In this paper a flexible and generally applicable knowledge--based framework for large-scale geographic map image analysis is proposed. The described framework is composed of three schemas, namely: map model, object detectors and image analysis flow scheme. A new, efficient hybrid knowledge representation scheme, and a flaxible, mixed control strategy based on reasoning with incomplete information are proposed. To increase reliability and accuracy of map image analysis, accumulation of information from defferent sources is used. The proposed approach has been implemented in the map conversion module MAPIN of the Integrated Spatial Organization System SIT, [20].
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.