基于NSCT与改进PCNN的红外与可见光图像融合方法研究  

Research on Infrared and Visible Image Fusion Method Based on NSCT and Improved PCNN

作　　者：刘帅 王磊[1] 郝永平[2] 高扬 刘双杰[2] LIU Shuai;WANG Lei;HAO Yong-ping;GAO Yang;LIU Shuang-jie(School of Mechanical Engineering,Shenyang Ligong University,Shenyang,China;Weapon Science and Technology Research Center of Shenyang Ligong University,Shenyang,China)

机构地区：[1]沈阳理工大学机械工程学院,沈阳 [2]沈阳理工大学兵器科学与技术研究中心,沈阳

出　　处：《光电技术应用》2021年第4期60-65,共6页Electro-Optic Technology Application

基　　金：重点实验室开放基金(6142107190411)。

摘　　要：针对传统图像融合方法引起的清晰度低、轮廓模糊以及适应性差等问题,提出了一种改进的红外与可见光图像融合方法。采用非下采样轮廓波(NSCT)对红外与可见光图像进行分解,分别得到带通子带系数与低频子带系数。采用融合准则采用改进的空间频率(MSF-PCNN)获取高频融合系数,采用改进的脉冲耦合神经网络(PCNN),即NL-PCNN,获取低频融合系数。针对两种异源低频信息,利用改进的加权锐化滤波器和加权均值滤波器作频率梯度分离进行轮廓提取。实验结果表明了所提融合算法的有效性,在获取图像轮廓信息,增强融合图像清晰度方面均优于传统的图像融合算法,具有较高的自适应能力。An improved infrared and visible image fusion method is proposed to solve problems that comprise low definition,fuzzy contour and poor adaptability for traditional image fusion methods.By mean of NSCT scheme for decomposing infrared and visible images,the sub-band coefficients of bandpass and low-frequency are obtained,respectively.MSF-PCNN is used to obtain high-frequency fusion coefficient,and provide the performance improvement of PCNN,namely NL-PCNN,which is to gain low-frequency fusion coefficient.According to two different data sources of low-frequency domain,the improved filters,such as the sharp-weighted filter and mean-weighted filter,have the ability of separating the frequency gradient to extract the profile.Experimental results show that the proposed fusion algorithm is effective.It offers advantages over the traditional image fusion algorithm for obtaining image contour information and enhancing the fusion image clarity,which has high adaptive ability.

关 键 词：图像融合 NSCT变换 改进PCNN 带通子带 低频子带 轮廓提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]