GRAVA: An architecture supporting automatic context transitions and its application to robust computer vision. Conventional approaches to most image understanding problems su?er from fragility when applied to natural environments. Complexity in Intelligent Systems can be managed by breaking the world intomanageable contexts. GRAVA supports robust performance by treatingchanges in the program�s environment as context changes. Automaticallytracking changes in the environment and making corresponding changesin the running program allows the program to operate robustly.We describe the architecture and explain how it achieves robustness.GRAVA is a re?ective architecture that supports self-adaptation and hasbeen successfully applied to a number of visual interpretation domains.
References in zbMATH (referenced in 4 articles , 1 standard article )
Showing results 1 to 4 of 4.
- Perez-Palacin, Diego; Merseguer, José: Performance evaluation of self-reconfigurable service-oriented software with stochastic Petri nets (2010)
- Robertson, Paul; Laddaga, Robert: GRAVA: an architecture supporting automatic context transitions and its application to robust computer vision (2003)
- Trias-Sanz, Roger; Loménie, Nicolas: Automatic bridge detection in high-resolution satellite images (2003)
- Robertson, Paul; Laddaga, Robert: A self-adaptive architecture and its application to robust face identification (2002)