[1]张 烨,刘晓佩.一种改进的压缩感知图像融合方法[J].西安科技大学学报,2018,(04):690-696.[doi:10.13800/j.cnki.xakjdxxb.2018.0425 ]
 ZHANG Ye,LIU Xiao-pei.An improved compressive sensing image fusion method[J].Journal of Xi'an University of Science and Technology,2018,(04):690-696.[doi:10.13800/j.cnki.xakjdxxb.2018.0425 ]
点击复制

一种改进的压缩感知图像融合方法(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2018年04期
页码:
690-696
栏目:
出版日期:
2018-07-15

文章信息/Info

Title:
An improved compressive sensing image fusion method
文章编号:
1672-9315(2018)04-0690-07
作者:
张 烨刘晓佩
西安科技大学 通信与信息工程学院,陕西 西安 710054
Author(s):
ZHANG YeLIU Xiao-pei
(College of Communication and Information Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)
关键词:
图像融合 非下采样contourlet变化 压缩感知 标准差 自适应
Keywords:
image fusion NSCT compressive sensing standard deviation adaptive
分类号:
TP 391.4
DOI:
10.13800/j.cnki.xakjdxxb.2018.0425
文献标志码:
A
摘要:
传统基于压缩感知的图像融合算法在通过压缩感知观测图像高频分量时会丢失分量的空间信息,仅能采用简单规则进行融合,导致融合图像纹理细节等信息效果较差。针对此,文中提出了一种结合图像高频特征的自适应融合规则。首先,对融合图像进行非下采样contourlet变换(NSCT),分解后得到的低频子带系数采用区域能量融合规则,较传统低频系数处理更好的保留源图像的背景信息; 然后,由于高频子带系数具有较高稀疏性,因此通过压缩感知进行压缩后根据标准差特征自适应选择融合规则; 最后,对重构系数进行非下采样contourlet逆变换。实验结果表明:与传统经典算法相比,新方法不仅精准提取到红外目标,同时充分保留可见光图像的细节信息,兼顾了待融合图像的背景信息和红外目标信息,有效提高了融合效果和主观感受。
Abstract:
The traditional image fusion algorithm based on compressive sensing(CS)can only adopt the simple fusion rule when the high frequency component spatial information is lost by CS observation,which leads to poor information such as detail of texture.In this paper,an adaptive fusion rule combining high frequency feature of image is proposed.First,making a NSCT decomposition to the infrared image and visible light image,and after that to fuse them using regional energy criterion for the low-frequency sub-bands to obtain a better fusion result than the traditional low frequency coefficients.Next,Since the high-frequency sub-band coefficients have high sparsity,they are compressed by CS and adopted adaptive fusion rule according to the standard deviation feature.Finally,inverse NSCT transform is carried out for the reconstructed coefficients.Compared with the traditional compressive sensing method,the new method not only accurately extract the infrared target,while retaining the full details of visible light images and containing the background information and infrared target information,which effectively improves the image fusion effect and subjective feelings.

参考文献/References:

[1] 李海超,李成龙,汤 进,等.热红外与可见光图像融合算法研究[J].计算机科学与探索,2016,10(3):407-412. LI Hai-chao,LI Cheng-long,TANG Jin,et al.Research on fusion algorithm for thermal and visible images[J].Journal of Frontiers of Computer Science and Technology,2016,10(3):407-412. [2] 钱小燕,韩 磊,王帮峰.红外与可见光图像快速融合算法[J].计算机辅助设计与图形学学报,2011,23(7):1211-1216. QIAN Xiao-yan,HAN Lei,WANG Bang-feng.A fast fusion algorithm of visible and infrared images[J].Journal of Computer Aided Designand Computer Graphics,2011,23(7):1211-1216. [3] 黄 慧,张宝辉,席 峰,等.基于目标增强的红外与可见光图像融合技术研究[J].红外技术,2017,39(7):908-913. HUANG Hui,ZHANG Bao-hui,XI Feng,et al.Image fusion technique based on target-enhancement[J].Infrared Technology,2017,39(7):908-913. [4] 徐雅薇,谢晓竹.多传感器图像融合方法及应用综述[J].四川兵工学报,2015,36(10):117-119. XU Ya-wei,XIE Xiao-zhu.Overview of approaches and applications of multi-sensor image fusion[J].Journal of Sichuan Ordnance,2015,36(10):117-119. [5] 王春华,马国超,马苗,等.基于目标提取的红外与可见光图像融合方法[J].计算机工程,2010,36(2):197-200. WANG Chun-hua,MA Guo-chao,MA Miao,et al.Fusion algorithm for infrared and visible light image based on objective extraction[J].Computer Engineering,2010,36(2):197-200. [6] Donoho D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306. [7] 马孟新,吴延海,张 昊,等.图像分块的贝叶斯压缩感知算法研究[J].西安科技大学学报,2014,34(5):625-630. MA Meng-xin,WU Yan-hai,ZHANG Hao,et al.Compressive sensing of block images based on Bayesian estimation[J].Journal of Xi'an University of Science and Technology,2014,34(5):625-630. [8] 柳翠寅,罗洪礼,李晓峰.基于压缩感知的红外与可见光图像融合[J].四川大学学报:工程科学版,2014,46(5):89-95. LIU Cui-yin,LUO Hong-li,LI Xiao-feng.A fusion algorithm for visible image and infrared image based on compressive sensing and nonsubsampled contourlet transform[J].Journal of Science University:Engineering Science Edition,2014,46(5):89-95. [9] 龚紫平.多观测及分块观测压缩感知的图像融合方法研究[D].广州:华南理工大学,2012. GONG Zi-ping.Research on compressed sensing based image fusion with multiple blocking measurement[D].Guangzhou:South China University of Technology,2012. [10]Luo X,Zhang J,Dai Q.A regional image fusion based on similarity characteristics[J].Signal Processing,2012,92(5):1268-1280. [11]DO M N.VETTE RLI M.The contourlet transform:an efficient directional multire solution Image representataion[J].IEEE Transactioons on Image Processing,2015,14(12):2091-2106. [12]焦李成,杨淑媛,刘 芳,等.压缩感知回顾与展望[J].电子学报,2011,39(7):1651-1658. JIAO Li-cheng,YANG Shu-yuan,LIU Fang,et al.Development and prospect of compressive sensing[J].Acta Electronica Sinica,2011,39(7):1651-1658. [13]邵文泽,韦志辉.压缩感知基本理论:回顾与展望[J].中国图象图形学报,2012,17(1):1-10. SHAO Wen-ze,WEI Zhi-hui.Advances and perspectives on compressed sensing theory[J].Journal of Image and Graphics,2012,17(1):1-10. [14]闫 迪.基于压缩感知理论的图像重构与图像融合算法研究[D].西安:西安科技大学,2013. YAN Di.Research on image recovery and fusion based on compressed sensing[D].Xi'an:Xi'an University of Science andTechnology,2013. [15]乔志洋,余娅荣.压缩感知理论在图像处理中的应用[J].云南大学学报,2017,39(S1):63-69. QIAO Zhi-yang,YU Ya-rong.Application of compressed sensing on image processing[J].Journal of Yunnan University,2017,39(S1):63-69. [16]林晨晖,聂建英.基于NSCT变换与压缩感知的红外/被动毫米波图像融合[J].福州大学学报:自然科学版,2017,45(6):789-791. LIN Chen-hui,NIE Jian-ying.Fusion algorithm for IR/PMMW image based on NSCT and compressive sensing[J].Journal of Fuzhou University:Natural Science Edition,2017,45(6):789-791. [17]胡玉成,王创新.基于区域方向的NSCT与PCNN图像融合算法[J].电子学报,2014,27(4):30-32. HU Yu-cheng,WANG Chuang-xin.An image fusion algorithm based on NSCT and PCNN[J].Electronic Scicene and Techeology,2014,27(4):30-32. [18]陈木生,蔡植善.基于NSCT的红外与可见光图像融合方法研究[J].激光与电子学进展,2015,52(6):114-119. CHEN Mu-sheng,CAI Zhi-shan.Study on fusion of visual and infrared images based on NSCT[J].Laser and Optoelectronics Progress,2015,52(6):114-119. [19]袁金楼,吴 谨,刘 劲.基于NSCT与DWT的压缩感知图像融合[J].红外技术,2015,37(11):957-961. YUAN Jin-lou,WU Jin,LIU Jin.Image Fusion based on compressed sensing of NSCT and DWT[J].Infrared Technology,2015,37(11):957-961. [20]Cunha A L,Zhou J P,Do M N.Nonsubsampled contourlet transform:theory design and applications[J].IEEE Transactioons on Image Processing,2006,15(10):3089-3101. [21]赵学军,刘 静.NSST域内基于压缩感知和PCNN的遥感图像融合[J].科学技术与工程,2016,16(14):260-261. ZHAO Xue-jun,LIU Jing.Remote sensing image fusion Based on compressed sensing and PCNN in nsst domain[J].Science Technology and Engineering,2016,16(14):260-261. [22]郭 明,符 拯,奚晓梁.基于局部能量的NSCT域红外与可见光图像融合算法[J].红外与激光工程,2012,41(8):2229-2235. GUO Ming,FU Zheng,XI Xiao-liang.Novel fusion algorithm for infrared and visible images based on local energy in NSCT domain[J].Infrared and Laser Engineering,2012,41(8):2229-2235. [23]Candes E J,Wakin M B.An introduction to compres-sive sampling[J].IEEE Signal Processing Magazine,2008,25(2):21-30. [24]亓兴兰,胡宗庆,刘 健.SPOT-5全色与多光谱遥感影像融合方法比较[J].北华大学学报:自然科学版,2011,12(2):214-218. QI Xing-lan,HU Zong-qing,LIU Jian.Fusion algorithms comparison of SPOT-5 PAN and multi-spectral remote sensing images[J].Journal of Beihua University:Natural Science Edition,2011,12:214-218. [25]赵飞翔,陶忠祥.基于 NSCT的红外与可见光图像融合[J].电光与控制,2013,20(9):29-33. ZHAO Fei-xiang,TAO Zhong-xiang.An algorithm for fusion of infrared and visible images based on NSCT[J].Electronics Optics and Control,2013,20(9):29-33.

相似文献/References:

[1]吴延海,张 烨,马孟新.基于NSCT变换和压缩感知的图像融合[J].西安科技大学学报,2015,(04):480.
 WU Yan-hai,ZHANG Ye,MA Meng-xin.Image fusion based on NSCT trasformation and compressive sensing[J].Journal of Xi'an University of Science and Technology,2015,(04):480.

备注/Memo

备注/Memo:
收稿日期:2017-04-10 责任编辑:高 佳
基金项目:陕西省自然科学基础研究计划(2016JQ6064,16JK1498)
通信作者:张 烨(1990-),女,陕西咸阳人,助理工程师,E-mail: zhangye815@qq.com
更新日期/Last Update: 2018-08-29