面向红外与可见光图像融合的改进双鉴别器生成对抗网络算法  

An Improved Dual Discriminator Generative Adversarial Network Algorithm for Infrared and Visible Image Fusion

作　　者：廖光凤 关志伟[1,2] 陈强 LIAO Guangfeng;GUAN Zhiwei;CHEN Qiang(School of Automobile and Transportation,Tianjin University of Technology and Education,Tianjin 300222,China;School of Automobile and Rail Transportation,Tianjin Sino-German University of Applied Sciences,Tianjin 300350,China;National&Local Joint Engineering Research Center for Intelligent Vehicle Road Collaboration and Safety Technology,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学汽车与交通学院,天津300222 [2]天津中德应用技术大学汽车与轨道交通学院,天津300350 [3]智能车路协同与安全技术国家地方联合工程研究中心,天津300222

出　　处：《红外技术》2025年第3期367-375,共9页Infrared Technology

基　　金：2021年天津市科技领军(培育)企业重大创新项目(22YDPYGX00050);天津市多元投入基金重点项目(21JCZDJC00800);天津市应用基础研究项目(22JCZDJC00390);天津市教委科研计划项目(2021KJ018);天津市科技局技术创新引导专项基金(23YDTPJC00980)。

摘　　要：针对现有的红外与可见光图像融合算法对全局和多尺度特征提取不充分,对不同模态图像的关键信息提取不精准的问题,提出了基于双鉴别器生成对抗网络的红外与可见光图像融合算法。首先,生成器结合卷积和自注意力机制,捕获多尺度局部特征和全局特征;其次,将注意力机制与跳跃连接结合,充分利用多尺度特征并减少下采样过程中的信息丢失;最后,两个鉴别器引导生成器关注红外图像的前景显著目标和可见光图像的背景纹理信息,使融合图像保留更多关键信息。在公开数据集M~3FD和MSRS上的实验结果表明,与对比算法相比,6种评价指标结果显著提高,其中平均梯度(Average Gradient, AG)在两个数据集上相较于次优结果分别提高了27.83%和21.06%。本文算法的融合结果细节丰富,具有较好的视觉效果。An infrared and visible image fusion algorithm,based on a dual-discriminator generative adversarial network,is proposed to address issues,such as the insufficient extraction of global and multiscale features and the imprecise extraction of key information,in existing infrared and visible image fusion algorithms.First,a generator combines convolution and self-attention mechanisms to capture multiscale local and global features.Second,the attention mechanism is combined with skip connections to fully utilize multiscale features and reduce information loss during the downsampling process.Finally,two discriminators guide the generator to focus on the salient targets of the infrared images and background texture information of visible-light images,allowing the fused image to retain more critical information.Experimental results on the public multi-scenario multi-modality(M3FD)and multi-spectral road scenarios(MSRS)datasets show that compared with the baseline algorithms,the results of the six evaluation metrics improved significantly.Specifically,the average gradient(AG)increased by 27.83%and 21.06%on the two datasets,respectively,compared with the second-best results.The fusion results of the proposed algorithm are rich in detail and exhibit superior visual effects.

关 键 词：图像融合 生成对抗网络 双鉴别器 红外图像 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]