Evaluations of unsupervised methods for land-cover/use classifications of landsat TM data

Supervised classification methods have been mainly used for land-cover/use classifications from the view point of classification accuracy, especially in the area where detailed land use dominates as in Japan. However, for high ground resolution image data such as Landsat TM and SPOT HRV data, it has been clarified that the classification accuracy using supervised classifications is lower than what was expected. One of the major reasons of this phenomenon may be caused by the difficulty with selecting sufficient training data. There is a possibility to solve this problem by using an unsupervised learning method because of its independent sampling characteristics. However, quantitative evaluations of performances of unsupervised classification methods for high resolution satellite data are not yet established. In this study, classification accuracies of unsupervised classification methods were evaluated for Landsat TM data with comparison to a conventional supervised maximum likelihood classification. The evaluated unsupervised methods are six kinds of hierarchical clustering, and a minimum residual clustering. Classification accuracies were estimated quantitatively by using digital land-cover/use test site data which were created by the authors. As a result, most of the clustering methods showed higher classification accuracies than a conventional supervised maximum likelihood classification, especially for urban and agricultural areas.