Advertisement

Behavior Recognition from Multiple Views Using Fused Hidden Markov Models

  • Dimitrios I. Kosmopoulos
  • Athanasios S. Voulodimos
  • Theodora A. Varvarigou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6040)

Abstract

In this work, we provide a framework for recognizing human behavior from multiple cameras in structured industrial environments. Since target recognition and tracking can be very challenging, we bypass these problems by employing an approach similar to Motion History Images for feature extraction. Modeling and recognition are performed through the use of Hidden Markov Models (HMMs) with Gaussian observation likelihoods. The problems of limited visibility and occlusions are addressed by showing how the framework can be extended for multiple cameras, both at the feature and at the state level. Finally, we evaluate the performance of the examined approaches under real-life visual behavior understanding scenarios and we discuss the obtained results.

Keywords

behavior recognition Hidden Markov Models multi-camera classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ivanov, Y.A., Bobick, A.F.: Recognition of visual activities and interactions by stochastic parsing. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 852–872 (2000)CrossRefGoogle Scholar
  2. 2.
    Dupont, S., Luettin, J.: Audio-visual speech modeling for continuous speech recognition. IEEE Trans. Multimedia 2, 141–151 (2000)CrossRefGoogle Scholar
  3. 3.
    Stork, D.G., Hennecke, M.E.: Speech reading by humans and machines. NATO. ASI Series F, vol. 150. Springer, Heidelberg (1996)Google Scholar
  4. 4.
    Xiang, T., Gong, S.: Beyond tracking: Modelling activity and understanding behaviour. Int. J. Comput. Vision 67(1), 21–51 (2006)CrossRefGoogle Scholar
  5. 5.
    Vogler, C., Metaxas, D.: Parallel HMMs for ASL recognition. In: ICCV 1999 (1999)Google Scholar
  6. 6.
    Zeng, Z., Tu, J., Pianfetti, B., Huang, T.: Audio-visual affective expression recognition through multistream fused hmm. IEEE Trans. Mult. 10(4), 570–577 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Dimitrios I. Kosmopoulos
    • 1
  • Athanasios S. Voulodimos
    • 2
  • Theodora A. Varvarigou
    • 2
  1. 1.N.C.S.R. “Demokritos” Institute of Inform. and Telecom.Aghia ParaskeviGreece
  2. 2.National Technical University of Athens School of Electr. and Comp. EnginneringZografouGreece

Personalised recommendations