Adaptive Super-Resolution for Remote Sensing Images Based on Sparse Representation With Global Joint Dictionary Model

被引:45
作者
Hou, Biao [1 ]
Zhou, Kang [1 ]
Jiao, Licheng [1 ]
机构
[1] Xidian Univ, Minist Educ China, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Shaanxi, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2018年 / 56卷 / 04期
基金
新加坡国家研究基金会; 中国国家自然科学基金;
关键词
Fast adaptive shrinkage-thresholding algorithm (FASTA); global joint dictionary model (GJDM); remote sensing images; sparse representation; super-resolution (SR); LINEAR INVERSE PROBLEMS; SUPER RESOLUTION; GRADIENT METHODS; K-SVD; ALGORITHM; INTERPOLATION; REGULARIZATION;
D O I
10.1109/TGRS.2017.2778191
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Sparse representation has been widely used in the field of remote sensing image super-resolution (SR) to restore a high-quality image from a low-resolution (LR) image, e.g., from the blurred and downsampled version of an LR image's high-resolution (HR) counterpart. It is well known that each image patch can be represented by a linear combination of the atoms of an overcomplete dictionary, and we can obtain an expression of sparse coefficients by l(1) norm regularization. Owing to the lack of an inner relationship between image patches and an image's global information, the traditional methods of jointly training two overcomplete dictionaries cannot obtain good SR results. Therefore, we propose an effective approach for remote sensing image SR based on sparse representation. More specifically, a novel global joint dictionary model (GJDM) is used to explore the prior knowledge of images, including local and global characteristics. First, we train two dictionaries for detail image patches and HR patches. Second, in order to enhance the inner relationship between image patches, we introduce a global self-compatibility model for global regularization. Finally, the sparse representation and the local and nonlocal constraints are integrated to improve the performance of the model, and the fast adaptive shrinkage-thresholding algorithm is employed to solve the convex optimization problem in the GJDM. Compared with other methods, the results of the proposed method show good SR performance in preserving details and texture information and significant improvement in a peak signal-to-noise ratio.
引用
收藏
页码:2312 / 2327
页数:16
相关论文
共 59 条
[1]   K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].
Aharon, Michal ;
Elad, Michael ;
Bruckstein, Alfred .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) :4311-4322
[2]   Image up-sampling using total-variation regularization with a new observation model [J].
Aly, HA ;
Dubois, E .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2005, 14 (10) :1647-1659
[3]  
[Anonymous], 1991, 209 U CAMBR COMP LAB
[4]  
[Anonymous], 2011, P 2011 INT WORKSHOP
[5]   2-POINT STEP SIZE GRADIENT METHODS [J].
BARZILAI, J ;
BORWEIN, JM .
IMA JOURNAL OF NUMERICAL ANALYSIS, 1988, 8 (01) :141-148
[6]   Fast Gradient-Based Algorithms for Constrained Total Variation Image Denoising and Deblurring Problems [J].
Beck, Amir ;
Teboulle, Marc .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (11) :2419-2434
[7]   A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems [J].
Beck, Amir ;
Teboulle, Marc .
SIAM JOURNAL ON IMAGING SCIENCES, 2009, 2 (01) :183-202
[8]  
Bill F., 2011, MARKOV ROM FIELDS
[9]  
Bjorck A, 1996, NUMERICAL METHODS LE
[10]   A non-local algorithm for image denoising [J].
Buades, A ;
Coll, B ;
Morel, JM .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, :60-65