基于NSST和稀疏表示的多源异类图像融合方法

王志社; 杨风暴; 彭智浩

红外技术, 2015, 37 (3): 210, 网络出版: 2015-04-14

基于NSST和稀疏表示的多源异类图像融合方法

Multi-source Heterogeneous Image Fusion Based on NSST and Sparse Presentation

论文大纲

王志社 ^1,2,*杨风暴 ¹彭智浩 ¹

作者单位

¹ 中北大学信息与通信工程学院，山西太原 030051

² 太原科技大学应用科学学院，山西太原 030024

图像融合多尺度学习字典稀疏表示方向信息熵 image fusion NSST NSST multi-scale study dictionary sparse presentation directional entropy

摘要

针对SAR、红外和可见光图像的灰度差异性大，融合图像感兴趣目标不突出的问题，提出一种基于NSST 和稀疏表示的多源异类图像融合方法。首先将训练图像进行NSST 变换，在低频系数上构建多尺度学习字典；对SAR、红外和可见光图像进行NSST 变换，利用滑动窗口分解低频系数为图像块序列，对图像块序列零均值化后再稀疏分解，采用稀疏系数绝对值取大的融合规则；高频子带系数采用局部方向信息熵显著性因子取大的融合规则；最后对融合系数进行NSST 逆变换得到最终的融合图像。

Abstract

This paper proposes a multi-source heterogeneous image fusion method based on NSST and sparse presentation to solve the problem that the interested targets are not prominent caused by great grey difference among SAR image, infrared image and visible image. Firstly, multi-scale study dictionary is built on the low frequency coefficients through carrying on NSST for the training image. SAR image, infrared image and visible image are transformed by NSST, and the low frequency coefficients are decomposed into image block sequence with sliding window method. Sparse decomposition is used for image block sequence after zero mean processing, and the fusion rule of the low frequency coefficients is that absolute value of sparse coefficient is larger. The fusion rule of high frequency subband coefficients is that significant factor of local orientation information entropy is larger. Finally final fusion image is obtained by NSST inverse transformation for fusion coefficients.

参考文献

[1] Byun Y. A ttexture-based fusiion scheme to inntegrate high-resoolution satellite SAR and optical imagees[J]. Remote Senssing Letters, 20144, 5(2): 103-111.

[2] M. N. Do, M. Vetterli. Thhe finite ridgelett transform for image representation[[J]. IEEE Transac tions Image Proceess, 2003, 12(1): 166-28.

[3] F. Nencini, A.. Garzelli, S. Baroonti, et al. Remotte sensing image fusion using the curveelet transform[J]. IInformation. Fusioon, 2007, 8(2): 1433-156.

[4] M. N. Do, M. Vetterli. The conntourlet transform:: an efficient direcctional multi-resolutioon image repressentation[J]. IEEEE Transactions Image Process, 2005,, 14(12): 2091-21006.

[5] Arthur L. Cuunha, Zhou Jian-PPing, Minh N. DDo. The nonsubsaampled contourlet traansform: theory,, design, and applications[J]. IEEE Transactions IImage Process, 20006, 15(10): 3089-33101.

[6] Chen Yong, XXiong Jie, Liu Huaa-lin, et al. Fusionn method of infrareed and visible images based on neighboorhood characteristtic and regionalizaation in NSCT domainn[J]. OPTIK, 2014, 124(17): 4980-49984.

[7] Adu Jian-hua, Gan Jian-hong, WWang Yan, et al. Image fusion bassed on nonsubsampledd contourlet transfform for infrared aand visible light immage[J]. Infrared Physiics & Technology, 2013, 61(12): 94-100.

[8] Yin Ming, Liu Wei, Zhao Xia, ett al. A novel imagee fusion algorithmm based on nonsubsammpled shearlet transforms[J]. OOptik, 2014, 1225(10): 2274-2282.

[9] Kong Wei-wei, ZZhang Long-jun, Yang Lei. Noveel fusion method for visible light and infrared images bbased on NSST-S F-PCNN[J]. Infraared Physics & Technoology, 2014, 65(7) : 103-112.

[10] Easley G, Labatee D, Lim W Q. Spparse directional iimage representatiions using the discrette shearlet transforrm[J]. Applied commputational harmoonicanalysis, 2008, 225(1): 25-46.

[11] 王珺, 彭进业 , 何何贵青, 等. 基于于非下采样 Contouurlet变换和稀疏表表示的红外与可见光光图像融合方法[J]. 兵工学报 , 20133, 34(7): 815-820.

Wang Jun, Peng Jin-ye, He Gui-qiing et al. Fusion mmethod for visible and infrared images based on non-ssubsampled contoourlet transform and sparse representaation [J]. Acta Armmamentarii, 2013, 34(7): 815-820.

[12] Aharon M, Eladd M, Bruckstein AA. K-SVD: an alggorithm for designning over complete dictionaries ffor sparse representation[J]. IEEEETransactions onSignal Processingg, 2006, 54(11): 43311-4322.

[13] 薛模根, 刘存超超, 徐国明 , 等. 基基于多尺度字典的的红外与微光图像像融合[J].红外技术术, 2013, 35(11): 6996-701.

Xue Mo-gen, Liuu Cun-chao, Xue GGuo-ming, et al. IInfrared and low liight level image fufusion based on multi-scale dicctionary[J]. Infraared Technology, 201 3, 35(11): 696-70 1.

[14] Yang B, Li S T.. Pixel-level imagge fusion with simmultaneous orthogoonal matching pursuitt [J]. Information FFusion, 2012, 13(11): 10-19.

[15] 王志社, 杨风暴, 陈磊等. 基于纹理分割和Top-hat 变换的合成孔径雷达与可见光图像增强融合[J]. 光学学报, 2014, 34(10): 1010002.

Wang Zhi-she, Yang Feng-bao, Chen Lei, et al. SAR and visible image enhanced fusion based on texture segmentation and top-hat transformation[J]. Acta Optica Sinica, 2014, 34(10): 1010002.

[16] 王宇庆, 王索建. 红外与可见光融合图像的质量评价[J].中国光学,2014, 7(3): 396-401.

Wang Yu-qing, Wang Suo-jian. Quality assessment method of IR and visible fusion image[J]. Chinese Optics, 2014, 7(3):396-401.

[17] Wang Zhou, A Bovik. A universal image quality index[J]. IEEE Signal Processing Letters, 2002, 9(3): 81-84.

[18] G Piella, H Heijmans. A new quality metric for image fusion[J]. Proceedings of the Tenth International Conference on Image Processing, Barcelona, Spain, 2003: 173-176.

[19] C S Xydeas, V Petrovic. Objective image fusion performance measure[J]. Electronic Letters, 2000, 36(4): 308-309.

王志社, 杨风暴, 彭智浩. 基于NSST和稀疏表示的多源异类图像融合方法[J]. 红外技术, 2015, 37(3): 210. WANG Zhi-she, YANG Feng-bao, PENG Zhi-hao. Multi-source Heterogeneous Image Fusion Based on NSST and Sparse Presentation[J]. Infrared Technology, 2015, 37(3): 210.

基于NSST和稀疏表示的多源异类图像融合方法

关于本站 Cookie 的使用提示

全站搜索

基于NSST和稀疏表示的多源异类图像融合方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索