An effective fusion based on compressive sensing

被引：0

作者：

Mou, Jiao ^{[1
,2
]}

Gao, Wei ^{[1
]}

Song, Zongxi ^{[1
]}

Xi, Jiangbo ^{[1
,2
]}

Wei, Laixing ^{[1
,2
]}

机构：

[1] Space Optics Laboratory, Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an

[2] University of Chinese Academy of Sciences, Beijing

来源：

Journal of Information and Computational Science | 2014年 / 11卷 / 11期

关键词：

Compressive sensing; Image fusion; Random observations; Sparse representation;

D O I：

10.12733/jics20104178

中图分类号：

学科分类号：

摘要：

Based on Compressive Sensing (CS) theory, an effective fusion method with the advantages of low sampling rate, simple structure and easy implementation is presented in this paper. We take single layer wavelet decomposition for two source images to obtain a low-frequency sub-band and three highfrequency sub-bands. The sparse matrix gotten by sparse representation of the high-frequency coefficients with the random matrix is only measured, then the low-frequency coefficients and the measurements of the high-frequency sparse matrix are fused with different schemes. After these process, high-frequency coefficients from the fused measurements is reconstructed via the Orthogonal Matching Pursuit (OMP) algorithm, and the fused image is obtained by inverse wavelet transform. Experimental results show, at the same sampling rates, the proposed method exhibits its superiority over the fusion method based on the Maximum of Absolute Values (MAV), self-adaptive weighted average fusion schemes based on entropy and standard deviation respectively, and under the lower sampling rate, it can also achieve better fusion performance. ©2014 Binary Information Press

引用

页码：3949 / 3958

页数：9

共 12 条

[1]

Zhao G., Bo Y., Liu D., Fusion for IR and visible images based on lifting wavelet transform, Computer Engineering and Design, 30, 7, pp. 1697-1699, (2009)

[2]

Huang X., Dai Q., Cao Y., Compressive sensing image fusion algorithm based on wavelet sparse basis, Application Research of Computers, 29, 9, pp. 3581-3853, (2012)

[3]

Ruan T., Na Y., Wang S., Remote sensing image fusion based on compressed sensing, 25, 4, pp. 43-45, (2012)

[4]

Donoho D.L., Compressed sensing, IEEE Transactions on Information Theory, 52, 4, pp. 1289-1306, (2006)

[5]

Candes E.J., Compressive sampling, Proceedings of the International Congress of Mathematicians, pp. 1433-1452, (2006)

[6]

Luo X., Zhang J., Yang J., Dai Q., Image fusion in compressed sensing, IEEE International Conference on Image Processing, pp. 2205-2208, (2009)

[7]

Divekar A., Ersoy O., Image fusion by compressive sensing, IEEE International Conference on Geoinformatics, pp. 1-6, (2009)

[8]

Zhou H., Feng Y., Wang D., Image fusion algorithm based on Bayesian compressive sensing, Application Research of Computers, 30, 2, pp. 613-615, (2013)

[9]

Zhang W., Zeng F., Zeng Q., Method of image fusion based on compressed sensing, Computer Engineering and Applications, 48, 12, pp. 194-197, (2012)

[10]

Shen J., Wu X., Liu Y., An approach of object recognition on remote sensing image based on fuzzy fusion, Computer Engineering and Application, 16, pp. 83-85, (2005)

← 1 2 →