Small Waterbody Extraction With Improved U-Net Using Zhuhai-1 Hyperspectral Remote Sensing Images

Water extraction is an important prerequisite for the protection and rational use of water resources. The existing waterbody extraction methods are mostly used for the extraction of large- and medium-sized waterbodies, whereas less attention has been paid to small waterbodies. In this letter, we adapt the U-Net convolutional neural network to extract small waterbodies from Zhuhai-1 satellite hyperspectral remote sensing image. To the best of our knowledge, this is the first time that U-Net framework has been used for small waterbody extraction from satellite hyperspectral image. Specifically, we increase the depth of the network, and because there are far more negative samples (non-waterbodies) in remote sensing data than positive samples (waterbodies), Intersection over Union (IoU) is used as an evaluation indicator during model training. The results show that this method can accurately extract small waterbodies in the complex scenes. Compared with the traditional methods of support vector machine and the normalized waterbody index, the accuracy of this method is significantly higher, and both the Recall and the Precision are close to 90%.