基于NSCT和最小化-局部平均梯度的图像融合  

Image Fusion Based on NSCT and Minimum-Local Mean Gradient

作　　者：杨孙运 奚峥皓[1] 王汉东 罗晓[1] 阚秀[1] YANG Sunyun;XI Zhenghao;WANG Handong;LUO Xiao;KAN Xiu(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《红外技术》2021年第1期13-20,共8页Infrared Technology

基　　金：国家自然科学基金项目(61803255)。

摘　　要：针对传统红外图像与可见光图像融合存在对比度低、细节丢失、目标模糊等问题,本文基于非下采样轮廓波变换(Non-subsampled Contourlet Transform,NSCT)的思想,通过改进权重函数和融合规则,建立新的融合算法实现红外图像和可见光图像的有效融合。首先,通过NSCT变换对红外和可见光图像进行多尺度分解得到对应的低频系数和高频系数。然后,采用改进的最小化规则和局部平均梯度规则分别对低频系数和高频系数进行融合处理,得到对应的最优融合系数,并将所得融合系数进行NSCT逆变换得到最终融合图像。最后,使用公共数据集与其他5种算法进行对比实验,并在7个具有实际意义的性能评价指标约束下,验证所设计算法的有效性和鲁棒性。To address the problems of low contrast,detail loss,and target blur in the fusion of traditional infrared and visible images,this study uses the idea of non-subsampled contourlet transform(NSCT)to improve the weight function and fusion rules and thus develops a new fusion algorithm to realize the effective fusion of infrared and visible images.First,NSCT is used to decompose infrared and visible images at multiple scales to obtain the corresponding low-and high-frequency coefficients.Then,the improved minimization and local mean gradient rules are used to fuse the low-and high-frequency coefficients,respectively,and thus to obtain the corresponding optimal fusion coefficient.The obtained fusion coefficient is then converted via an NSCT inverse transformation to obtain the final fused image.Finally,a public dataset is used to compare the proposed algorithm with the other five algorithms.The effectiveness and robustness of the proposed algorithm are verified under the constraints of seven performance evaluation indices having practical significance.

关 键 词：图像融合 非下采样轮廓波变换 最小化规则 局部平均梯度规则 红外 可见光 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]