EVIDENTIAL COMBINATION OF ONTOLOGICAL AND STATISTICAL INFORMATION FOR ACTIVE SCENE CLASSIFICATION

Thomas Reineking, Niclas Schult, Joana Hois

2009

Abstract

We introduce an information-driven scene classification system that combines different types of knowledge derived from a domain ontology and a statistical model in order to analyze scenes based on recognized objects. The domain ontology structures and formalizes which kind of scene classes exist and which object classes occur in them. Based on this structure, an empirical analysis of annotations from the LabelMe image database results in a statistical domain description. Both forms of knowledge are utilized for determining which object class detector to apply to the current scene according to the principle of maximum information gain. All evidence is combined in a belief-based framework that explicitly takes into account the uncertainty inherent to the statistical model and the object detection process as well as the ignorance associated with the coarse granularity of ontological constraints. Finally, we present preliminary classification performance results for scenes from the LabelMe database.

References

  1. Baader, F., Calvanese, D., McGuinness, D., Nardi, D., and Patel-Schneider, P. (2003). The description logic handbook. Cambridge University Press.
  2. Dubois, D. and Prade, H. (1986). On the unicity of Dempster's rule of combination. International Journal of Intelligent Systems, 1(2):133-142.
  3. Henderson, J. and Hollingworth, A. (1999). High-level scene perception. Annual Review of Psychology, 50(1):243-271.
  4. Horridge, M. and Patel-Schneider, P. F. (2008). Manchester OWL syntax for OWL 1.1. OWL: Experiences and Directions (OWLED 08 DC), Gaithersberg, Maryland.
  5. Horrocks, I., Kutz, O., and Sattler, U. (2006). The Even More Irresistible SROIQ. In Knowledge Representation and Reasoning (KR). AAAI Press.
  6. Kollar, T. and Roy, N. (2009). Utilizing object-object and object-scene context when planning to find things. In International Conference on Robotics and Automation (ICRA).
  7. Konev, B., Lutz, C., Walther, D., and Wolter, F. (2009). Formal properties of modularisation. In Stuckenschmidt, H., Parent, C., and Spaccapietra, S., editors, Modular Ontologies. Springer.
  8. Maillot, N. E. and Thonnat, M. (2008). Ontology based complex object recognition. Image and Vision Computing, 26(1):102-113.
  9. Martínez Mozos, O ., Triebel, R., Jensfelt, P., Rottmann, A., and Burgard, W. (2007). Supervised semantic labeling of places using information extracted from sensor data. Robotics and Autonomous Systems, 55(5):391- 402.
  10. Masolo, C., Borgo, S., Gangemi, A., Guarino, N., and Oltramari, A. (2003). Ontologies library. WonderWeb Deliverable D18, ISTC-CNR.
  11. Oliva, A. and Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3):145-175.
  12. Pal, N., Bezdek, J., and Hemasinha, R. (1993). Uncertainty measures for evidential reasoning II: A new measure of total uncertainty. International Journal of Approximate Reasoning, 8(1):1-16.
  13. Russell, B., Torralba, A., Murphy, K., and Freeman, W. (2008). LabelMe: a database and web-based tool for image annotation. International Journal of Computer Vision, 77(1-3):157-173.
  14. Schill, K., Umkehrer, E., Beinlich, S., Krieger, G., and Zetzsche, C. (2001). Scene analysis with saccadic eye movements: Top-down and bottom-up modeling. Journal of Electronic Imaging, 10(1):152-160.
  15. Schill, K., Zetzsche, C., and Hois, J. (2009). A beliefbased architecture for scene analysis: From sensorimotor features to knowledge and ontology. Fuzzy Sets and Systems, 160(10):1507-1516.
  16. Schneiderman, H. and Kanade, T. (2004). Object detection using the statistics of parts. International Journal of Computer Vision, 56(3):151-177.
  17. Shafer, G. (1976). A Mathematical Theory of Evidence. Princeton University Press, Princeton, NJ.
  18. Sirin, E., Parsia, B., Grau, B. C., Kalyanpur, A., and Katz, Y. (2007). Pellet: A practical OWL-DL reasoner. Web Semantics: Science, Services and Agents on the World Wide Web, 5(2):51-53.
  19. Smets, P. (1992). The nature of the unnormalized beliefs encountered in the transferable belief model. In Uncertainty in Artificial Intelligence, pages 292-297.
  20. Smets, P. and Kennes, R. (1994). The transferable belief model. Artificial intelligence, 66(2):191-234.
  21. Vernon, D. (2008). Cognitive vision: The case for embodied perception. Image and Vision Computing, 26(1):127- 140.
  22. Zetzsche, C., Wolter, J., and Schill, K. (2008). Sensorimotor representation and knowledge-based reasoning for spatial exploration and localisation. Cognitive Processing, 9:283-297.
Download


Paper Citation


in Harvard Style

Reineking T., Schult N. and Hois J. (2009). EVIDENTIAL COMBINATION OF ONTOLOGICAL AND STATISTICAL INFORMATION FOR ACTIVE SCENE CLASSIFICATION . In Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2009) ISBN 978-989-674-012-2, pages 72-79. DOI: 10.5220/0002304300720079


in Bibtex Style

@conference{keod09,
author={Thomas Reineking and Niclas Schult and Joana Hois},
title={EVIDENTIAL COMBINATION OF ONTOLOGICAL AND STATISTICAL INFORMATION FOR ACTIVE SCENE CLASSIFICATION},
booktitle={Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2009)},
year={2009},
pages={72-79},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002304300720079},
isbn={978-989-674-012-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2009)
TI - EVIDENTIAL COMBINATION OF ONTOLOGICAL AND STATISTICAL INFORMATION FOR ACTIVE SCENE CLASSIFICATION
SN - 978-989-674-012-2
AU - Reineking T.
AU - Schult N.
AU - Hois J.
PY - 2009
SP - 72
EP - 79
DO - 10.5220/0002304300720079