Head Gesture Recognition Using Optical Flow Based Background Subtraction

  • Soukaina Chraa Mesbahi
  • Mohamed Adnane Mahraz
  • Jamal Riffi
  • Hamid Tairi
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 37)

Abstract

This paper presents a technique of real time head gesture recognition system. The primary objective is to implement system that can detect the movement of the head in different directions. The method comprises Gaussian mixture model GMM for background subtraction accompanied by optical flow algorithm, which contributed us the required information respecting head movement. An idea is given regarding the intensity variation between the frames of inputted video. This variation in intensity is used to determine the optical flow and the sum of the velocity vectors of the foreground image. Using the median filter to remove noise from an image, such noise reduction is a typical pre-processing step to improve the results of later processing. In our experiments, we tried to determine the movement of the head in different directions: left, right, up and down.

Keywords

Head gesture GMM Background subtraction Optical flow 

References

  1. 1.
    Holte, M.B., Tran, C., Trivedi, M.M., Moeslund, T.B.: Human pose estimation and activity recognition from multi-view videos: comparative explorations of recent developments. IEEE J. Sel. Top. Signal Process. 6(5), 538–552 (2012)CrossRefGoogle Scholar
  2. 2.
    Mukherjee, S., Das, K.: An adaptive GMM approach to background subtraction for application in real time surveillance. Int. J. Res. Eng. Technol. 2(1), 125–129 (2013)Google Scholar
  3. 3.
    Friedman, N., Russell, S.: Image segmentation in video sequences: a probabilistic approach. In: Proceedings Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI 1997), pp. 175–181 (1997)Google Scholar
  4. 4.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking (PDF). In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999).  https://doi.org/10.1109/cvpr.1999.784637
  5. 5.
    Farneback, G.: Polynomial expansion for orientation and motion estimation. Ph.D. thesis, Linkoping University, Sweden, SE-581 83 Linkoping, Sweden Dissertation No 790, ISBN 91-7373-475-6 (2002)Google Scholar
  6. 6.
    Piccardi, M.: Background subtraction techniques: a review (PDF). In: IEEE International Conference on Systems, Man and Cybernetics, vol. 4, pp. 3099–3104 (2004).  https://doi.org/10.1109/icsmc.2004.1400815
  7. 7.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B Methodol. 39(1), 1–38 (1977)MathSciNetMATHGoogle Scholar
  8. 8.
    Balakrishnan, S., Wainwright, M.J., Yu, B.: Statistical guarantees for the EM algorithm: from population to sample-based analysis. CoRR abs/1408.2156 (2014)Google Scholar
  9. 9.
    Bouwmans, T., El Baf, F., El Vachon, B.: Background modeling using mixture of Gaussians for foreground detection - a survey: (PDF). Recent Pat. Comput. Sci. 1, 219–237 (2008)CrossRefGoogle Scholar
  10. 10.
    Dibyendu, M., Wu, Q.M.J., Thanh, N.M.: Gaussian mixture model with advanced distance measure based on support weights and histogram of gradients for background suppression. IEEE Trans. Ind. Inf. PP(99), 1–11 (2014)Google Scholar
  11. 11.
    Farnebck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) Proceedings of the 13th Scandinavian Conference on Image Analysis (SCIA 2003), pp. 363–370. Springer, Heidelberg (2003)Google Scholar
  12. 12.
    Knutsson, H., Westin, C.F.: Normalized and differential convolution: methods for interpolation and filtering of incomplete and uncertain data. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York City, USA, 515–523. IEEE (1993)Google Scholar
  13. 13.
    Westin, C.F.: A tensor framework for multidimensional signal processing. Ph.D. thesis, Linkoping University, Sweden, SE-581 83 Linkoping, Sweden Dissertation No 348. ISBN 91-7871-421-4 (1994)Google Scholar
  14. 14.
    KadewTraKuPong, P., Bowden, R.: An improved adaptive background mixture model for realtime tracking with shadow detection. In: Proceedings of 2nd European Workshop on Advanced Video Based Surveillance Systems, AVBS01, September 2001Google Scholar
  15. 15.
    Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: Proceedings of the 17th International Conference on Pattern Recognition, vol. 2, pp. 28–31 (2004)Google Scholar
  16. 16.
    Zivkovic, Z., van der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recogn. Lett. 27(7), 773–780 (2006)CrossRefGoogle Scholar
  17. 17.
    Godbehere, A.B., Matsukawa, A., Goldberg, K.Y.: Visual tracking of human visitors under variable-lighting conditions for a responsive audio art installation. In: ACC, pp. 4305–4312 (2012)Google Scholar
  18. 18.
    Saikia, P., Das, K.: Hand gesture recognition using optical flow based classification with reinforcement of GMM based background subtraction. Int. J. Comput. Appl. 0975-8887, March 2013Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.LIIAN, Department of Computer Science, Faculty of Science Dhar El MahrazUniversity Sidi Mohamed Ben AbdellahFezMorocco

Personalised recommendations