Pansharpening by Convolutional Neural Networks
Pansharpening by Convolutional Neural Networks
复制标题
DOI：
10.3390/rs8070594
复制
发表时间：
2016-07-01
期刊：
影响因子：
5
通讯作者：
Scarpa, Giuseppe
中科院分区：
文献类型：
--
作者：
Masi, Giuseppe;Cozzolino, Davide;Scarpa, Giuseppe
提出了一种基于卷积神经网络的新的全色锐化方法。我们将最近针对超分辨率提出的一种简单有效的三层架构应用于全色锐化问题。此外，为了在不增加复杂性的情况下提高性能，我们通过纳入几种典型的遥感非线性辐射指数图来扩充输入。在三个有代表性的数据集上进行的实验表明，所提出的方法提供了非常有前景的结果，在全参考和无参考指标方面，以及在视觉检查方面，都与当前最先进的技术具有很大的竞争力。
A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.