Navigating through Logic-Based Scene Models for High-Level Scene Interpretations
This paper explores high-level scene interpretation with logic-based conceptual models. The main interest is in aggregates which describe interesting co-occurrences of physical objects and their respective views in a scene. Interpretations consist of instantiations of aggregate concepts supported by evidence from a scene. It is shown that flexible interpretation strategies are possible which are important for cognitive vision, e.g. mixed bottom-up and top-down interpretation, exploitation of context, recognition of intentions, task-driven focussing. The knowledge representation language is designed to easily map into a Description Logics (DL), however, current DL systems do not (yet) offer services which match high-level vision interpretation requirements. A table-laying scene is used as a guiding example. The work is part of the EU-project CogVis.
Unable to display preview. Download preview PDF.
- 2.Vila, L.: A Survey on Temporal Reasoning in Artificial Intelligence”, AI Communications, Vol. 7, (1994) 4–28Google Scholar
- 3.Reiter, R., Mackworth, A.: The Logic of Depiction, TR 87-23, Dept. Computer Science, Univ. of British Columbia, Vancouver, Canada (1987)Google Scholar
- 4.Matsuyama, T., Hwang, V.S.: SIGMA — A Knowledge-Based Aerial Image Understanding System, Advances in Computer Vision and Machine Intelligence, Plenum (1990)Google Scholar
- 5.Schröder, C.: Bildinterpretation durch Modellkonstruktion: Eine Theorie zur rechnergestützten Analyse von Bildern, Dissertation, DISKI 196, infix (1999)Google Scholar
- 6.Nagel, H.-H.: From Video to Language — a Detour via Logic vs. Jumping to Conclusions, Proc. Integration of Speech and Image Understanding, IEEE Computer Society (1999) 79–99Google Scholar
- 7.Möller, R., Neumann, B., Wessel, M.: Towards Computer Vision with Description Logics: Some Recent Progress, Proc. Integration of Speech and Image Understanding, IEEE Computer Society (1999) 101–116Google Scholar
- 8.Barwise, J., Perry, J.: Situations and Attitudes, Bradford (1983)Google Scholar
- 9.Neumann, B.: Description of Time-Varying Scenes, Semantic Structures, Lawrence Erlbaum (1989) 167–206Google Scholar
- 10.Neumann, B.: Conceptual Framework for High-Level Vision, FBI-HH-B-241/02, FB Informatik, Universität Hamburg (2002)Google Scholar
- 11.Horrocks, I., Sattler, U., Tobies, S.: Reasoning with Individuals for the Description Logic SHIQ, Proc. 17th Int. Conf. on Automated Deduction (CADE-17). LNCS Springer (2002)Google Scholar
- 12.Haarslev, V., Möller, R.: RACER Userś Guide and Reference Manual Version 1.7, http://www.fh-wedel.de/~mo/3214/racer-manual-1-7.pdf