Abstract
This paper proposes a novel approach to recognize actions and objects within the context of each other. Assuming that the different actions involve different objects in image sequences and there is one-to-one relation between object and action type, we present a Bayesian network based framework which combines motion patterns and object usage information to recognize actions/objects. More specifically, our approach recognizes high-level actions and the related objects without any body-part segmentation, hand tracking, and temporal segmentation methods. Additionally, we present a novel motion representation, based on 3D Haar-like features, which can be formed by depth, color, or both images. Our approach is also appropriate for object and action recognition where the involved object is partially or fully occluded. Finally, experiments show that our approach improves the accuracy of both action and object recognition significantly.
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
Ullman, S.: High-level vision: object recognition and visual cognition. MIT Press (1996)
Fei-Fei, L., Fergus, R., Torralba, A.: Recognizing and learning object categories: short course. In: ICCV (2009)
Carbonetto, P., de Freitas, N., Barnard, K.: A Statistical Model for General Contextual Object Recognition. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 350–362. Springer, Heidelberg (2004)
Torralba, A.: Contextual priming for object detection. Int. J. Comput. Vision 53, 169–191 (2003)
Filipovych, R., Ribeiro, E.: Recognizing primitive interactions by exploring actor-object states. In: CVPR (2008)
Wu, J., Osuntogun, A., Choudhury, T., Philipose, M., Rehg, J.M.: A scalable approach to activity recognition based on object use. In: ICCV, pp. 1–7 (2007)
Kjellström, H., Romero, J., Kragić, D.: Visual object-action recognition: interfering object affordances from human demonstration. Comput. Vis. Image Underst. 115, 81–90 (2011)
Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Underst. 104, 90–126 (2006)
Poppe, R.: A survey on vision-based human action recognition. Image Vision Comput. 28, 976–990 (2010)
Gall, J., Fossati, A., Gool, L.J.V.: Functional categorization of objects using real-time markerless motion capture. In: CVPR, pp. 1969–1976 (2011)
Ciu, X., Liu, Y., Shan, S., Chen, X., Gao, W.: 3D Haar-like features for pedestrian detection. In: ICME 2007, pp. 1263–1266 (2007)
Fei-Fei, L.: Bag of words models: recognizing and learning object categories. In: CVPR 2007 (2007)
Rubinstein, Y., Hastie, T.: Discriminative vs. informative learning. In: Proc. of the 3th Int. Conf. on Knowledge Discovery and Data Mining, pp. 49–53 (1997)
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
Ar, I., Akgul, Y.S. (2012). A Framework for Combined Recognition of Actions and Objects. In: Bolc, L., Tadeusiewicz, R., Chmielewski, L.J., Wojciechowski, K. (eds) Computer Vision and Graphics. ICCVG 2012. Lecture Notes in Computer Science, vol 7594. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33564-8_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-33564-8_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33563-1
Online ISBN: 978-3-642-33564-8
eBook Packages: Computer ScienceComputer Science (R0)