RSDehazeNet: Dehazing Network With Channel Refinement for Multispectral Remote Sensing Images
RSDehazeNet: Dehazing Network With Channel Refinement for Multispectral Remote Sensing Images
复制标题
RSDehazeNet：多光谱遥感图像通道细化的去雾网络
DOI：
10.1109/tgrs.2020.3004556
复制
发表时间：
2021-03-01
影响因子：
8.2
通讯作者：
Li, Kun
中科院分区：
文献类型：
--
作者：
Guo, Jianhua;Yang, Jingyu;Li, Kun
多光谱遥感（RS）图像经常受到雾霾的污染，降低了遥感数据的质量，降低了解译和分类的精度。最近，新兴的深度卷积神经网络（CNN）为我们提供了RS图像去雾的新方法。不幸的是，CNN的能力受到缺乏足够的模糊-干净的RS图像对的限制，这使得监督学习变得不切实际。为了满足监督CNN的数据饥饿，我们提出了一种新的烟雾合成方法，通过建模的波长依赖性和空间变化的特点，在遥感图像中的烟雾产生现实的烟雾多光谱图像。该方法不仅弥补了多光谱遥感图像去雾中训练样本的不足，而且为定量评价提供了基准数据。此外，我们还提出了一个端到端的RSDehazeNet去雾。我们利用RSDehazeNet中的局部和全局残差学习策略，以快速收敛并具有上级性能。通道注意模块被纳入利用强通道相关性的多光谱遥感图像。实验结果表明，该网络优于国家的最先进的方法合成数据和真实的Landsat-8 OLI多光谱遥感图像。
Multispectral remote sensing (RS) images are often contaminated by the haze that degrades the quality of RS data and reduces the accuracy of interpretation and classification. Recently, the emerging deep convolutional neural networks (CNNs) provide us new approaches for RS image dehazing. Unfortunately, the power of CNNs is limited by the lack of sufficient hazy-clean pairs of RS imagery, which makes supervised learning impractical. To meet the data hunger of supervised CNNs, we propose a novel haze synthesis method to generate realistic hazy multispectral images by modeling the wavelength-dependent and spatial-varying characteristics of haze in RS images. The proposed haze synthesis method not only alleviates the lack of realistic training pairs in multispectral RS image dehazing but also provides a benchmark data set for quantitative evaluation. Furthermore, we propose an end-to-end RSDehazeNet for haze removal. We utilize both local and global residual learning strategies in RSDehazeNet for fast convergence with superior performance. Channel attention modules are incorporated to exploit strong channel correlation in multispectral RS images. Experimental results show that the proposed network outperforms the state-of-the-art methods for synthetic data and real Landsat-8 OLI multispectral RS images.