Integration of satellite images and open data for impervious surface classification

Abstract

Supervised learning is vital to classify impervious surface from satellite images. Despite its effectiveness, the training samples need to be provided manually, which is time consuming and labor intensive, or even impractical when classifying satellite images at the regional/global scale. This study, therefore, sets out to automatically generate training samples from open data, based on the fact that cities and urban areas are nowadays full of individual geo-referenced data, such as social network data. The proposed method consists of automatic generation of training samples based on a filtering process of open data, satellite image pre-processing, and impervious surface detection using one class classification (OCC). Two Landsat-8 Operational Land Imager images were selected to test the proposed method. The results show that the proposed method is effective in impervious surface with good classification accuracy. The findings in this study shine new light on the applications of open data in remote sensing.