Abstract
Conventional approaches to most image understanding problems suffer from fragility when applied to natural environments. Complexity in Intelligent Systems can be managed by breaking the world into manageable contexts. GRAVA supports robust performance by treating changes in the program’s environment as context changes. Automatically tracking changes in the environment and making corresponding changes in the running program allows the program to operate robustly.
We describe the architecture and explain how it achieves robustness. GRAVA is a reflective architecture that supports self-adaptation and has been successfully applied to a number of visual interpretation domains.
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
Robertson, P.: A Self-Adaptive Architecture for Image Understanding. PhD thesis, University of Oxford (2001)
Maes, P., Nardi, D.: Meta-Level Architectures and Reflection. North-Holland (1988)
Giroux, S.: Open reflective agents. In M. Wooldridge, J.P. M., Tambe, M., eds.: Intelligent Agents II Agent Theories, Architectures, and Languages. Springer (1995) 315–330
Laddaga, R., Robertson, P.: Yolambda Reference Manual. Dynamic Object Language Labs, Inc. (1996)
IEEE: Ieee standard for the scheme programming language. IEEE Standard 1178–1990, IEEE Pisscaataway (1991)
Robertson, P., Laddaga, R.: A self-adaptive architecture and its aplication to robust face identification. In: PRICAI 2002, Trends in Artificial Intelligence, Springer Verlag, LNAI 2417 (2002) 542–551
Robertson, P., Laddaga, R.: An agent architecture for information fusion and its application to robust face identification. In: Proceedings of the 21st International Conference on Applied Informatics, Innsbruck Austria. (2003) 132–139
Robertson, P., Laddaga, R.: Principle component decomposition for automatic context induction. In: Proceedings Artificial and Computational Intelligence, Tokyo 2002, ACI (2002)
Viterbi, A.: Error bounds for convolution codes and an asymptotically optimal decoding algorithm. IEEE Transactions on Information Theory 13 (1967) 260–269
Baum, L.: An inequality and associated maximization technique in statistical estimation for probabilistic functions of a markov process. Inequalities 3 (1972) 1–8
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Robertson, P., Laddaga, R. (2003). GRAVA: An Architecture Supporting Automatic Context Transitions and Its Application to Robust Computer Vision. In: Blackburn, P., Ghidini, C., Turner, R.M., Giunchiglia, F. (eds) Modeling and Using Context. CONTEXT 2003. Lecture Notes in Computer Science(), vol 2680. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44958-2_43
Download citation
DOI: https://doi.org/10.1007/3-540-44958-2_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40380-7
Online ISBN: 978-3-540-44958-4
eBook Packages: Springer Book Archive