Community Research and Development Information Service - CORDIS

Abstract

Remotely-sensed imagery from recent satellite sensors now offers considerable potential for mapping the Earth's surface. However, some developments are still needed in order to process the image information and to present it in a form which is compatible with the needs of end-users. One typical application in which this situation is particularly acute is land cover mapping. A procedure is being developed to generalise automatically satellite image data products into cartographically-acceptable land cover maps. The method initially involves low-level generalisation procedures concerned with smoothing a detailed neural network classification to form primitive spatial units, followed by a higher-level problem-solving stage. In the higher-level stage an expert system approach will be used to optimise the decision-making process in macroscopic generalisation.

Additional information

Authors: GOFFREDO S, JRC Ispra (IT);WILKINSON G G, JRC Ispra (IT);FISHER P F, University of Leicester, Department of Geography (GB)
Bibliographic Reference: Paper presented: Remote Sensing Society Annual Conference 1993, Chester (GB), September 16-17, 1993
Availability: Available from (1) as Paper EN 37650 ORA
Record Number: 199311037 / Last updated on: 1994-11-29
Category: PUBLICATION
Original language: en
Available languages: en