Dual Self-Attention Swin Transformer for Hyperspectral Image Super-Resolution
Dual Self-Attention Swin Transformer for Hyperspectral Image Super-Resolution
复制标题
DOI：
10.1109/tgrs.2023.3275146
复制
发表时间：
2023
影响因子：
8.2
通讯作者：
Yaqian Long;Xun Wang;Meng Xu;Shuyu Zhang;Shuguo Jiang;S. Jia
中科院分区：
文献类型：
--
作者：
Yaqian Long;Xun Wang;Meng Xu;Shuyu Zhang;Shuguo Jiang;S. Jia
空间分辨率是衡量高光谱成像质量的重要指标，在没有任何辅助信息的情况下获得高分辨率高光谱图像变得越来越具有挑战性。一种有前途的方法是使用深度学习（DL）技术从低分辨率（LR）图像（即超分辨率（SR））中重建高光谱图像。虽然卷积神经网络通常用于高光谱图像SR (HSI-SR)，但由于缺乏远程依赖学习能力，往往导致不可避免的性能下降。在本文中，我们提出了一种双自关注Swin变压器SR （DSSTSR）网络，该网络利用了移位窗口（Swin）变压器在全局和局部特征的空间表示方面的能力，并从HSI的相邻波段学习光谱序列信息。此外，DSSTSR还引入了图像去噪模块，利用小波变换方法减轻条纹噪声对HSI-SR的影响。我们使用公开近距离数据集进行的大量实验表明，DSSTSR在三个图像质量指标方面优于其他最先进的HSI-SR方法。此外，我们将DSSTSR应用于卫星高光谱图像的SR，获得了更好的分类结果。与竞争对手相比，DSSTSR在提高空间分辨率的同时保留了光谱信息。这些结果表明，DSSTSR网络在遥感图像处理标准化和实际应用方面具有很大的潜力。
Spatial resolution is a crucial indicator for measuring the quality of hyperspectral imaging (HSI) and obtaining high-resolution (HR) hyperspectral images without any auxiliary information has become increasingly challenging. One promising approach is to use deep-learning (DL) techniques to reconstruct HR hyperspectral images from low-resolution (LR) images, namely super-resolution (SR). While convolutional neural networks are commonly used for hyperspectral image SR (HSI-SR), they often lead to unavoidable performance degradation due to the lack of long-range dependence learning ability. In this article, we propose a dual self-attention Swin transformer SR (DSSTSR) network that utilizes the ability of the shifted windows (Swin) transformer in the spatial representation of both global and local features and learns spectral sequence information from adjacent bands of HSI. Additionally, DSSTSR incorporates an image denoising module using the wavelet transformation method to mitigate the impact of stripe noise on HSI-SR. Our extensive experiments using publicly close-range datasets demonstrate that DSSTSR outperforms other state-of-art HSI-SR methods in terms of three image quality metrics. Furthermore, we applied DSSTSR to the SR of satellite hyperspectral images and achieved improved classification results. Compared to its competitors, DSSTSR exhibits superior performance in enhancing spatial resolution while preserving spectral information. These results suggest that the DSSTSR network has great potential for standardization in remote-sensing image processing and practical applications.