湍流退化图像复原技术研究  

Review of Turbulence-Degraded Image Restoration Techniques

作　　者：吴晓庆 WU Xiao-qing(Key Laboratory of Atmospheric Optics,Anhui Institute of Optics and Fine Mechanics,HFIPS,Chinese Academy of Sciences,Hefei 230031,China;Nanhu laser Laboratory,National University of Defense Technology,Changsha 410073,China;Science Island Branch of Graduate School,University of Science and Technology of China,Hefei 230026,China)

机构地区：[1]中国科学院合肥物质科学研究院安徽光学精密机械研究所,中国科学院大气光学重点实验室,安徽合肥230031 [2]中国人民解放军国防科技大学南湖之光实验室,湖南长沙410073 [3]中国科学技术大学研究生院科学岛分校,安徽合肥230026

出　　处：《安徽师范大学学报（自然科学版）》2024年第4期301-305,339,共6页Journal of Anhui Normal University(Natural Science)

基　　金：中国科学院战略性先导科技专项(A类)(XDA17010104);国家自然科学基金项目(91752103)。

摘　　要：湍流退化图像复原技术旨在解决成像系统中因湍流效应引起的图像模糊和失真问题。本文介绍了湍流对图像影响的多种模型,包括Kolmogorov湍流模型、移动平均模型、Zernike多项式模型和平均结构函数模型。重点介绍了退化图像盲复原技术和深度学习的图像复原方法最新研究进展、课题组在该领域的研究进展和未来图像复原技术研究的方向。Turbulence-degraded image restoration techniques aim to address the problems of image blurring and distortion caused by turbulence effects in imaging systems.This paper introduces various models that describe the impact of turbulence on images,including the Kolmogorov turbulence model,the moving average model,the Zernike polynomial model,and the average structure function model.It highlights the latest research progress in blind image restoration techniques and deep learning-based image restoration methods.Additionally,it presents the research advancements made by our research group in this field and discusses future directions for image restoration technology research.

关 键 词：湍流退化模型 图像盲复原 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]