Remote sensing minefield area reduction: Semantic knowledge-based image understanding

This study addresses the design issues of an intelligent system for image understanding applied to remote sensing minefield area reduction. We propose a system using a combination of image processing techniques and a knowledge-based intelligent scheme that interactively cooperate together to produce a danger map of the surveyed area. This contribution suggests a semantic knowledge-based scene interpretation system. Our approach exploits semantic contextual information, combining scene and application domain knowledge. The conceptual issues of the proposed system, developed under the EU-IST ARC project ”Airborne minefield area reduction”, are presented and discussed.