INTERPRETATION-DIRECTED SEGMENTATION OF ERTS IMAGES

ID
TR-76-03
Authors
Dale W. Starr and Alan K. Mackworth
Publishing date
June 1976
Abstract

Automatic interpretation of images from Earth Technology Satellites 1 (ERTS-1) can be used in a variety of applications with considerable accuracy. Most Earth Resources systems however, classify strictly on a point by point basis, with no use of any spatial knowledge. Standard photo-interpretation techniques are combined with some techniques from Artificial Intelligence to produce an increase in accuracy over a point-by-point classification method. Traditional classification methods are used to obtain an initial segmentation of the image. Then, a controlled region merging process allows the regions with unambiguous interpretations to influence the interpretation of neighbouring regions, thereby introducing considerable context sensitivity into the interpretation process. Results are given of an experiment to interpret areas of different forest cover.