By Topic

A hierarchical expert system for updating forestry maps with Landsat data

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Goldberg, M. ; University of Ottawa, Ottawa, Ont., Canada ; Goodenough, D.G. ; Alvo, M. ; Karam, G.M.

This paper reports upon the design of an expert system at the Canada Centre for Remote Sensing for updating maps of forested areas using Landsat imagery. The system is decomposed into a number of specialist experts organized in a hierarchical fashion around a series of blackboards which are used for communications between the different levels. At the lowest level in the hierarchy, is an expert which acts as the interface to the low-level, procedural-based, image processing algorithms. A short review of expert systems, with special emphasis on the analysis of remotely sensed imagery, is first given. Various approaches to treating uncertainty in expert systems are then discussed, in particular, the approach based upon the theory of evidence. The forestry map updating problem is described and the classical solution presented. Our hierarchically organized expert system is then presented in the context of this problem. Finally, an expert interface to the image processing algorithms is described.

Published in:

Proceedings of the IEEE  (Volume:73 ,  Issue: 6 )