The use of deep learning for water extraction requires precise pixel-level labels. However, it is very difficult to label high-resolution remote sensing images at the pixel level. Therefore, we study how to utilize point labels to extract water bodies and propose a novel method called the neighbor feature aggregation network (NFANet). Compared with pixellevel labels, point labels are much easier to obtain, but they will lose much information. In this paper, we take advantage of the similarity between the adjacent pixels of a local water-body, and propose a neighbor sampler to resample remote sensing images. Then, the sampled images are sent to the network for feature aggregation. In addition, we use an improved recursive training algorithm to further improve the extraction accuracy, making the water boundary more natural. Furthermore, our method utilizes neighboring features instead of global or local features to learn more representative features. The experimental results show that the proposed NFANet method not only outperforms other studied weakly supervised approaches, but also obtains similar results as the state-of-the-art ones.
翻译:使用深层水提取学的方法需要精确的像素级标签。 但是, 在像素级标签上贴高分辨率遥感图像标签非常困难。 因此, 我们研究如何使用点标签提取水体, 并提出称为邻居地貌聚合网( NFANet ) 的新颖方法。 与像素级标签相比, 点标签更容易获得, 但是它们会损失很多信息 。 在本文中, 我们利用邻近的当地水体像素之间的相似性, 并推荐一个邻居样板来重塑遥感图像 。 然后, 抽样图像被发送到功能集成网络 。 此外, 我们使用改进的循环培训算法来进一步提高提取精度, 使水边界更加自然。 此外, 我们的方法使用邻接点而非全球或地方特征来学习更具代表性的特征。 实验结果表明, 拟议的NFANet方法不仅比其他研究过弱的系统, 也取得了类似于状态技术的类似结果 。