[1]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].南京师范大学学报(自然科学版),2017,40(01):39.[doi:10.3969/j.issn.1001-4616.2017.01.007]
 Chen Weiye,Sun Quansen.Remote Sensing Image Super-resolution Reconstructionin Multi-scale Compressed Sensing Framework[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(01):39.[doi:10.3969/j.issn.1001-4616.2017.01.007]
点击复制

多尺度压缩感知框架下的遥感图像超分辨率重建()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第40卷
期数:
2017年01期
页码:
39
栏目:
·数学与计算机科学·
出版日期:
2017-03-31

文章信息/Info

Title:
Remote Sensing Image Super-resolution Reconstructionin Multi-scale Compressed Sensing Framework
文章编号:
1001-4616(2017)01-0039-09
作者:
陈伟业孙权森
南京理工大学计算机科学与工程学院,江苏 南京 210094
Author(s):
Chen WeiyeSun Quansen
School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
关键词:
遥感图像超分辨率重建多尺度压缩感知
Keywords:
remote sensing imagesuper-resolution reconstructionmulti-scalecompressed sensing
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-4616.2017.01.007
文献标志码:
A
摘要:
传统的基于压缩感知的超分辨率重建算法将图像看作单尺度,并没有考虑不同尺度的图像块可能包含不同的判别信息. 为了有效利用遥感图像的尺度特性,提出了一种多尺度压缩感知框架下的遥感图像超分辨率重建算法. 首先通过图像块聚类构建多尺度训练样本集,接着运用Fisher判别准则学习包含遥感图像类别信息的判别字典,然后根据压缩感知中测量矩阵的构造方式估计低分辨率图像的获取过程,最后结合判别字典依次重建多尺度模式下的各子区域图像. 实验结果证明了将多尺度压缩感知引入图像超分辨率重建的有效性,提出的算法在视觉效果和评价指标上均优于现有的几种算法.
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.

参考文献/References:

[1] DONOHO D L. Compressed sensing[J]. IEEE transactions on information theory,2006,52(4):1 289-1 306.
[2]TSAIG Y,DONOHO D L. Extensions of compressed sensing[J]. Signal processing,2006,86(3):549-571.
[3]CANDèS E J,WAKIN M B. An introduction to compressive sampling[J]. IEEE signal processing magazine,2008,25(2):21-30.
[4]FAN N. Super-resolution using regularized orthogonal matching pursuit based on compressed sensing theory in the wavelet domain[C]//IEEE international conference on computer graphics,imaging and visualization. Tianjin,China:IEEE,2009:349-354.
[5]YANG J,WRIGHT J,HUANG T S,et al. Image super-resolution via sparse representation[J]. IEEE transactions on image processing,2010,19(11):2 861-2 873.
[6]YANG S,SUN F,WANG M,et al. Novel super resolution restoration of remote sensing images based on compressive sensing and example patches-aided dictionary learning[C]//IEEE international workshop on multi-platform/multi-sensor remote sensing and mapping. Xiamen,China:IEEE,2011:1-6.
[7]KULKARNI N,NAGESH P,GOWDA R,et al. Understanding compressive sensing and sparse representation-based super-resolution[J]. IEEE transactions on circuits and systems for video technology,2012,22(5):778-789.
[8]PAN Z,YU J,HUANG H,et al. Super-resolution based on compressive sensing and structural self-similarity for remote sensing images[J]. IEEE transactions on geoscience and remote sensing,2013,51(9):4 864-4 876.
[9]DONG W,ZHANG L,SHI G,et al. Nonlocally centralized sparse representation for image restoration[J]. IEEE transactions on image processing,2013,22(4):1 620-1 630.
[10]TRINH D,LUONG M,DIBOS F,et al. Novel example-based method for super-resolution and denoising of medical images[J]. IEEE transactions on image processing,2014,23(4):1 882-1 895.
[11]REN K,XU F. Super-resolution images fusion via compressed sensing and low-rank matrix decomposition[J]. Infrared physics and technology,2015,68:61-68.
[12]DONG C,LOY C C,HE K,et al. Image super-resolution using deep convolutional networks[J]. IEEE transactions on pattern analysis and machine intelligence,2016,38(2):295-307.
[13]DAUBECHIES I,DEFRISE M,DE MOL C. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint[J]. Communications on pure and applied mathematics,2004,57(11):1 413-1 457.
[14]ZHANG X,BURGER M,BRESSON X,et al. Bregmanized nonlocal regularization for deconvolution and sparse reconstruction[J]. SIAM journal on imaging sciences,2010,3(3):253-276.
[15]ZHANG Z,RAO B D. Extension of SBL algorithms for the recovery of block sparse signals with intra-block correlation[J]. IEEE transactions on signal processing,2013,61(8):2 009-2 015.
[16]BRADY D J,HAGEN N. Multiscale lens design[J]. Optics express,2009,17(13):10 659-10 674.
[17]YANG M,ZHANG L,FENG X,et al. Fisher discrimination dictionary learning for sparse representation[C]//IEEE international conference on computer vision. Barcelona,Spain:IEEE,2011:543-550.
[18]GAN L. Block compressed sensing of natural images[C]//IEEE international conference on digital signal processing. Cardiff,UK:IEEE,2007:403-406.

备注/Memo

备注/Memo:
收稿日期:2016-08-20.
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(D040201).
通讯联系人:孙权森,教授,博士生导师,研究方向:模式识别、图像处理、遥感信息系统. E-mail:sunquansen@njust.edu.cn
更新日期/Last Update: 1900-01-01