Considering Non overlapped Bands Construction A General Dictionary Learning Framework for Hyper spec

Improving the spatial resolution of hyperspectral (HS) images is of great significance for the subsequent applications. As the multispectral (MS) image can provide abundant complementary land-cover spatial information, HS and MS image fusion (HMF) methods have become a mainstream to generate HS images with both high spatial and spectral resolution. HMF has witnessed rapid progress by leveraging dictionary learning (DicL) technique. However, existing approaches are highly sensitive to the image registration accuracy, and the reconstruction performance of the nonoverlapped spectral bands between HS and MS images is extremely limited. To alleviate the effect of image misregistration and enrich the spectral information of nonoverlapped bands, a general HMF DicL framework, which considers nonoverlapped spectral bands reconstruction and image misregistration, is proposed in this article. For registration error, the proposed method is rectified by the improved DicL, which can solve the problem of the spectral information matching gap existing in traditional HMF methods between HS image and MS image. Meanwhile, for nonoverlapped spectral bands reconstruction, a novel coefficient optimization strategy is adopted to improve the nonoverlapped bands reconstruction. Therefore, the registration error can be avoided to the greatest extent and the accuracy of nonoverlapped bands reconstruction can be effectively improved. Experiments both on simulated and real-world datasets demonstrate that the proposed method can effectively tackle the registration error problem and increase the HMF accuracy with different spectral ranges. Meanwhile, the proposed framework provides guidance significance for the DicL-based HMF methods with various constraints to improve the nonoverlapped bands reconstruction accuracy.