Body Language Based Individual Identification in Video Using Gait and Actions

  • Y. Pratheepan
  • P. H. S Torr
  • J V Condell
  • G. Prasad
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5099)


In intelligent surveillance systems, recognition of humans and their activities is generally the most important task. Two forms of human recognition can be useful: the determination that an object is from the class of humans (which is called human detection), and determination that an object is a particular individual from this class (this is called individual recognition). This paper focuses on the latter problem. For individual recognition, this report considers two different categories. First, individual recognition using “style of walk” i.e. gait and second “style of doing similar actions” in video sequences. The “style of walk” and “style of actions” are proposed as a cue to discriminate between two individuals. The “style of walk” and “style of actions” for each individual is called their “body language” information.


Video Sequence Image Sequence Dynamic Time Warping Individual Recognition Longe Common Subsequence 
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.
    Johansson, G.: Visual motion perception. Science American 232(6), 76–88 (1975)CrossRefGoogle Scholar
  2. 2.
    Cutting, J., Prott, D., Kozlowski, L.: A biomechanical invariant for gait perception. Journal of Experimental Psychology: Human Perception and Performance 4(3), 357–372 (1978)CrossRefGoogle Scholar
  3. 3.
    Little, J.J., Boyd, J.E.: Recognizing people by their gait: The shape of motion. Computer Vision Research 1(2), 1–32 (1998)Google Scholar
  4. 4.
    Nixon, M., Carter, J., Nash, J., Huang, P., Cunado, D., Stevenage, S.: Automatic gait recognition. IEE Colloquium Motion Analysis and Tracking, 31-36 (1999)Google Scholar
  5. 5.
    Johnson, A., Bobick, A.: Gait recognition using static, activity specific parameters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 423–430 (2001)Google Scholar
  6. 6.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Pearson Education, London Google Scholar
  7. 7.
    Sirovich,, Kirby, M.: Low dimensional procedure for the charecterization of human faces. Journal of Optical Society of America 4(3), 519–524 (1987)CrossRefGoogle Scholar
  8. 8.
    Nayar, S.K., Murase, H., Nene, S.A.: Parametric appearance representation in early visual learning, ch. 6. Oxford University Press, Oxford (1996)Google Scholar
  9. 9.
    Murase, H., Sakai, R.: Moving object recognition in eigenspace representation: gait analysis and lip reading. Pattern Recognition Letters 17(2), 155–162 (1996)CrossRefGoogle Scholar
  10. 10.
    He, Q., Debrunner, C.H.: Individual recognition from periodic activity using hidden markov models. In: Proceedings IEEE Workshop on Human Motion, pp. 47–52 (2000)Google Scholar
  11. 11.
    Guo, A., Siegelmann, H.: Time-warped longest common subsequence algorithm for music retrieval. In: Proc. Fifth International Conference on Music Information Retrieval, pp. 10–14 (2004)Google Scholar
  12. 12.
    Condell, J.V., Scotney, B.W., Morrow, P.J.: Adaptive Grid Refinement Procedures for Efficient Optical Flow Computation. International Journal of Computer Vision (1), 31–54 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Y. Pratheepan
    • 1
  • P. H. S Torr
    • 2
  • J V Condell
    • 1
  • G. Prasad
    • 1
  1. 1.School of Computing and Intelligent Systems, Faculty of Computing and EngineeringUniversity of Ulster at MageeLondonderry
  2. 2.Department of ComputingOxford Brookes University, WheatleyOxfordUK

Personalised recommendations