Accession Number : ADP003020

Title :   Expert Systems for Understanding Remotely Sensed Images,

Corporate Author : MARYLAND UNIV COLLEGE PARK

Personal Author(s) : Kanal,L. N. ; Lambird,B. A. ; Lavine,D.

Report Date : 31 JAN 1984

Pagination or Media Count : 19

Abstract : This paper discusses some basic issues in the design of expert or knowledge-based systems for understanding remotely sensed images, with particular reference to cartographic feature extraction problems. The many types of knowledge that must be modelled in remote sensing and cartography and the characteristics distinguishing cartographic image processing from other image processing tasks are outlined. The problems of knowledge representation, knowledge-based search, fusion of information from multisensor sources and knowledge-bases, and the resolution of conflicting information are briefly treated. A distributed architecture and a control structure based on a parallel non-directional search algorithm are outlined. Finally, open problems are mentioned. (Author)

Descriptors :   *Information systems, *Image processing, *Remote detectors, Mapping, Extraction

Distribution Statement : APPROVED FOR PUBLIC RELEASE