학술교육원

Impervious surfaces are important indicators for urban development  monitoring. Accurate mapping of urban impervious surfaces with observational satellites, such as VNREDSat-1,  remains challenging due to the spectral diversity not captured by an individual PAN image. In this article, five  multi-resolution image fusion techniques were compared for the task of classifting urban impervious  surfaces. The result shows that for VNREDSat-1 dataset, UNB and Wavelet tranformation methods are the best  techniques in reserving spatial and spectral information of original MS image, respectively. However, the UNB  technique gives the best results when it comes to impervious surface classification, especially in the  case of shadow areas included in non-impervious surface group.