1.江南大学 理学院, 江苏 无锡 214122
2.江苏省轻工光电工程技术研究中心, 江苏 无锡 214122
3.光电对抗测试评估技术重点实验室, 河南 洛阳 471003
[ "冯佳濠(1998—),男,江苏无锡人,硕士研究生,2020年于盐城工学院获得学士学位,主要从事深度学习与自适应光学结合的研究。E-mail:6201205010@ stu.jiangnan.edu.cn" ]
[ "胡立发(1974—),男,湖北武汉人,博士,研究员,2003年于东北大学获得博士学位,主要从事液晶自适应光学的研究。E-mail: hulifa@jiangnan.edu.cn" ]
扫 描 看 全 文
冯佳濠, 胡启立, 姜律, 等. 基于Transformer结构的高精度湍流波前重构[J]. 液晶与显示, 2023,38(6):798-808.
FENG Jia-hao, HU Qi-li, JIANG Lü, et al. High-precision turbulence wavefront reconstruction based on Transformer structure[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(6):798-808.
冯佳濠, 胡启立, 姜律, 等. 基于Transformer结构的高精度湍流波前重构[J]. 液晶与显示, 2023,38(6):798-808. DOI: 10.37188/CJLCD.2023-0067.
FENG Jia-hao, HU Qi-li, JIANG Lü, et al. High-precision turbulence wavefront reconstruction based on Transformer structure[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(6):798-808. DOI: 10.37188/CJLCD.2023-0067.
动态变化的大气湍流和观测目标的亮度的降低严重影响了夏克-哈特曼波前传感器(SHWFS)探测波前的精度。针对这两种复杂的观测条件,本文提出了一种以Transformer结构为基础的神经网络模型,它具有很好的全局建模能力,可以高精度地从SHWFS光斑阵列图像中重建波前。通过在动态变化的典型大气湍流相干长度,r,0,下进行仿真模拟,所提出的网络模型的残余波前RMS误差值稳定在0.010~0.024 μm之间。与已有的方法相比,本文方法能够更准确地重构波前像差。此外,本文方法的重构精度受导星或观测目标的亮度变化影响很小。因此,本文方法的重构精度对两种观测条件变化均具有较强的稳定性,为大口径天文光学望远镜的高分辨率成像提供了一种有前景的方法。
The dynamically changing atmospheric turbulence and the reduced brightness of the observed target severely affect the accuracy of the Shack-Hartmann wavefront sensor (SHWFS) to detect wavefronts. Under these two complicated observational conditions, this paper proposes a neural network model based on Transformer structure,which has excellent global modelling capabilities and could reconstruct wavefronts from light spot array images from SHWFS with high accuracy. The residual wavefront RMS error of the presented network model can be stabilized between 0.010 μm and 0.024 μm by simulating for dynamically varying typical atmospheric turbulence coherence length ,r,0,. Comparing with reported methods, the wavefront aberrations can be reconstructed more accurately. In addition, the reconstruction accuracy of the method is robust to the magnitude variation of guide stars or detection targets. Therefore, the reconstruction accuracy of this method has strong stability to the changes of two observation conditions, and provides a promising way for high-resolution imaging for large-aperture astronomical optical telescopes.
自适应光学深度学习Shack-Hartmann波前传感器Transformer波前重构
adaptive opticsdeep learningshack-hartmann wavefront sensortransformerwavefront reconstruction
ANGEL J R P. Ground-based imaging of extrasolar planets using adaptive optics [J]. Nature, 1994, 368(6468): 203-207. doi: 10.1038/368203a0http://dx.doi.org/10.1038/368203a0
陈浩,宣丽,胡立发,等.望远镜的紧凑型闭环液晶自适应光学系统设计[J].液晶与显示,2010,25(3):379-385. doi: 10.3969/j.issn.1007-2780.2010.03.017http://dx.doi.org/10.3969/j.issn.1007-2780.2010.03.017
CHEN H, XUAN L, HU L F, et al. Design on compact type closed-loop liquid crystal adaptive optical system for telescope [J]. Chinese Journal of Liquid Crystals and Displays, 2010, 25(3): 379-385. (in Chinese). doi: 10.3969/j.issn.1007-2780.2010.03.017http://dx.doi.org/10.3969/j.issn.1007-2780.2010.03.017
LANE R G, TALLON M. Wave-front reconstruction using a Shack-Hartmann sensor [J]. Applied Optics, 1992, 31(32): 6902-6908. doi: 10.1364/ao.31.006902http://dx.doi.org/10.1364/ao.31.006902
MERKLE F. Adaptive optics for the ESO-VLT [C]//Proceedings of SPIE 1013, Optical Design Methods, Applications and Large Optics. Hamburg: SPIE, 1989: 224-232. doi: 10.1117/12.949383http://dx.doi.org/10.1117/12.949383
BAKER K L, MOALLEM M M. Iteratively weighted centroiding for Shack-Hartmann wave-front sensors [J]. Optics Express, 2007, 15(8): 5147-5159. doi: 10.1364/oe.15.005147http://dx.doi.org/10.1364/oe.15.005147
KONG Q F, WANG S, YANG P, et al. Aberration correction of Fresnel zone lenses telescope based on adaptive optics system [J]. Optical Engineering, 2018, 57(6): 063107. doi: 10.1117/1.oe.57.6.063107http://dx.doi.org/10.1117/1.oe.57.6.063107
GAO X L, JIANG Z L, HE X L, et al. Iterative imaging through strong dynamic turbulence media [J]. Optics and Lasers in Engineering, 2022, 149: 106779. doi: 10.1016/j.optlaseng.2021.106779http://dx.doi.org/10.1016/j.optlaseng.2021.106779
KEE K, WU C S, PAULSON D A, et al. Assisting target recognition through strong turbulence with the help of neural networks [J]. Applied Optics, 2020, 59(30): 9434-9442. doi: 10.1364/ao.405663http://dx.doi.org/10.1364/ao.405663
DUBOSE T B, GARDNER D F, WATNIK A T. Intensity-enhanced deep network wavefront reconstruction in Shack-Hartmann sensors [J]. Optics Letters, 2020, 45(7): 1699-1702. doi: 10.1364/ol.389895http://dx.doi.org/10.1364/ol.389895
SWANSON R, LAMB M, CORREIA C, et al. Wavefront reconstruction and prediction with convolutional neural networks [C]//Proceedings of SPIE 10703, Ⅵ. Austin: SPIE, 2018: 107031F. doi: 10.1117/12.2312590http://dx.doi.org/10.1117/12.2312590
HU L J, HU S W, GONG W, et al. Deep learning assisted Shack-Hartmann wavefront sensor for direct wavefront detection [J]. Optics Letters, 2020, 45(13): 3741-3744. doi: 10.1364/ol.395579http://dx.doi.org/10.1364/ol.395579
LI Z Q, LI X Y. Centroid computation for Shack-Hartmann wavefront sensor in extreme situations based on artificial neural networks [J]. Optics Express, 2018, 26(24): 31675-31692. doi: 10.1364/oe.26.031675http://dx.doi.org/10.1364/oe.26.031675
FRIED D L. Limiting resolution looking down through the atmosphere [J]. Journal of the Optical Society of America, 1966, 56(10): 1380-1384. doi: 10.1364/josa.56.001380http://dx.doi.org/10.1364/josa.56.001380
赵子云,顾虎,马文超,等.自适应光学系统误差分析与参数优化研究[J].液晶与显示,2021,36(5):663-672. doi: 10.37188/CJLCD.2020-0356http://dx.doi.org/10.37188/CJLCD.2020-0356
ZHAO Z Y, GU H, MA W C, et al. Error budget and parameters optimization of adaptive optics system [J]. Chinese Journal of Liquid Crystals and Displays, 2021, 36(5): 663-672. (in Chinese). doi: 10.37188/CJLCD.2020-0356http://dx.doi.org/10.37188/CJLCD.2020-0356
CHULANI H M, RODRÍGUEZ-RAMOS J M. Simulations and laboratory performance results of the weighted Fourier phase slope centroiding algorithm in a Shack‒Hartmann sensor [J]. Optical Engineering, 2018, 57(5): 053107. doi: 10.1117/1.oe.57.5.053107http://dx.doi.org/10.1117/1.oe.57.5.053107
FÉTICK R J L, FUSCO T, NEICHEL B, et al. Physics-based model of the adaptive-optics-corrected point spread function [J]. Astronomy & Astrophysics, 2019, 628: A99. doi: 10.1051/0004-6361/201935830http://dx.doi.org/10.1051/0004-6361/201935830
BUFTON J L. Comparison of vertical profile turbulence structure with stellar observations [J]. Applied Optics, 1973, 12(8): 1785-1793. doi: 10.1364/ao.12.001785http://dx.doi.org/10.1364/ao.12.001785
李大禹,朱召义,王少鑫,等.哈特曼波前探测器电子倍增增益的自适应控制方法[J].液晶与显示,2017,32(2):124-131. doi: 10.3788/yjyxs20173202.0124http://dx.doi.org/10.3788/yjyxs20173202.0124
LI D Y, ZHU Z Y, WANG S X, et al. Adaptive control of EMCCD gain in Hartmann wavefront sensor [J]. Chinese Journal of Liquid Crystals and Displays, 2017, 32(2): 124-131. (in Chinese). doi: 10.3788/yjyxs20173202.0124http://dx.doi.org/10.3788/yjyxs20173202.0124
DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale [C]. 9th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2021.
CORDONNIER J B, LOUKAS A, JAGGI M. On the relationship between self-attention and convolutional layers [C]//Proceedings of the 8th International Conference on Learning Representations. Addis Ababa: OpenReview.net, 2020.
LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows [C]. IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 9992-10002. doi: 10.1109/iccv48922.2021.00986http://dx.doi.org/10.1109/iccv48922.2021.00986
SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions [C]. IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1-9. doi: 10.1109/cvpr.2015.7298594http://dx.doi.org/10.1109/cvpr.2015.7298594
LI S D, CHEN X N, HE D, et al. Can vision transformers perform convolution? [J/OL]. arXiv, 2021: 2111.01353.
RENIEBLAS G P, NOGUÉS A T, GONZÁLEZ M D A M, et al. Structural similarity index family for image quality assessment in radiological images [J]. Journal of Medical Imaging, 2017, 4(3): 035501. doi: 10.1117/1.jmi.4.3.035501http://dx.doi.org/10.1117/1.jmi.4.3.035501
FRIED D L. Least-square fitting a wave-front distortion estimate to an array of phase-difference measurements [J]. Journal of the Optical Society of America, 1977, 67(3): 370-375. doi: 10.1364/josa.67.000370http://dx.doi.org/10.1364/josa.67.000370
CUBALCHINI R. Modal wave-front estimation from phase derivative measurements [J]. Journal of the Optical Society of America, 1979, 69(7): 972-977. doi: 10.1364/josa.69.000972http://dx.doi.org/10.1364/josa.69.000972
HU L F, XUAN L, LIU Y J, et al. Phase-only liquid-crystal spatial light modulator for wave-front correction with high precision [J]. Optics Express, 2004, 12(26): 6403-6409. doi: 10.1364/opex.12.006403http://dx.doi.org/10.1364/opex.12.006403
宣丽,李大禹,刘永刚.液晶自适应光学在天文学研究中的应用展望[J].液晶与显示,2015,30(1):1-9. doi: 10.3788/yjyxs20153001.0001bhttp://dx.doi.org/10.3788/yjyxs20153001.0001b
XUAN L, LI D Y, LIU Y G. Prospect of liquid crystal adaptive optics in astronomy application [J]. Chinese Journal of Liquid Crystals and Displays, 2015, 30(1): 1-9. (in Chinese). doi: 10.3788/yjyxs20153001.0001bhttp://dx.doi.org/10.3788/yjyxs20153001.0001b
THOMPSON L A. Adaptive optics in astronomy [J]. Physics Today, 1994, 47(12): 24-33. doi: 10.1063/1.881406http://dx.doi.org/10.1063/1.881406
0
浏览量
48
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构