Consistent Modeling of Functional Dependencies along with World Knowledge

In this paper we propose a method for vision systems to consistently represent functional dependencies between different visual routines along with relational short- and long-term knowledge about the world. Here the visual routines are bound to visual properties of objects stored in the memory of the system. Furthermore, the functional dependencies between the visual routines are seen as a graph also belonging to the object-s structure. This graph is parsed in the course of acquiring a visual property of an object to automatically resolve the dependencies of the bound visual routines. Using this representation, the system is able to dynamically rearrange the processing order while keeping its functionality. Additionally, the system is able to estimate the overall computational costs of a certain action. We will also show that the system can efficiently use that structure to incorporate already acquired knowledge and thus reduce the computational demand.

Authors:

• Sven Rebhan
• Nils Einecke
• Julian Eggert

Keywords:

• Adaptive systems
• Knowledge representation
• Machinevision
• Systems engineering

References:

[1] Julian Eggert, Sven Rebhan, and Edgar K¨orner. First steps towards
an intentional vision system. In Proceedings of the 5th International
Conference on Computer Vision Systems (ICVS), 2007.
[2] Jack B. Dennis. First version of a data flow procedure language.
In Proceedings of the Colloque sur la Programmation, volume 19 of
Lecture Notes in Computer Science, pages 362-376, London, UK, 1974.
Springer-Verlag.
[3] Jack B. Dennis. Data flow supercomputers. Computer, 13(11):48-56,
November 1980.
[4] Jeanne Ferrante, Karl J. Ottenstein, and Joe D. Warren. The program
dependence graph and its use in optimization. ACM Transactions on
Programming Language and Systems, 9(3):319-349, July 1987.
[5] Robert Cartwright and Matthias Felleisen. The semantics of program
dependence. In Proceedings of the ACM SIGPLAN 89 Conference
on Programming Language Design and Implementation, pages 13-27,
1989.
[6] Per Andersson. Modelling and implementation of a vision system for
embedded systems, 2003.
[7] Florian R¨ohrbein, Julian Eggert, and Edgar K¨oerner. Prototypical
relations for cortex-inspired semantic representations. In Proceedings
of the 8th International Conference on Cognitive Modeling (ICCM),
pages 307-312. Psychology Press, Taylor & Francis Group, 2007.
[8] Robert A. Ballance, Arthur B. Maccabe, and Karl J. Ottenstein. The
program dependence web: A representation supporting control-, data-,
and demand-driven interpretation of imperative languages. In Proceedings
of the ACM SIGPLAN 90 Conference on Programming Language
Design and Implementation, volume 25, pages 257-271, New York, NY,
USA, 1990. ACM.
[9] Sven Rebhan, Florian R¨ohrbein, Julian Eggert, and Edgar K¨orner. Attention
modulation using short- and long-term knowledge. In A. Gasteratos,
M. Vincze, and J.K. Tsotsos, editors, Proceeding of the 6th International
Conference on Computer Vision Systems (ICVS), LNCS 5008, pages
151-160. Springer Verlag, 2008.
[10] Milan Sonka, Vaclav Hlavac, and Roger Boyle. Image Processing,
Analysis, and Machine Vision. Thomson-Engineering, 2 edition, 1998.
[11] Daniel Weiler and Julian Eggert. Multi-dimensional histogram-based image
segmentation. In Proceedings of the 14th International Conference
on Neural Information Processing (ICONIP), pages 963-972, 2007.