基于对抗生成的轻量化红外图像增强网络  

Lightweight Infrared Image Enhancement Network Based on Adversarial Generation

作　　者：程江华[1] 潘乐昊 刘通[1] 程榜 李嘉元 伍智华 CHENG Jianghua;PAN Lehao;LIU Tong;CHENG Bang;LI Jiayuan;WU Zhihua(Department of Electronic Science,College of Electronic Science and Technology,National University of Defense Technology,Changsha,Hunan 410073,China)

机构地区：[1]国防科技大学电子科学学院电子科学系,湖南长沙410073

出　　处：《信号处理》2024年第3期484-491,共8页Journal of Signal Processing

基　　金：湖南省自然科学基金(2020JJ4670)。

摘　　要：目前,红外成像技术在医学、安保、环境监测、军事探测等方面获得了广泛应用。然而,由于低成本红外成像设备的固有缺陷及大气环境对热辐射传导的影响,导致其采集的图像亮度较暗、细节模糊、对比度低,影响后续图像语义分析及目标检测识别等任务。传统基于模型的红外图像增强方法常需利用图像先验信息,模型参数与场景相关,模型泛化能力不强;基于深度学习的红外图像增强算法有助于增强红外图像质量,但结构冗余,不利于边缘端部署。生成对抗网络(GAN)可以通过判别器和生成器两个网络的轮流对抗训练显著提升红外图像增强效果,但网络训练参数量大,边缘端部署占用资源多,运算复杂度高。本文设计了一种基于对抗生成的轻量化红外图像增强网络,通过在GAN模型的基础上增加多层次特征融合结构并设计多尺度损失函数,提升了特征提取效率并减少了网络层数,在提升图像质量的同时提高了增强效率,利于算法的边缘端部署。实验表明,本文方法在同等参数量下,通过添加多层次特征融合结构和多尺度损失函数,兼顾了图像的全局和局部特征,保证了细节信息不丢失,在提高网络性能的前提下未明显增加计算复杂度;在红外图像增强效果相当的情况下,模型参数量降低75.0%,边缘端设备推断时间降低32.07%。At present,infrared imaging technology has been widely used in medicine,security,environmental monitoring,military detection,and other aspects.However,due to the inherent defects of low-cost infrared imaging equipment and the influence of the atmospheric environment on thermal radiation conduction,the acquired images have dark brightness,blurred details,and low contrast,which affects subsequent image semantic analysis and target detection and recognition.Traditional model-based infrared image enhancement methods often require image prior information,model parameters are related to the scene,and the model generalization ability is weak.The infrared image enhancement algorithm based on deep learning enhances the infrared image quality,but the structure is redundant,which is not conducive to edge deployment.Generative adversarial networks(GAN)can significantly enhance infrared image quality via rotational adversarial training of the discriminator and generator.However,this method entails substantial network training parameters,consumes considerable resources in edge deployment,and possesses high computational complexity.In this study,a lightweight infrared image enhancement network based on adversarial generation is designed,which improves the feature extraction efficiency and reduces the number of network layers by adding a multi-level feature fusion structure and designing a multi-scale loss function based on the GAN model,which improves the image quality and enhancement efficiency,which is conducive to the edge deployment of the algorithm.Experiments show that the proposed method considers the global and local features of the image by adding a multi-level feature fusion structure and a multiscale loss function under the same number of parameters,ensuring that the detailed information is not lost and the computational complexity is not significantly increased under the premise of improving network performance.For similar infrared image enhancement effects,the number of model parameters is reduced by 75.0%,and the

关 键 词：红外图像增强 深度学习 轻量化网络 生成对抗 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]