TESTING LAND-USE MAP ACCURACY
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
In providing land-use maps to meet prescribed specification accuracy standards from remote sensing data, some form of reliable statistical testing is necessary. Cost considerations in operational remote sensing land-use surveys necessitate the use of a sampling stragety for field checking. Such a strategy should require that only the minimum number of field areas necessary need be checked, yet ensure that results are still statistically valid. Such a procedure is explained and recommended for inclusion in all land-use survey job specifications issued by international, government and other user agencies.