基于深度学习的自适应光学波前传感技术研究综述  

Review of wavefront sensing technology in adaptive optics based on deep learning

作　　者：李自强 李新阳[1,2] 高泽宇 贾启旺 Li Ziqiang;Li Xinyang;Gao Zeyu;Jia Qiwang(Key Laboratory on Adaptive Optics,Chinese Academy of Sciences,Chengdu 610209,China;Institute of Optics and Electronics,Chinese Academy of Sciences,Chengdu 610209,China)

机构地区：[1]中国科学院自适应光学重点实验室,成都610209 [2]中国科学院光电技术研究所,成都610209

出　　处：《强激光与粒子束》2021年第8期1-13,共13页High Power Laser and Particle Beams

基　　金：国家自然科学基金项目(62005286)。

摘　　要：波前传感是自适应光学系统的重要组成部分,在地基大口径望远镜、激光大气传输、无线光通信、激光驱动核聚变等领域发挥了关键作用,同时也常应用于自由曲面的光学测量中。与此同时,深度学习作为一种较为通用的前沿技术,成功在计算机视觉、自然语言处理等众多领域取得了革命性进展。使用深度学习的方法改进自适应光学系统中的波前传感器,以期实现更精准的波前探测,以及适应更复杂的应用场景是自适应光学的发展趋势,也是深度学习应用领域的一个新课题。介绍了深度学习在自适应光学波前传感中的应用现状,主要分析了在相位反演波前传感器和哈特曼波前传感器中的研究特点,并在最后进行了总结和展望。Wavefront sensing is an important part of adaptive optics system,which plays a key role in the fields of ground-based telescopes,laser transmission in atmosphere,wireless optical communication,laser nuclear fusion,and freeform surface optical measurement etc.Meanwhile,as a general advanced technology,deep learning has made revolutionary progress in many fields such as computer vision,natural language processing and so on.Using deep learning method to improve the wavefront sensor in adaptive optics system to achieve more accurate wavefront detection and adapt to more complex application scenarios is the development trend of adaptive optics,and also a new topic in the field of deep learning.This paper,introduces the application status of deep learning in adaptive optics wavefront sensing in detail.It also analyzes the research characteristics of different types of wavefront sensors,such as phase retrieval wavefront sensor and Shack-Hartmann wavefront sensor,and makes a summary at the end.

关 键 词：自适应光学 深度学习 波前传感 相位反演 哈特曼波前传感器 

分 类 号：O43[机械工程—光学工程] TP18[理学—光学]