一种基于稀疏字典和残余字典的遥感图像超分辨重建算法

Remote Sensing Image Super-resolution by Using Sparse Dictionary and Residual Dictionary

为了解决低分辨率遥感图像超分辨率重建问题,提出一种基于稀疏字典和结构自相似性的遥感图像超分辨方法。首先,引入了稀疏字典学习方法,改善了字典的结构性,得到的字典具有较好的正则性与灵活性。此外,为了更好地重建高分辨率图像,学习初始稀疏字典对和残余稀疏字典对。初始稀疏字典对用于重建初始高分辨率遥感图像;初始高分辨率遥感图像相对于原始高分辨率图像失去了部分细节信息,用残余稀疏字典对对图像的残留信息进行重建。最后,根据遥感图像存在大量的结构相似性特性,利用非局部均值算法对重建图像进行修正。实验结果表明,本算法与其他算法相比,图像质量在主观和客观方面都有所提高,峰值信噪(PSNR)比达到24.690 5,SSIM达到0.736 3。

A super resolution( SR) method for remote sensing images based on sparse dictionary and structural self-similarity was proposed. Furthermore,compared with correspondence between LR and HR image patches from a conventional SR methods,two dictionary pairs,i. e. primitive sparse dictionary pair and residual sparse dictionary pair, are raining database. The primitive sparse dictionary pair is learned to reconstruct initial high-resolution( HR) remote sensing image from a single low-resolution( LR) input. However,the initial HR remote sensing image loses some details compare with the corresponding original HR image completely. Therefore,residual sparse dictionary pair is learned to reconstruct residual information. Finally,self-similarity structural widely exist in remote sensing images and this feature can be used to correct the reconstructed image by nonlocal means( NLM)method. Experimental results showed that the proposed algorithm provides better subjective and objective quality,when compared to the conventional algorithms and its PSNR is 24. 690 5,SSIM is 0. 736 3.