Advertisement

Applying Space State Models in Human Action Recognition: A Comparative Study

  • M. Ángeles Mendoza
  • Nicolás Pérez de la Blanca
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5098)

Abstract

This paper presents comparative results of applying different architectures of generative classifiers (HMM, FHMM, CHMM, Multi-Stream HMM, Parallel HMM ) and discriminative classifier as Conditional Random Fields (CRFs) in human action sequence recognition. The models are fed with histogram of very informative features such as contours evolution and optical-flow. Motion orientation discrimination has been obtained tiling the bounding box of the subject and extracting features from each tile. We run our experiments on two well-know databases, KTH´s database and Weizmann´s. The results show that both type of models reach similar score, being the generative model better when used with optical flow features and being the discriminative one better when uses with shape-context features.

Keywords

Feature Vector Hide Markov Model Action Recognition Gesture Recognition Hide State 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ahmad, M., Lee, S.: Human Action Recognition Using Multi-View Image Sequence Features. In: Proc. of the 7th International Conference on Automatic Face and Gesture Recognition, pp. 523–528 (2006)Google Scholar
  2. 2.
    Bach, N.H., Shinoda, K., Furui, S.: Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast. IEEE Trans. on Information and Systems E89-D(9), 2553–2561 (2006)CrossRefGoogle Scholar
  3. 3.
    Belongie, S., Malik, J.: Matching with Shape Contexts. In: IEEE Workshop on Content-Based Access of Image and Video Libraries, pp. 20–26 (2000)Google Scholar
  4. 4.
    Bobick, A.F., Ivanov, Y.A.: Action recognition using probabilistic parsing. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 196–202 (1998)Google Scholar
  5. 5.
    Brand, M., Oliver, N., Pentland, A.: Coupled hidden Markov models for complex action recognition. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 994–999 (1997)Google Scholar
  6. 6.
    Bregler, C.: Learning and Recognizing Human Dynamics in Video Sequences. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 568–574 (1997)Google Scholar
  7. 7.
    Chen, C.H., Liang, J.M., Hu, H.H., Jiao, L.C., Yang, X.: Factorial Hidden Markov Models for Gait Recognition. In: Proc. of The 2nd International Conf. on Biometrics, pp. 124–133 (2007)Google Scholar
  8. 8.
    Connolly, C.I.: Learning to Recognize Complex Actions Using Conditional Random Fields. In: Interntional Symposium on Visual Computing, vol. 2, pp. 340–348 (2007)Google Scholar
  9. 9.
    Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing Action at a Distance. In: International Conf. on Computer Vision, pp. 726–733 (2003)Google Scholar
  10. 10.
    Feng, X., Perona, P.: Human action recognition by sequence of movelet codewords. In: Proc. of 1st International Symposium on 3D Data Processing Visualization and Transmission, pp. 717–721 (2002)Google Scholar
  11. 11.
    Ghahramani, Z., Jordan, M.I.: Factorial Hidden Markov Models. Machine Learning 29(2-3), 245–273 (1997)zbMATHCrossRefGoogle Scholar
  12. 12.
    Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 9(12), 2247–2253 (2007)CrossRefGoogle Scholar
  13. 13.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. of the 18th International Conf. on Machine Learning, pp. 282–289 (2001)Google Scholar
  14. 14.
    Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proc. of Imaging Understanding Workshop, pp. 121–130 (1981)Google Scholar
  15. 15.
    Mendoza, M.A., de la Blanca, N.P.: HMM-Based Action Recognition Using Contour Histograms. In: Proc. of the 3th Iberian Conf. on Pattern Recognition and Image Analysis, pp. 394–401 (2007)Google Scholar
  16. 16.
    Morency, L.P., Quattoni, A., Darrell, T.: Latent-Dynamic Discriminative Models for Continuous Gesture Recognition. Massachussetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory (CSAIL) Technical Reports (2007)Google Scholar
  17. 17.
    Morency, L.P., Quattoni, A., Christoudias, C.M., Wang, S.: Hidden-state Conditional Random Field Library. User Guide (2007)Google Scholar
  18. 18.
    Murphy, K.P.: The Bayes Net Toolbox for MATLAB. Computing Science and Statis (2001)Google Scholar
  19. 19.
    Rabiner, L.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  20. 20.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing Human Actions: a Local SVM Approach. In: Proc. of the 17th International Conf. on Pattern Recognition, vol. 3(1), pp. 32–36 (2004)Google Scholar
  21. 21.
    Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Conditional models for contextual human motion recognition. In: IEEE International Conf. on Computer Vision, vol. 2(1), pp. 1805–1808 (2005)Google Scholar
  22. 22.
    Sutton, C., McCallum, A.: An Introduction to Conditional Random Fields for Relational Learning. In: Introduction to Statistical Relational Learning. MIT Press, Cambridge (2006)Google Scholar
  23. 23.
    Vogler, C., Metaxas, D.: Parallel Hidden Markov Models for American Sign Language Recognition. In: International Conf. on Computer Vision, pp. 116–122 (1999)Google Scholar
  24. 24.
    Wang, S., Quattoni, A., Morency, L.P., Demirdjian, D., Darrel, T.: Hidden Conditional Random Fields for Gesture Recognition. In: IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2(1), pp. 1521–1527 (2006)Google Scholar
  25. 25.
    Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden Markov model. In: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 379–385 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • M. Ángeles Mendoza
    • 1
  • Nicolás Pérez de la Blanca
    • 1
  1. 1.ETSI Informática y e TelecomunicaciónUniversity of GranadaGranadaSpain

Personalised recommendations