In this paper, we present a new method of recognizing human actions by inference of stochastic grammars for the purpose of automatic analysis of nonverbal actions of human beings. We applied the principle that a human action can be defined as a combination of multiple articulation movements. We measure and quantize each articulation movements in 3D and represent two sets of 4-connected chain code for xy and zy projection planes, so that they are appropriate for the stochastic grammar inference method. This recognition method is tested by using 900 actions of human upper body. The result shows a comparatively successful achievement of 93.8% recognition rate through the experiments of 8 action types of head and 84.9% recognition rate of 60 action types of upper body.


Recognition Rate Action Type Human Action Recognition Chain Code Grammatical Inference 
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.
    Becker, D.A.: Sensei: A Real-Time Recognition, Feedback and Training System for T’ai Chi Gestures. MIT Media Lab Perceptual Computing Group TR 426 (1997)Google Scholar
  2. 2.
    Moeslund, T.B., Granum, E.: ‘A Survery of Computer Vision-Based Human Motion Capture. Computer Vision and Image Understanding 81(3), 231–268 (2001)zbMATHCrossRefGoogle Scholar
  3. 3.
    Inanov, Y.A.: Application of stochastic grammars to understanding action, MIT thesis (1998)Google Scholar
  4. 4.
    Hong, P., Turk, M., Huang, T.: Gesture Modeling and Recognition Using Finite State Machines. In: Int’l. Conference on Gesture Recognition, Grenoble, France (2000)Google Scholar
  5. 5.
    Frey, S.: Das Berner System zur Untersuchung nonverbaler Interaktion. Methoden der Analyse von Face-to-Face-Situationen, Stuttgart, Metzler, pp. 203–236 (1981)Google Scholar
  6. 6.
    Gonzalez, R.C., Thomason, M.G.: Syntactic Pattern Recognition, pp. 177–270. Addison-Wesley Publishing Company, Reading (1978)zbMATHGoogle Scholar
  7. 7.
    Fu, K.S.: Syntactic Methods in Pattern Recognition, pp. 54–55 & 124- 229. Academic Press, London (1974)zbMATHGoogle Scholar
  8. 8.
    Doest, H.: Stochastic Grammars: Consistency and Inference. Beoorderlingscommissie, 53–84 (1994)Google Scholar
  9. 9.
    Gronfors, T., Juhola, M.: Experiments and comparison of inference methods of regular grammars. IEEE Trans. on Systems, Man and Cybernetics 22(4), 821–826 (1992)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Cruz-Alcazar, P.P., Vidal-Ruiz, E.: Modeling musical style using grammatical inference techniques: a tool for classifying and generating melodies. In: Third International Conference on Web Delivering of Music, pp. 77–84 (2003)Google Scholar
  11. 11.
    Vidal, E.: Application of the error-correcting grammatical inference algorithm (ECGI) to planar shape recognition. IEE Colloquium on Grammatical Inference: Theory, Applications and Alternatives, 24/1–24/10 (1993)Google Scholar
  12. 12.
    Atwell, E., et al.: Multi-level disambiguation grammar inferred from English corpus, treebank, and dictionary. IEE Colloquium on Grammatical Inference: Theory, Applications and Alternatives, 9/1–9/7 (1993)Google Scholar
  13. 13.
    Galiano, I., Segarra, E.: The application of k-testable languages in the strict sense to phone recognition in automatic speech recognition. IEE Colloquium on Grammatical Inference: Theory, Applications and Alternatives, 22/1–22/7 (1993)Google Scholar
  14. 14.
    Munkelt, O., et al.: A model driven 3D image interpretation system applied to person detection in video images. In: 14th ICPR, vol. 98, pp. 70–73 (1998)Google Scholar
  15. 15.
    Bull, P.E.: Posture and Gesture, pp. 163–187. Pergamon Press, Oxford (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Kyungeun Cho
    • 1
  • Hyungje Cho
    • 1
  • Kyhyun Um
    • 1
  1. 1.Department of Computer and Multimedia EngineeringDongguk UniversitySeoulKorea

Personalised recommendations