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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64(2-3), 107–123 (2005)
Laptev, I., Marszałek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Conference on Computer Vision & Pattern Recognition (June 2008)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
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)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
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)
Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: NIPS, pp. 801–808 (2007)
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)
Hyvrinen, A., Hurri, J., Hoyer, P.O.: Natural Image Statistics: A Probabilistic Approach to Early Computational Vision, 1st edn. Springer Publishing Company, Incorporated (2009)
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)
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)
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)
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)
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)
Yang, X., Tian, Y.: Eigenjoints-based action recognition using nave-bayes-nearest-neighbor. In: CVPR Workshops, pp. 14–19. IEEE (2012)
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)
Oreifej, O., Liu, Z.: Hon4d: Histogram of oriented 4d normals for activity recognition from depth sequences (June 2013)
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)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks, pp. 153–160 (2007)
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)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, G., Zhang, F., Giuliani, M., Buckl, C., Knoll, A. (2013). Unsupervised Learning Spatio-temporal Features for Human Activity Recognition from RGB-D Video Data. In: Herrmann, G., Pearson, M.J., Lenz, A., Bremner, P., Spiers, A., Leonards, U. (eds) Social Robotics. ICSR 2013. Lecture Notes in Computer Science(), vol 8239. Springer, Cham. https://doi.org/10.1007/978-3-319-02675-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-02675-6_34
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02674-9
Online ISBN: 978-3-319-02675-6
eBook Packages: Computer ScienceComputer Science (R0)