Abstract

There is an increasing need to understand pattern and growth of impervious surfaces in rural regions. However, studies using remote sensing of impervious surfaces have often focused on mapping impervious surfaces in urban regions with less emphasis placed on the rural impervious surfaces. In this paper, we use the 12 featured spaces to detect impervious surface from Landsat TM and OLI, including 6 indicators: (NDBI), (SAVI), (SI), (RISI), (Brightness), (Max.diff) and 6- spectral bands of Landsat satellite images. These featured spaces are used to recognize of impervious surface features on satellite images with the help of K-Nearest Neighbors algorithm (KNN). The results showed that K-Nearest Neighbors algorithm applied to the selected features group of impervious surfaces (6 spectral bands, 6 indicators) allows accurate extraction of impervious surfaces in countryside. This is the basis to assess the trend of impervious surface area in space and time research.