The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 1207–1211, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-1207-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 1207–1211, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-1207-2019

  05 Jun 2019

05 Jun 2019

A NEW THINKING OF LULC CLASSIFICATION ACCURACY ASSESSMENT

K. S. Cheng1,2, J. Y. Ling1, T. W. Lin1, Y. T. Liu1, Y. C. Shen1, and Y. Kono3 K. S. Cheng et al.
  • 1Dept. of Bioenvironmental Systems Engineering, National Taiwan University, Taiwan, R.O.C.
  • 2Master Program in Statistics, National Taiwan University, Taiwan, R.O.C.
  • 3Center for Southeast Asian Studies, Kyoto University, Kyoto, Japan

Keywords: Land-Use/Land-Cover (LULC), Accuracy Assessment, Confusion Matrix, Confidence Interval, Bootstrap Resampling

Abstract. A majority of studies involving remote sensing LULC classification conducted classification accuracy assessment without consideration of the training data uncertainty. In this study we present new concepts of LULC classification accuracies, namely the training-sample-based global accuracy and the classifier global accuracy, and a general expression of different measures of classification accuracy in terms of the sample dataset for classifier training and the sample dataset for evaluation of classification results. Through stochastic simulation of a two-feature and two-class case, we demonstrate that the training-sample confusion matrix should replace the commonly adopted reference-sample confusion matrix for evaluation of LULC classification results. We then propose a bootstrap-simulation approach for establishing 95% confidence intervals of classifier global accuracies.