南京师大学报（自然科学版）2017，Vol.40Issue(1)：39-47,9.DOI:10.3969/j.issn.1001-4616.2017.01.007
多尺度压缩感知框架下的遥感图像超分辨率重建
Remote Sensing Image Super-resolution Reconstruction in Multi-scale Compressed Sensing Framework
摘要
Abstract
The traditional compressed sensing based super-resolution reconstruction algorithm regards images as a single scale without considering that different scale image patches may have different discriminant information.To effectively utilize the scale characteristics of remote sensing images,a new remote sensing image super-resolution reconstruction algorithm in the multi-scale compressed sensing framework was proposed.First,image patches were clustered to construct multi-scale training sample sets.Next,the Fisher criterion was used to learn a discriminative dictionary containing the classification information of remote sensing images.Then,the acquisition process of the low-resolution image was estimated by the construction method of the measurement matrix in compressed sensing.Finally,the sub-region images in the multi-scale mode were reconstructed by using the discriminant dictionary.The experimental results demonstrate that it is effective to introduce multi-scale compressed sensing into image super-resolution reconstruction.The proposed algorithm outperforms other existing algorithms both in visual qualities and evaluation criteria.关键词
遥感图像/超分辨率重建/多尺度/压缩感知Key words
remote sensing image/super-resolution reconstruction/multi-scale/compressed sensing分类
信息技术与安全科学引用本文复制引用
陈伟业,孙权森..多尺度压缩感知框架下的遥感图像超分辨率重建[J].南京师大学报（自然科学版）,2017,40(1):39-47,9.基金项目
国家自然科学基金项目(61273251)、民用航天技术“十二五”预先研究项目(D00201). （61273251）
