Pixel-wise regression using U-Net and its application on pansharpening
Pixel-wise regression using U-Net and its application on pansharpening
复制标题
DOI：
10.1016/j.neucom.2018.05.103
复制
发表时间：
2018-10-27
期刊：
影响因子：
6
通讯作者：
Tang, Huiming
中科院分区：
文献类型：
--
作者：
Yao, Wei;Zeng, Zhigang;Tang, Huiming
卷积神经网络被广泛用于解决图像识别和其他分类问题，其中整个图像被视为单个对象。本文以遥感图像的泛锐化问题为例，讨论了如何利用卷积神经网络建立逐像素回归模型。为了满足逐像素分析对定位精度和回归过程的抽象能力的要求，在我们的研究中，一个U形结构被应用于构建网络模型。通过在网络前端和后端的卷积层之间建立直接连接，可以保留对应于不同分辨率级别的图像特征。然后，可以获得这些多分辨率图像特征与目标图像像素值之间的回归关系。实验结果表明，该模型能有效地实现图像的全色锐化，与现有方法相比，在控制图像几何变形和颜色失真方面具有更好的性能。(C)2018爱思唯尔出版社
Convolutional neural networks are widely used for solving image recognition and other classification problems in which the whole image is considered as a single object. In this paper, we take the pansharpening problem of remote sensing images as an example to discuss how to establish pixel-wise regression models using convolutional neural networks. In order to meet the requirements of pixel-wise analysis on both the localization accuracy and the abstraction ability of the regression process, a U-shaped architecture is applied in our study to construct the network model. By establishing direct connections between convolution layers at the front end and the back end of the network, image features corresponding to different resolution levels can be retained. Then a regression relationship between these multi-resolution image features and the target image pixel values can be obtained. Experimental results show that the proposed regression model can effectively accomplish pansharpening, with better performance in controlling geometric deformation and color distortion, as compared to some state of the art methods. (C) 2018 Published by Elsevier B.V.