基于双路级联对抗机制的红外与可见光图像融合方法  

Infrared and Visible Image Fusion Method Based on Dual-path Cascade Adversarial Mechanism

作　　者：唐丽丽 刘刚 肖刚[2] TANG Lili;LIU Gang;XIAO Gang(College of Automation Engineering,Shanghai Electric Power University,Shanghai 200090,China;College of Aeronautics and Astronautics Aerospace,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]上海电力大学自动化工程学院,上海200090 [2]上海交通大学航空航天学院,上海200240

出　　处：《光子学报》2021年第9期313-323,共11页Acta Photonica Sinica

基　　金：国家自然科学基金(Nos.61673270,61203224);国家重点基础研究发展计划(No.2014CB744903);上海浦江人才计划(No.16PJD028)。

摘　　要：针对现有的基于生成对抗网络的图像融合方法存在忽略红外图像的热目标信息,可见光图像的部分细节信息丢失的情况,提出一种基于双路级联对抗机制的红外与可见光图像融合方法。首先,在生成器模型中采用双路级联的方式分别对红外与可见光图像进行特征提取,为提高融合质量在内容损失函数中引入结构相似度。然后,在判别器模型中采用双判别方式判别生成图像的真假。最后,在公开的数据集上进行实验并与8种经典先进的图像融合方法进行比较。实验结果表明:融合图像在保留红外图像的目标信息同时也保留了可见光图像更多的细节信息,在主观评价和客观评估上均获得较好的性能。The thermal target information of infrared image and some detail information of visible images are usually ignored in image fusion method based on generative adversarial network.To address the problem,an infrared and visible image fusion method based on dual-path cascade adversarial mechanism is proposed.In the stage of the generator model,a dual-path cascade is used to extract features of infrared and visible images,respectively.To improve the quality of fusion,structural similarity is introduced into the loss function.In the stage of the discriminator model,a dual discriminator is used to distinguish the generated image from the true natural visual images.The proposed method is experimented on the public data,and compared with eight state-of-the-art image fusion methods.The experimental results show that the fusion image not only retains more the target information of infrared images,but also retains more detail information of visible images,which is superior to state-of-the-art methods in subjective evaluation and objective assessment.

关 键 词：图像融合 生成对抗网络 双路级联 双判别器 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]