Abstract
In high-level scene interpretation, it is useful to exploit the evolving probabilistic context for stepwise interpretation decisions. We present a new approach based on a general probabilistic framework and beam search for exploring alternative interpretations. As probabilistic scene models, we propose Bayesian Compositional Hierarchies (BCHs) which provide object-centered representations of compositional hierarchies and efficient evidence-based updates. It is shown that a BCH can be used to represent the evolving context during stepwise scene interpretation and can be combined with low-level image analysis to provide dynamic priors for object classification, improving classification and interpretation. Experimental results are presented illustrating the feasibility of the approach for the interpretation of facade images.
Chapter PDF
References
Tsotsos, J.K., Mylopoulos, J., Covvey, H.D., Zucker, S.W.: A Framework for Visual Motion Understanding. In: IEEE PAMI-2, pp. 563–573 (1980)
Nagel, H.-H.: From Image Sequences towards Conceptual Descriptions. Image and Vision Computing 6(2), 59–74 (1988)
Neumann, B.: Description of Time-Varying Scenes. In: Waltz, D. (ed.) Semantic Structures, pp. 167–206. Lawrence Erlbaum, Mahwah (1989)
Georis, B., Mazière, M., Brémond, F., Thonnat, M.: Evaluation and Knowledge Representation Formalisms to Improve Video Understanding. In: Proc. IEEE International Conf. on Computer Vision Systems ICVS 2006, p. 27. IEEE Computer Society, Los Alamitos (2006)
Neumann, B., Moeller, R.: On Scene Interpretation with Description Logics. In: Christensen, H.I., Nagel, H.-H. (eds.) Cognitive Vision Systems. LNCS, vol. 3948, pp. 247–275. Springer, Heidelberg (2006)
Rimey, R.D.: Control of Selective Perception using Bayes Nets and Decision Theory. TR 468, Univ. of Rochester, Computer Science Department, Rochester, USA 14627 (1993)
Koller, D., Pfeffer, A.: Object-oriented Bayesian Networks. In: The Thirteenth Annual Conference on Uncertainty in Artificial Intelligence, pp. 302–313 (1997)
Getoor, L., Taskar, B.: Introduction to Statistical Relational Learning (eds, pp. 129–174. The MIT Press, Cambridge (2007)
Gyftodimos, E., Flach, P.A.: Hierarchical Bayesian Networks: A Probabilistic Reasoning Model for Structured Domains. In: de Jong, E., Oates, T. (eds.) Proc. Workshop on Development of Representations, ICML, pp. 23–30 (2002)
Neumann, B.: Bayesian Compositional Hierarchies - A Probabilistic Structure for Scene Interpretation. TR FBI-HH-B-282/08, Univ. of Hamburg, Department Informatik (2008)
Mumford, D., Zhu, S.-C.: A Stochastic Grammar of Images. Now Publishers (2007)
Yu, J., Luo, J.: Leveraging Probabilistic Season and Location Context Models for Scene Understanding. In: The 2008 International Conference on Content-based Image and Video Retrieval (CIVR 2008), pp. 169–178. ACM, New York (2008)
Perko, R., Wojek, C., Schiele, B., Leonardis, A.: Integrating Visual Context and Object Detection within a Probabilistic Framework. In: Paletta, L., Tsotsos, J.K. (eds.) Attention in Cognitive Systems. LNCS, vol. 5395, pp. 54–68. Springer, Heidelberg (2009)
Li, L.-J., Socher, R., Fei-Fei, L.: Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework. In: Computer Vision and Pattern Recognition, CVPR (2009)
Lowerre, B.: The Harpy Speech Recognition System. Ph.D. thesis, Carnegie Mellon University (1976)
Mitchell, T.M.: Machine Learning. The Mc-Graw-Hill, New York (1997)
Kreutzmann, A., Terzić, K., Neumann, B.: Context-aware Classification for Incremental Scene Interpretation. In: Proc. Workshop on Use of Context in Vision Processing (UCVP 2009), Boston (2009)
Terzić, K., Neumann, B.: Decision Trees for Probabilistic Top-down and Bottom-up Integration. Technical Report FBI-HH-B-288/09, University of Hamburg (2009)
etrims - e-Training for Interpreting Images of Man-made Scenes, http://www.ipb.uni-bonn.de/projects/etrims/
Terzić, K., Hotz, L., Šochman, J.: Interpreting Structures in Man-made Scenes; Combining Low-Level and High-Level Structure Sources. In: International Conference on Agents and Artificial Intelligence (ICAART 2010), Valencia (2010)
Jahangiri, M., Petrou, M.: Fully Bottom-Up Blob Extraction in Building Facades. In: Proc. Pattern Recognition and Image Analysis, PRIA (2008)
Drauschke, M.: An Irregular Pyramid for Multi-Scale Analysis of Objects and Their Parts. In: Torsello, A., Escolano, F., Brun, L. (eds.) Workshop on Graph-based Representations (GbR 2009). LNCS, vol. 5534, pp. 293–303. Springer, Heidelberg (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 IFIP International Federation for Information Processing
About this paper
Cite this paper
Neumann, B., Terzic, K. (2010). Context-Based Probabilistic Scene Interpretation. In: Bramer, M. (eds) Artificial Intelligence in Theory and Practice III. IFIP AI 2010. IFIP Advances in Information and Communication Technology, vol 331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15286-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-15286-3_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15285-6
Online ISBN: 978-3-642-15286-3
eBook Packages: Computer ScienceComputer Science (R0)