Knowledge based dynamic modeling system for sensor fusion applications

In a dynamic situation, data modalities range from static (e.g., spatial data representation, objects description) to dynamic (e.g., moving entities, evolving objects). Static data typically reside on local database systems while dynamic data are continuously generated from sensors or special events; we need to integrate both types of data for a realistic modeling of a dynamic situation. In this paper we discuss the implementation of a knowledge based centered system which integrates (1) an expert system shell, (2) a geographical information system, and (3) a sensor data processor. The knowledge encoded in the expert system shell is able to reason on the different data collected over time and, accordingly, to trigger some actions. Actions are of two forms: (1) general messages/alerts to the user to denote a particularly interesting data configuration, and (2) feedback to the various sub-components to improve processing and prediction operations.