and jogging based on component-wise HMM learning.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ahmad, M., Lee, S.: Human action recognition using multi-view image sequence features. In: FGR, pp. 10–12 (2006)Google Scholar
  2. 2.
    Davis, J., Taylor, S.: Analysis and recognition of walking movements. In: Analysis and recognition of walking movements, Quebec, Canada, pp. 11–15 (2002)Google Scholar
  3. 3.
    Mendoza, M., Pérez de la Blanca, N.: Hmm-based action recognition using contour histograms. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds.) IbPRIA 2007. LNCS, vol. 4477, pp. 394–401. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Micilotta, A., Ong, E., Bowden, R.: Detection and tracking of humans by probabilistic body part assembly. In: British Machine Vision Conference, pp. 429–438 (2005)Google Scholar
  5. 5.
    Moeslund, T., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. In: CVIU 104, pp. 90–126 (2006)Google Scholar
  6. 6.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Transaction on Pattern Analysis and Machine Intelligence 23(4), 349–361 (2001)CrossRefGoogle Scholar
  7. 7.
    Park, S., Aggarwal, J.: Semantic-level understanding of human actions and interactions using event hierarchy, 2004. In: CVPR Workshop on Articulated and Non-Rigid Motion, Washington DC, USA (2004)Google Scholar
  8. 8.
    Ramanan, D., Forsyth, D., Zisserman, A.: Tracking people by learning their appearance. IEEE Transaction on PAMI 29(1), 65–81 (2007)Google Scholar
  9. 9.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: ICPR III, pp. 32–36 (2004)Google Scholar
  10. 10.
    Sigal, L., Black, M.: Humaneva: Synchronized video and motion capture dataset for evaluation of articulated human motion. Technical Report CS-06-08, Brown University (2006)Google Scholar
  11. 11.
    Sundaresan, A., RoyChowdhury, A., Chellappa, R.: A hidden markov model based framework for recognition of humans from gait sequences. In: ICIP, pp. 93–96 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Bhaskar Chakraborty
    • 1
  • Marco Pedersoli
    • 1
  • Jordi Gonzàlez
    • 2
  1. 1.Computer Vision Center & Dept. de Ciències de la Computació, Edifici OCampus UABBellaterraSpain
  2. 2.Institut de Robòtica i Informàtica Industrial (UPC – CSIC) BarcelonaSpain

Personalised recommendations