Cooperation and fusion of operators: Application to automatic matching of cartographic objects

The aim of this study is to provide a system able to identify and to match linear cartographic objects on SPOT images using geographic databases, and to update the databases. Automatic matching of geographic features in complex remote sensing images faces different problems, such as diversity of context or complexity of information. In order to simplify identification and to limit the search space, the authors use databases as a priori knowledge to help the scene understanding. But, diversity and imprecision of information sources to process generate new problems. The fuzzy logic theory has proved in the last years its ability to solve a large range of problems concerning imprecision