We create an open remote sensing landslide dataset called Bijie landslide dataset for developing automatic landslide detection methods. The dataset consists of satellite optical images, shapefiles of landslides’ boundaries and digital elevation models. All the images in this dataset, i.e. 770 landslide images (red points) and 2003 non-landslide images were cropped from the TripleSat satellite images captured from May to August 2018.
For the landslide instances, we provide the landslide images (*.png), the landslide shapefiles (mask files, *.png), the corresponding DEM data (*.png) and each landslide’ boundary coordinates (polygon, *.txt). For the non-landslide samples, the images and the corresponding DEM data were provided. All the data was prepared with a careful three-fold inspection to ensure its reliability. More details can be found in: Ji, S., Yu, D., Shen, C., Li, W., & Xu, Q. Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides, 1-16, 2020.