Analyst variation associated with landcover image classification of Landsat ETM+ data for the assessment of coarse spatial resolution regional/global landcover products

Abstract

This study examined analyst variation associated with land cover image classification using 30 x 30 m Landsat ETM+ data for the assessment of coarse spatial resolution regional/global land cover products. The study was designed to test the effect of varying training site selections (location and number) among six analysts performing a supervised classification on a Landsat ETM+ image. Design constraints maintained other aspects of the classification process constant (i.e., type of classifier, choice of band combinations, etc.). Results indicated training site selection alone did not provide a predictive measure of classification accuracy. Only when training data selection was combined with variations in spatial resolution did significant differences occur. Differences in classification accuracies between analysts increased three-fold in the aggregation process from 90 x 90 m to 1200 x 1200 m. Error sources (i.e. analyst differences) and the dynamics of the spatial aggregation process can potentially account for differences in environmental modeling outcomes.

Department

Natural Resources and the Environment

Publication Date

12-1-2013

Journal Title

GIScience and Remote Sensing

Publisher

Taylor & Francis

Digital Object Identifier (DOI)

10.1080/15481603.2013.865399

Document Type

Article

Rights

© 2013 Copyright Taylor and Francis Group, LLC.

Share

COinS