基于深度学习和多次棋盘分割法的高分辨率影像河流提取

针对目前从遥感影像中提取的河流, 尤其是细小河流容易出现中断的情况, 将深度学习与多次棋盘分割法相结合, 应用于高分辨率遥感影像的河流提取。基于对山区、平原和城市3景高分二号卫星遥感影像的实验表明, 与现有的方法相比, 该方法提取的河流更加连续, 并且能够提取高分二号卫星遥感影像中两个像元的细小河流。

River Extraction from High-Resolution Satellite Images Combining DeepLearning and Multiple Chessboard Segmentation

Using existing methods to extract rivers, especially the small river from remote sensing images, isliable to be interrupted. The combination of deep learning and multiple chessboard segmentation is applied to riverextraction from high resolution remote sensing images. Three GF-2 satellite remote sensing images in mountainarea, plain and city are used for experiment. The results show that compared with the existing methods, extractedriver by proposed method is more continuous. The small rivers accounts for two pixel widths can also be extractedin GF-2 satellite remote sensing images.