Abstract
One of the reasons why humans are so successful at interpreting everyday situations is that they are able to combine disparate forms of knowledge. Most artificial systems, by contrast, are restricted to a single representation and hence fail to utilize the complementary nature of multiple sources of information. In this paper, we introduce an information-driven scene categorization system that integrates common sense knowledge provided by a domain ontology with a learned statistical model in order to infer a scene class from recognized objects. We show how the unspecificity of coarse logical constraints and the uncertainty of statistical relations and the object detection process can be modeled using Dempster-Shafer theory and derive the resulting belief update equations. In addition, we define an uncertainty minimization principle for adaptively selecting the most informative object detectors and present classification results for scenes from the LabelMe image database.
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.
Similar content being viewed by others
References
Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision 42, 145–175 (2001)
Schill, K., Zetzsche, C., Hois, J.: A belief-based architecture for scene analysis: From sensorimotor features to knowledge and ontology. Fuzzy Sets and Systems 160, 1507–1516 (2009)
MartÃnez Mozos, Ó., Triebel, R., Jensfelt, P., Rottmann, A., Burgard, W.: Supervised semantic labeling of places using information extracted from sensor data. Robotics and Autonomous Systems 55, 391–402 (2007)
Kollar, T., Roy, N.: Utilizing object-object and object-scene context when planning to find things. In: International Conference on Robotics and Automation (ICRA) (2009)
Maillot, N.E., Thonnat, M.: Ontology based complex object recognition. Image and Vision Computing 26, 102–113 (2008)
Russell, B., Torralba, A., Murphy, K., Freeman, W.: LabelMe: a database and web-based tool for image annotation. International Journal of Computer Vision 77, 157–173 (2008)
Baader, F., Calvanese, D., McGuinness, D., Nardi, D., Patel-Schneider, P.: The Description Logic Handbook. Cambridge University Press, Cambridge (2003)
Motik, B., Patel-Schneider, P.F., Grau, B.C.: OWL 2 Web Ontology Language: Direct Semantics. Technical report, W3C (2008), http://www.w3.org/TR/owl2-semantics/
Horrocks, I., Kutz, O., Sattler, U.: The Even More Irresistible SROIQ. In: Knowledge Representation and Reasoning (KR). AAAI Press, Menlo Park (2006)
Sirin, E., Parsia, B., Grau, B.C., Kalyanpur, A., Katz, Y.: Pellet: A practical OWL-DL reasoner. In: Web Semantics: Science, Services and Agents on the World Wide Web, vol. 5, pp. 51–53 (2007)
Kutz, O., Lücke, D., Mossakowski, T.: Heterogeneously Structured Ontologies—Integration, Connection, and Refinement. In: Meyer, T., Orgun, M.A. (eds.) Advances in Ontologies, Proc. of the Knowledge Representation Ontology Workshop (KROW 2008), pp. 41–50. ACS (2008)
Masolo, C., Borgo, S., Gangemi, A., Guarino, N., Oltramari, A.: Ontologies library. WonderWeb Deliverable D18, ISTC-CNR (2003)
Konev, B., Lutz, C., Walther, D., Wolter, F.: Formal properties of modularisation. In: Stuckenschmidt, H., Parent, C., Spaccapietra, S. (eds.) Modular Ontologies. LNCS, vol. 5445, pp. 25–66. Springer, Heidelberg (2009)
Vernon, D.: Cognitive vision: The case for embodied perception. Image and Vision Computing 26, 127–140 (2008)
Horridge, M., Patel-Schneider, P.F.: Manchester OWL syntax for OWL 1.1. In: OWL: Experiences and Directions (OWLED 2008), DC, Gaithersberg, Maryland (2008)
Sirin, E., Parsia, B., Grau, B.C., Kalyanpur, A., Katz, Y.: Pellet: A practical OWL-DL reasoner. In: Web Semantics: Science, Services and Agents on the World Wide Web, vol. 5, pp. 51–53 (2007)
Shafer, G.: A Mathematical Theory of Evidence. Princeton University Press, Princeton (1976)
Smets, P., Kennes, R.: The transferable belief model. Artificial intelligence 66, 191–234 (1994)
Smets, P.: Belief functions: the disjunctive rule of combination and the generalized Bayesian theorem. International Journal of Approximate Reasoning 9, 1–35 (1993)
Delmotte, F., Smets, P.: Target identification based on the transferable belief model interpretation of Dempster-Shafer model. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans 34, 457–471 (2004)
Dubois, D., Prade, H.: On the unicity of Dempster’s rule of combination. International Journal of Intelligent Systems 1, 133–142 (1986)
Smets, P.: The nature of the unnormalized beliefs encountered in the transferable belief model. In: Uncertainty in Artificial Intelligence, pp. 292–297 (1992)
Pal, N., Bezdek, J., Hemasinha, R.: Uncertainty measures for evidential reasoning II: A new measure of total uncertainty. International Journal of Approximate Reasoning 8, 1–16 (1993)
Smets, P.: Decision making in the TBM: the necessity of the pignistic transformation. International Journal of Approximate Reasoning 38, 133–147 (2005)
Reineking, T., Schult, N., Hois, J.: Evidential combination of ontological and statistical information for active scene classification. In: International Conference on Knowledge Engineering and Ontology Development (KEOD) (2009)
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Annals of Statistics 28 (1998), 2000
Henderson, J., Hollingworth, A.: High-level scene perception. Annual Review of Psychology 50, 243–271 (1999)
Schill, K., Umkehrer, E., Beinlich, S., Krieger, G., Zetzsche, C.: Scene analysis with saccadic eye movements: Top-down and bottom-up modeling. Journal of Electronic Imaging 10, 152–160 (2001)
Zetzsche, C., Wolter, J., Schill, K.: Sensorimotor representation and knowledge-based reasoning for spatial exploration and localisation. Cognitive Processing 9, 283–297 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reineking, T., Schult, N., Hois, J. (2011). Combining Statistical and Symbolic Reasoning for Active Scene Categorization. In: Fred, A., Dietz, J.L.G., Liu, K., Filipe, J. (eds) Knowledge Discovery, Knowlege Engineering and Knowledge Management. IC3K 2009. Communications in Computer and Information Science, vol 128. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19032-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-19032-2_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19031-5
Online ISBN: 978-3-642-19032-2
eBook Packages: Computer ScienceComputer Science (R0)