Abstract
This work presents a novel approach for human action recognition based on the combination of computer vision techniques and common-sense knowledge and reasoning capabilities. The emphasis of this work is on how common sense has to be leveraged to a vision-based human action recognition so that nonsensical errors can be amended at the understanding stage. The proposed framework is to be deployed in a realistic environment in which humans behave rationally, that is, motivated by an aim or a reason.
This research was supported by the Spanish Ministry of Science and Innovation under the project DREAMS (TEC2011-28666-C04-03).
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
Vezzani, R., Baltieri, D., Cucchiara, R.: HMM Based Action Recognition with Projection Histogram Features. In: Ünay, D., Çataltepe, Z., Aksoy, S. (eds.) ICPR 2010. LNCS, vol. 6388, pp. 286–293. Springer, Heidelberg (2010)
Martinez-Contreras, F., Orrite-Urunuela, C., Herrero-Jaraba, E., Ragheb, H., Velastin, S.A.: Recognizing human actions using silhouette-based hmm. In: Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009, pp. 43–48. IEEE Computer Society, Washington, DC (2009)
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR. IEEE Computer Society (2008)
Zhang, J., Gong, S.: Action categorization with modified hidden conditional random field. Pattern Recogn. 43(1), 197–203 (2010)
Baker, C.L., Saxe, R., Tenenbaum, J.B.: Action understanding as inverse planning. Cognition (2009)
Lenat, D.B., Guha, R.V.: Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project. Addison-Wesley Longman Publishing Co., Inc., Boston (1989)
Nebel, J.-C., Lewandowski, M., Thévenon, J., MartÃnez, F., Velastin, S.: Are Current Monocular Computer Vision Systems for Human Action Recognition Suitable for Visual Surveillance Applications? In: Bebis, G., Boyle, R., Parvin, B., Koracin, D., Wang, S., Kyungnam, K., Benes, B., Moreland, K., Borst, C., DiVerdi, S., Yi-Jen, C., Ming, J. (eds.) ISVC 2011, Part II. LNCS, vol. 6939, pp. 290–299. Springer, Heidelberg (2011)
Davidson, D.: Actions, reasons, and causes. The Journal of Philosophy 60(23), 685–700 (1963)
Allen, J.F.: Towards a general theory of action and time. Artif. Intell. 23, 123–154 (1984)
Fahlman, S.E.: Marker-Passing Inference in the Scone Knowledge-Base System. In: Lang, J., Lin, F., Wang, J. (eds.) KSEM 2006. LNCS (LNAI), vol. 4092, pp. 114–126. Springer, Heidelberg (2006)
Fahlman, S.E.: The Scone knowledge-base project (2010), http://www.cs.cmu.edu/~sef/scone/ (retrieved on February 8, 2010)
Weinland, D., Boyer, E., Ronfard, R.: Action Recognition from Arbitrary Views using 3D Exemplars. In: International Conference on Computer Vision, Rio de Janeiro, Brazil, pp. 1–7. IEEE (2007)
Martinez del Rincon, J., Santofimia, M.J., Nebel, J.C.: Common-sense reasoning for human action recognition. Under Review Process (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Santofimia, M.J., Martinez-del-Rincon, J., Nebel, JC. (2012). Common-Sense Knowledge for a Computer Vision System for Human Action Recognition. In: Bravo, J., Hervás, R., RodrÃguez, M. (eds) Ambient Assisted Living and Home Care. IWAAL 2012. Lecture Notes in Computer Science, vol 7657. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35395-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-35395-6_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35394-9
Online ISBN: 978-3-642-35395-6
eBook Packages: Computer ScienceComputer Science (R0)