面向多光谱卫星成像的广义光谱超分辨率  

Generalized Spectral Super-resolution for Multispectral Satellite Imagings

作　　者：何江[1] 袁强强[1] 李杰[1] HE Jiang;YUAN Qiangqiang;LI Jie(School of Geodesy and Geomatics,Wuhan University,Wuhan 430079,China)

机构地区：[1]武汉大学测绘学院,武汉430079

出　　处：《光子学报》2023年第2期151-158,共8页Acta Photonica Sinica

基　　金：国家自然科学基金(Nos.41922008,62071341,61971319)。

摘　　要：针对多种多光谱卫星成像模式,对原始光谱超分辨率概念进行扩充,提出一种联合数据驱动与模型驱动的深度学习算法。模拟构建的多个数据集,讨论了不同多光谱成像模式下的光谱超分辨率之间的差异,验证了所构建算法的稳健性,提高了现有多光谱卫星影像利用率,对光谱超分辨率的更广泛情形进行了概括。Spectral super-resolution,a very important computational imaging technology to obtain highspatial-resolution hyperspectral images at a low cost,has received more and more attention.However,the existing works about spectral super-resolution are all based on the assumption that there is only spectral degradation between the observed multispectral data and the real spectra.For multispectral satellites,different imaging modes also include spatial degradation.For this type of data,the existing spectral superresolution usually uses only a part of the multispectral data to reconstruct hyperspectral data,which will lead to the waste of multispectral data.This paper extends the traditional spectral super-resolution to the generalized spectral super-resolution by summarizing the imaging modes of different multispectral satellites.There are FusSR,which makes full use of the additional multispectral bands with a lower spatial resolution to further optimize the spectral reconstruction,and PansSR,which uses the panchromatic channel with a higher spatial resolution to simultaneously improve the spatial resolution of the reconstructed hyperspectral data.The above two extended spectral super-resolution technologies have made the best of all multispectral data.Besides,after modeling the imaging degradation,the generalized spectral super-resolution is expressed as an optimal problem containing two data fidelity terms and one image prior term.To ensure the algorithm's physical interpretability,the deep unrolling strategy is adopted to build a generalized spectral super-resolution network that combines data-driven and model-driven manner.In addition,the idea of spectral grouping is also employed to generate the initial results.The spectral grouping includes three steps.Firstly,the difference information between bands is calculated.Then the coverage relationship of spectral response function between hyperspectral images and multispectral images is counted.Lastly,bands with high correlation are uniformly reconstructed,so as to eliminat

关 键 词：广义光谱超分辨率 多光谱成像 高光谱成像 数据驱动 模型驱动 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]