基于迭代深度网络的红外图像增强算法  

Infrared image enhancement algorithm based on iteration deep convolution network

作　　者：陈世红 陈荣军 CHEN Shi-hong;CHEN Rong-jun(Department of Information Engineering,Guangdong Eco-engineering Polytechnic,Guangzhou 510520,China;School of Computer Science,Guangdong Polytechnic Normal University,Guangzhou 510665,China)

机构地区：[1]广东生态工程职业学院信息工程系,广东广州510520 [2]广东技术师范大学计算机科学学院,广东广州510665

出　　处：《激光与红外》2021年第1期114-121,共8页Laser & Infrared

基　　金：广东省普通高校特色创新类项目(No.2018GKTSCX061,No.2020KTSCX271)资助。

摘　　要：由于现有基于深度网络的图像增强模型直接学习退化图像与清晰图像之间的映射函数,忽略了观测模型保真项的约束,导致恢复的图像存在虚假纹理和细节丢失。本文提出了一种用于红外图像增强的改进深度网络,该网络将深度学习网络嵌入到一个迭代的图像增强任务中,通过图像增强模块和反投影模块交错优化,实现数据一致性约束。本文提出的深度网络不仅可以利用深度特征学习先验,还可以利用观测模型的一致性先验。实验结果表明,本文提出的算法可以在图像去噪和去模糊任务上获得非常有竞争力的重建结果,在低对比度区域也能获得清晰的重建效果。Since the existing image enhancement model based on the deep network directly learns the mapping relationship between the degraded image and the clear image,and ignores the constraint of the fidelity term in the observation model,the reconstructed image has false texture and loss of details.This paper proposes an improved deep network for infrared image enhancement,which embeds the denoising network module into an iterative-based enhancement task,and achieves data consistency constraint by interleaving and optimizing the denoising auto-encoder module and the back projection module.Our proposed deep network can not only use the deep feature to describe the priori information,but also use the consistency priori of the observation model.The experimental results show that the proposed algorithm can achieve very competitive reconstruction results in image denoising and deblurring tasks,and can also achieve clear reconstruction results in low-contrast areas such as point object.

关 键 词：红外图像 图像增强 图像去噪 图像去模糊 深度学习 自编码 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]