各向异性导向滤波的红外与可见光图像融合  

Infrared and visible image fusion with multi-scale anisotropic guided filtering

作　　者：刘明葳 王任华[1] 李静[1] 焦映臻 Liu Mingwei;Wang Renhua;Li Jing;Jiao Yingzhen(Department of Information and Cyber Security,People’s Public Security University of China,Beijing 100038,China;School of Mathematics Statistics,Central China Normal University,Wuhan 430079,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京100038 [2]华中师范大学数学与统计学院,武汉430079

出　　处：《中国图象图形学报》2021年第10期2421-2432,共12页Journal of Image and Graphics

基　　金：高分辨率对地观测重点专项项目(GFZX0404130307);国家重点研发计划项目(2018YFC0825806)。

摘　　要：目的针对红外与可见光图像融合时易产生边缘细节信息丢失、融合结果有光晕伪影等问题,同时为充分获取多源图像的重要特征,将各向异性导向滤波和相位一致性结合,提出一种红外与可见光图像融合算法。方法首先,采用各向异性导向滤波从源图像获得包含大尺度变化的基础图和包含小尺度细节的系列细节图;其次,利用相位一致性和高斯滤波计算显著图,进而通过对比像素显著性得到初始权重二值图,再利用各向异性导向滤波优化权重图,达到去除噪声和抑制光晕伪影;最后,通过图像重构得到融合结果。结果从主客观两个方面,将所提方法与卷积神经网络(convolutional neural network,CNN)、双树复小波变换(dual-tree complex wavelet transform,DTCWT)、导向滤波(guided filtering,GFF)和各向异性扩散(anisotropic diffusion,ADF)等4种经典红外与可见光融合方法在TNO公开数据集上进行实验对比。主观分析上,所提算法结果在边缘细节、背景保存和目标完整度等方面均优于其他4种方法;客观分析上,选取互信息(mutual information,MI)、边缘信息保持度(degree of edge information,QAB/F)、熵(entropy,EN)和基于梯度的特征互信息(gradient based feature mutual information,FMI_gradient)等4种图像质量评价指数进行综合评价。相较于其他4种方法,本文算法的各项指标均有一定幅度的提高,MI平均值较GFF提高了21.67%,QAB/F平均值较CNN提高了20.21%,EN平均值较CNN提高了5.69%,FMI_gradient平均值较GFF提高了3.14%。结论本文基于各向异性导向滤波融合算法可解决原始导向滤波存在的细节"光晕"问题,有效抑制融合结果中伪影的产生,同时具有尺度感知特性,能更好保留源图像的边缘细节信息和背景信息,提高了融合结果的准确性。Objective Infrared(IR)images are based on the thermal radiation of the scene,and they are not susceptible to illumination and weather conditions.IR images are insensitive to the change of the brightness of the scene,and they usually have poor image quality and lack detailed information of the scene.By contrast,visible(VIS)images are sensitive to the optical information of the scene and contain a large amount of texture details.However,in low light and nighttime conditions,VIS images cannot capture the target clearly.IR and VIS images can provide complementary and redundancy information of a scene in the fusion image.Thus,image fusion is an important technique for image processing and computer vision applications such as feature extraction and target recognition.Multi-scale decomposition(MSD)has the advantage of extracting features at different scales,which is one of the most widely used image fusion methods.Many traditional multiscale transform method signore the different image features of IR and VIS images.Therefore,traditional IR and VIS image fusion methods always lead to problems of missing the edge detail information and suppressing less halo.In this study,an IR and VIS image fusion algorithm based on anisotropic guide filter and phase congruency(PC)is proposed,which preserves edge details and suppresses artifacts effectively.Method The proposed scheme can not only preserve the details of source IR and VIS images,but also suppress the halo and artifacts effectively by combining the advantages of edge-preserving filter and PC.First,the input images are decomposed into a base layer and a series of detail layers.The base layer contains large scale variations in intensity,and the detail layers capture enough texture details by anisotropic guided filtering.Second,the saliency maps of the source images are calculated on the PC and Gaussian filter,and then,the binary weight maps are optimized by anisotropic guided filters of different scales,which can reduce noise and suppress halo.Finally,the fusion result is rec

关 键 词：图像融合 多尺度分解(MSD) 边缘保持滤波 各向异性导向滤波(AnisGF) 相位一致性(PC) 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]