Unsupervised Learning Spatio-temporal Features for Human Activity Recognition from RGB-D Video Data

  • Guang Chen
  • Feihu Zhang
  • Manuel Giuliani
  • Christian Buckl
  • Alois Knoll
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8239)

Abstract

Being able to recognize human activities is essential for several applications, including social robotics. The recently developed commodity depth sensors open up new possibilities of dealing with this problem. Existing techniques extract hand-tuned features, such as HOG3D or STIP, from video data. They are not adapting easily to new modalities. In addition, as the depth video data is low quality due to the noise, we face a problem: does the depth video data provide extra information for activity recognition? To address this issue, we propose to use an unsupervised learning approach generally adapted to RGB and depth video data. we further employ the multi kernel learning (MKL) classifier to take into account the combinations of different modalities. We show that the low-quality depth video is discriminative for activity recognition. We also demonstrate that our approach achieves superior performance to the state-of-the-art approaches on two challenging RGB-D activity recognition datasets.

Keywords

activity recognition unsupervised learning depth video 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64(2-3), 107–123 (2005)CrossRefGoogle Scholar
  2. 2.
    Laptev, I., Marszałek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Conference on Computer Vision & Pattern Recognition (June 2008)Google Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  4. 4.
    Wang, H., Ullah, M.M., Kläser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: British Machine Vision Conference, p. 127 (September 2009)Google Scholar
  5. 5.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 607–609 (1996)CrossRefGoogle Scholar
  7. 7.
    Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS, pp. 801–808 (2007)Google Scholar
  8. 8.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Schölkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems 19, pp. 153–160. MIT Press, Cambridge (2007)Google Scholar
  9. 9.
    Hyvrinen, A., Hurri, J., Hoyer, P.O.: Natural Image Statistics: A Probabilistic Approach to Early Computational Vision, 1st edn. Springer Publishing Company, Incorporated (2009)Google Scholar
  10. 10.
    Socher, R., Huval, B., Bath, B.P., Manning, C.D., Ng, A.Y.: Convolutional-recursive deep learning for 3d object classification. In: Bartlett, P.L., Pereira, F.C.N., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) NIPS, pp. 665–673 (2012)Google Scholar
  11. 11.
    Le, Q., Zou, W., Yeung, S., Ng, A.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3361–3368 (2011)Google Scholar
  12. 12.
    Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(1), 221–231 (2013)CrossRefGoogle Scholar
  13. 13.
    Zhang, H., Parker, L.: 4-dimensional local spatio-temporal features for human activity recognition. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2044–2049 (2011)Google Scholar
  14. 14.
    Xia, L., Chen, C.C., Aggarwal, J.: View invariant human action recognition using histograms of 3d joints. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 20–27 (2012)Google Scholar
  15. 15.
    Yang, X., Tian, Y.: Eigenjoints-based action recognition using nave-bayes-nearest-neighbor. In: CVPR Workshops, pp. 14–19. IEEE (2012)Google Scholar
  16. 16.
    Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1290–1297 (2012)Google Scholar
  17. 17.
    Oreifej, O., Liu, Z.: Hon4d: Histogram of oriented 4d normals for activity recognition from depth sequences (June 2013)Google Scholar
  18. 18.
    LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1, 541–551 (1989)CrossRefGoogle Scholar
  19. 19.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks, pp. 153–160 (2007)Google Scholar
  20. 20.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifier, pp. 61–74. MIT Press (1999)Google Scholar
  21. 21.
    Kamarainen, J.K., Kyrki, V., Kälviäinen, H.: Invariance properties of Gabor filter based features - overview and applications. IEEE Transactions on Image Processing 15(5), 1088–1099 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Guang Chen
    • 1
  • Feihu Zhang
    • 1
  • Manuel Giuliani
    • 2
  • Christian Buckl
    • 2
  • Alois Knoll
    • 1
  1. 1.Institut für Informatik VITechnische Universität MünchenGarchingGermany
  2. 2.fortiss GmbHMunichGermany

Personalised recommendations