Abstract
This paper proposes a novel dynamic sparse representation-based classification scheme to treat the problem of interaction action analysis between persons using sparse representation. The occlusion problem and the difficulty to model complicated interactions are the major challenges in person-to-person action analysis. To address the occlusion problem, the proposed scheme represents an action sample in an over-complete dictionary whose base elements are the training samples themselves. This representation is naturally sparse and makes errors (caused by different environmental changes like lighting or occlusions) sparsely appear in the training library. Because of the sparsity, it is robust to occlusions and lighting changes. The difficulty of complicated action modeling can be tackled by adding more examples to the over-complete dictionary. Thus, even though the interaction relations are complicated, the proposed method still works successfully to recognize them and can be easily extended to analyze action events among multiple persons.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Weinland, D., Ronfard, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation, and recognition. Computer Vision and Image Understanding 115(2), 224–241 (2011)
Poppe, R.: A survey on vision-based human action recognition. Image and Vision Computing 28(6), 976–990 (2010)
Aharon, M., Elad, M., Bruckstein, A.: K-svd: An algorithm for designing overcompletedictionries for sparse representation. IEEE Trans. on Signal Processing, 4311–4322 (2006)
Qiu, Q., Jiang, Z., Chellappa, R.: Sparse Dictionary-based Representation and Recognition of Action Attributes. In: IEEE Conference on Computer Vision (2011)
Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online learning for matrix factorization and sparse coding. J. Mach. Learn. Res. 11, 19–60 (2010)
Wang, Y., Huang, K., Tan, T.: Human activity recognition based on R transform. In: IEEE Conference on Computer Vision and Pattern Recognition (2007)
Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1446–1453 (2009)
Mahajan, D., Kwatra, N., Jain, S., Kalra, P.: A framework for activity recognition and detection of unusual activities. In: International Conference on Graphic and Image Processing (2004)
Laptev, I., Perez, P.: Retrieving actions in movies. In: International Conference on Computer Vision (October 2007)
Messing, R., Pal, C., Kautz, H.: Activity recognition using the velocity histories of tracked keypoints. In: International Conference on Computer Vision (October 2009)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)
Gaidon, A., Harchaoui, Z., Schmid, C.: Actom Sequence Models for Efficient Action Detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2011)
Rosales, R., Sclaroff, S.: 3D Trajectory Recovery for Tracking Multiple Objects and Trajectory Guided Recognition of Actions. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 117–123 (1999)
Nguyen, N.T., Bui, H.H., Venkatesh, S., West, G.: Recognition and monitoring high-level behaviours in complex spatial environments. In: IEEE International Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, vol. 2, pp. 620–625 (June 2003)
Yao, B., Fei-Fei, L.: Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence
Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. Advances in Neural Information Processing Systems (2011)
Filipovych, R., Ribeiro, E.: Recognizing Primitive Interactions by Exploring Actor-Object States. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–7 (June 2008)
Park, S., Park, J., Aggarwal, J.K.: Video Retrieval of Human Interactions Using Model-based Motion Tracking and Multi-Layer Finite State Automata. In: Bakker, E.M., Lew, M., Huang, T.S., Sebe, N., Zhou, X.S. (eds.) CIVR 2003. LNCS, vol. 2728, pp. 394–403. Springer, Heidelberg (2003)
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
Chuang, KT., Hsieh, JW., Yan, Y. (2013). Modeling and Recognizing Action Contexts in Persons Using Sparse Representation. In: Pan, JS., Yang, CN., Lin, CC. (eds) Advances in Intelligent Systems and Applications - Volume 2. Smart Innovation, Systems and Technologies, vol 21. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35473-1_53
Download citation
DOI: https://doi.org/10.1007/978-3-642-35473-1_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35472-4
Online ISBN: 978-3-642-35473-1
eBook Packages: EngineeringEngineering (R0)