基于稀疏表示的遥感图像超分辨率重建  

Super-resolution reconstruction of sparse remote sensing images

作　　者：王银玲 王昕[1] WANG Yinling;WANG Xin(School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China)

机构地区：[1]长春工业大学计算机科学与工程学院,吉林长春130012

出　　处：《长春工业大学学报》2021年第2期175-180,共6页Journal of Changchun University of Technology

基　　金：吉林省教育厅“十三五”科学技术研究项目(JJKH20181040KJ)。

摘　　要：根据稀疏定理,首先对遥感图像数据进行训练,得到高分辨率图像块字典与低分辨率图像块字典,然后利用低分辨率图像块字典求出稀疏表示系数,最后根据稀疏表示系数得到超分辨率重建图像。结果可以看出,经过改进后,重建图像的客观评价指标更优。With sparse theorem,remote sensing image data is trained to obtain both the high-resolution and low-resolution image block dictionary.The low-resolution block is used to get the sparse representation coefficient which is for super-resolution image reconstruction.It can be seen from the results that after improvement,the objective evaluation index of the reconstructed image is better.

关 键 词：稀疏表示 超分辨率重建 迭代反投影 稀疏正则化 

分 类 号：TN391.41[电子电信—物理电子学]