浏览全部资源
扫码关注微信
1. 四川大学电子信息学院
2. 南京邮电大学 通信与信息工程学院
Published:2015,
Published Online:11 October 2014,
扫 描 看 全 文
杨晓敏,吴炜,干宗良,严斌宇,张莹莹.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[J].工程科学与技术,2015,47(3):71-76.
RemoteSensingImageSuper-resolutionbyUsingSparseDictionaryandResidualDictionary. [J]. Advanced Engineering Sciences 47(3):71-76(2015)
杨晓敏,吴炜,干宗良,严斌宇,张莹莹.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[J].工程科学与技术,2015,47(3):71-76. DOI: 10.15961/j.jsuese.2015.03.010.
RemoteSensingImageSuper-resolutionbyUsingSparseDictionaryandResidualDictionary. [J]. Advanced Engineering Sciences 47(3):71-76(2015) DOI: 10.15961/j.jsuese.2015.03.010.
中文摘要: 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24.6905,SSIM达到0.7363。
Abstract:Asuperresolution(SR)methodforremotesensingimagesbasedonsparsedictionaryandstructuralself-similaritywasproposed.Furthermore
comparedwithcorrespondencebetweenLRandHRimagepatchesfromaconventionalSRmethods
twodictionarypairs
i.e.primitivesparsedictionarypairandresidualsparsedictionarypair
arerainingdatabase.Theprimitivesparsedictionarypairislearnedtoreconstructinitialhigh-resolution(HR)remotesensingimagefromasinglelow-resolution(LR)input.However
theinitialHRremotesensingimagelosessomedetailscomparewiththecorrespondingoriginalHRimagecompletely.Therefore
residualsparsedictionarypairislearnedtoreconstructresidualinformation.Finally
self-similaritystructuralwidelyexistinremotesensingimagesandthisfeaturecan beusedtocorrectthereconstructedimagebynonlocalmeans(NLM)method.Experimentalresultsshowedthattheproposedalgorithmprovidesbettersubjectiveandobjectivequality
whencomparedtotheconventionalalgorithmsanditsPSNRis24.6905
SSIMis0.7363
遥感图像超分辨率字典学习稀疏表示
remotesensingimagessuper-resolutiondictionarylearningsparserepresentation
0
Views
2
下载量
8
CNKI被引量
Publicity Resources
Related Articles
Related Author
Related Institution