Landslide Semantic Segmentation Using Satellite Imagery

Abstract

This work aims to improve the accuracy of landslide detection with single satellite imagery by using slope factor extraction and normalized difference vegetation index (NDVI) extraction and by combining three semantic segmentation models based on a convolutional neural network with a decision tree. The proposed method uses three semantic segmentation models with a decision tree. The first model is trained by a training set of color images. The second model is trained by a training set of slope factor images. The third model is trained by a training set of NDVI images. The slope factor and NDVI are extracted from color images that contain red, green, and blue bands. The results from three models are used to generate features for training the classification decision tree. Evaluation metrics (precision, recall, and F2 score) can be improved by using slope factor and NDVI. In combining three models, the F1 score and F2 score are increased more than using single of color images 16.71% and 24.15%, respectively. Moreover, the slope factor detection model and NDVI detection model can support some areas that color image detection model cannot detect.