ABSTRACT
This paper mainly introduces the methods of extracting landslide information using ALOS images and GIS (Geographical Information System) technology. In this study, we classified images using three different methods for extracting landslide information based on characteristics of ALOS image. The three different methods respectively were unsupervised, supervised, and PCA (Principal Components Analysis) classification. From the result of classification images, we found that the classified image by PCA supervised method was better than other methods. But the accuracy of landslide information extracted from this classification image was still very low and had many problems. Because the value of pixel between the landslide and the sand and some field area was very close, so we cannot distinguish those areas just using image classification method. To solve this problem, we applied GIS technology with DEM data in the study area. The result shows that the accuracy of the extracted landslide information after used supervised and GIS methods were better than before.
