ISSUES OF REPRESENTING CONTEXT ILLUSTRATED BY VIDEO-SURVEILLANCE APPLICATIONS

This paper tackles several issues of context representation in knowled ge-based systems. First, we propose a definition of context through th e description of the different types of information manipulated by a p rocess. Thanks to this definition we explain the role of the granulari ty level of processing and the role of the abstraction level of applic ation in modelling context. Based on this definition two main issues r elated to context are tackled: how context representation can be built and organized and how context contents can be re-used for other appli cations. Then we propose several solutions to deal with these issues: using a multi-viewpoint representation and describing context through symbolic information. We illustrate the proposed context model with th e process of dynamic scene interpretation. After explaining the reason s why this process is particularly concerned with the use of contextua l information, we describe the context representation and its implemen tation for this specific process. Finally, we give an example illustra ting the utilization of the context representation and we describe the software we have developed to ease the acquisition stage of context c ontents. (C) 1998 Academic Press Limited.