Fusion of Panchromatic and Multispectral Images via Coupled Sparse Non-Negative Matrix Factorization

被引：39

作者：

Zhang, Kai ^{[1
]}

Wang, Min ^{[2
]}

Yang, Shuyuan ^{[1
]}

Xing, Yinghui ^{[1
]}

Qu, Rong ^{[1
]}

机构：

[1] Xidian Univ, Minist Educ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China

[2] Xidian Univ, Natl Key Lab Radar Signal Proc, Xian 710071, Peoples R China

来源：

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING | 2016年 / 9卷 / 12期

基金：

中国国家自然科学基金;

关键词：

Coupled sparse non-negative matrix factorization (CSNMF); L-1/2-norm regularization; sparse representation; LANDSAT TM; QUALITY;

D O I：

10.1109/JSTARS.2015.2475754

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we construct a new coupled sparse non-negative matrix factorization (CSNMF) model for the fusion of panchromatic (PAN) and multispectral (MS) images. Two CSNMFs are developed for a joint sparse representation of MS and PAN images. Moreover, a sequential iterative algorithm is proposed to simultaneously find the solution to CSNMF. Because learned dictionaries can reveal the latent structure of images in spatial and spectral domains, the fused high-resolution MS images can be calculated by multiplying the dictionary of PAN image and the sparse coefficients of MS images. Some experiments are taken on simulated and real QuickBird data, and the results show that CSNMF outperforms its counterparts in both visual quality and numerical guidelines.

引用

页码：5740 / 5747

页数：8

共 32 条

[11] Hoyer PO, 2002, NEURAL NETWORKS FOR SIGNAL PROCESSING XII, PROCEEDINGS, P557, DOI 10.1109/NNSP.2002.1030067
[12] A Practical Compressed Sensing-Based Pan-Sharpening Method
Jiang, Cheng
Zhang, Hongyan
Shen, Huanfeng
Zhang, Liangpei
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2012, 9 (04) : 629 - 633
[13] Pansharpening Quality Assessment Using the Modulation Transfer Functions of Instruments
Khan, Muhammad Murtaza
Alparone, Luciano
Chanussot, Jocelyn
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (11): : 3880 - 3891
[14] Laben C. A., 2000, U.S. Patent, Patent No. 6011875
[15] Learning the parts of objects by non-negative matrix factorization
Lee, DD
Seung, HS
[J]. NATURE, 1999, 401 (6755) : 788 - 791
[16] Lee DD, 2001, ADV NEUR IN, V13, P556
[17] A New Pan-Sharpening Method Using a Compressed Sensing Technique
Li, Shutao
Yang, Bin
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (02): : 738 - 746
[18] Fusion of Multispectral and Panchromatic Images Using a Restoration-Based Method
Li, Zhenhua
Leung, Henry
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2009, 47 (05): : 1480 - 1489
[19] Mascarenhas N. B., 1991, P INT GEOSCI REM SEN, P321
[20] Introduction of sensor spectral response into image fusion methods. application to wavelet-based methods
Otazu, X
González-Audícana, M
Fors, O
Núñez, J
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (10): : 2376 - 2385

← 1 2 3 4 →