Abstract
Activity recognition in complex scenes can be very challenging because human actions are unconstrained and may be observed from multiple views. While progress has been made in recognizing activities from fixed views, more research is needed in developing view invariant recognition methods. Furthermore, the recognition and classification of activities involves processing data in the space and time domains, which involves large amounts of data and can be computationally expensive to process. To accommodate for view invariance and high dimensional data we propose the use of Manifold Learning using Locality Preserving Projections (LPP). We develop an efficient set of features based on radial distance and present a Manifold Learning framework for learning low dimensional representations of action primitives that can be used to recognize activities at multiple views. Using our approach we present high recognition rates on the Inria IXMAS dataset.
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
Shlens, J.: A Tutorial on Principal Component Analysis. Salk Institute for Biological Studies, La Jolla (2005)
Bodor, R., Drenner, A., Fehr, D., Masoud, O., Papanikolopoulos, N.: View-independent human motion classification using image-based reconstruction. Image and Vision Computing 27(8), 1194–1206 (2009)
Cherla, S., Kulkarni, K., Kale, A., Ramasubramanian, V.: Towards fast, view-invariant human action recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2008, pp. 1–8 (2008)
Oikonomopoulos, A., Pantic, M., Patras, I.: An Implicit Spatiotemporal Shape Model for Human Activity Localization and Recognition. In: IEEE Conf. Computer Vision and Pattern Recognition (Workshops), Miami, USA (June 2009)
Souvenir, R., Parrigan, K.: Viewpoint Manifolds for Action Recognition. EURASIP Journal on Image and Video Processing 2009, Article ID 738702, 13 (2009)
He, X., Niyogi, P.: Locality Preserving Projections. In: Proc. Conf. Advances in Neural Information Processing Systems (2003)
Belkin, M., Niyogi, P.: Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. In: Advances in Neural Information Processing Systems, Vancouver, British Columbia, Canada, vol. 14 (2002)
Pless, R., Souvenir, R.: A Survey of Manifold Learning for Images. IPJS Transactions on Computer Vision and Applications 1, 83–94 (2009)
Ogale, A., Karapurkar, A., Aloimonos, Y.: View-Invariant Modeling and Recognition of Human Actions Using Grammars. In: Int. Conf. on Computer Vision (ICCV), Workshop on Dynamical Vision, Beijing, China (October 2005)
Oikonomopoulos, A., Patras, I., Pantic, M.: An implicit spatiotemporal shape model for human activity localization and recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2009, pp. 27–33 (2009)
Cayton, L.: Algorithms for Manifold Learning. Technical report, University of California, San Diego, California (2003)
Tang, Y., Rose, R.: A study of using locality preserving projections for feature extraction in speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2008, March 31-April 4, pp. 1569–1572 (2008)
Cai, L., Du., S.: Rotation, scale and translation invariant image watermarking using Radon transform and Fourier transform. In: Proceedings of the IEEE 6th Circuits and Systems Symposium Emerging Technologies: Frontiers of Mobile and Wireless Communication, May 31-June 2, vol. 1, pp. 281–284 (2004)
Hejazi, M., Shevlyakov, G., Yo-Sung, H.: Modified Discrete Radon Transforms and Their Application to Rotation-Invariant Image Analysis. In: IEEE 8th Workshop Multimedia Signal Processing 2006, October 3-6, pp. 429–434 (2006)
Ye, M., Androutsos, D.: Robust affine invariant shape image retrieval using the ICA Zernike Moment Shape Descriptor. In: 16th IEEE International Conference Image Processing (ICIP), November 7-10, pp. 1065–1068 (2009)
Poppe, R., Poel, M.: Comparison of silhouette shape descriptors for example-based human pose recovery. In: 7th International ConferenceAutomatic Face and Gesture Recognition, FGR 2006, April 2-6, pp. 541–546 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Azary, S., Savakis, A. (2010). View Invariant Activity Recognition with Manifold Learning. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2010. Lecture Notes in Computer Science, vol 6454. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17274-8_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-17274-8_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17273-1
Online ISBN: 978-3-642-17274-8
eBook Packages: Computer ScienceComputer Science (R0)