Technique for Recovering Wavefront Phase Bad Points by Deep Learning

WU Jiali; LIANG Jingyuan; FEI Shaolong; ZHONG Xirui

doi:10.23919/cje.2022.00.008

Volume 32 Issue 2

Mar. 2023

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2023 > 32(2): 303-312

WU Jiali, LIANG Jingyuan, FEI Shaolong, et al., “Technique for Recovering Wavefront Phase Bad Points by Deep Learning,” Chinese Journal of Electronics, vol. 32, no. 2, pp. 303-312, 2023, doi: 10.23919/cje.2022.00.008

Citation:

WU Jiali, LIANG Jingyuan, FEI Shaolong, et al., “Technique for Recovering Wavefront Phase Bad Points by Deep Learning,” Chinese Journal of Electronics, vol. 32, no. 2, pp. 303-312, 2023, doi: 10.23919/cje.2022.00.008

Citation:

PDF( 4372 KB)

Technique for Recovering Wavefront Phase Bad Points by Deep Learning

doi: 10.23919/cje.2022.00.008

1.
Faculty of Automation & Information Engineering, Xi’an University of Technology, Xi’an 710048, China

Funds: This work was supported by the Key Industrial Innovation Chain Project of Shaanxi Province (2017ZDCXL-GY-06-01, 2020ZDLGY05-02), the Xi’an Science and Technology Planning Project (2020KJRC0083), and the Scientific Research Plan Projects of Shaanxi Education Department (18JK0341).

More Information

Author Bio:
Jiali WU is a Ph.D. candidate of Xi’an University of Technology. Her main research interests are wireless optical communication system and adaptive optics technology. (Email: wjl940315@163.com)

Jingyuan LIANG (corresponding author) received the M.S. degree from Xi’an University of Technology in 2015. She is an Assistant Engineer of the School of Automation and Information Engineering of Xi’an University of Technology. Her main research field is wireless optical communication technology. (Email: ljy@xaut.edu.cn)

Shaolong FEI is an M.S. candidate of Xi’an University of Technology. His major is communication and information systems. His main research field is wireless optical communication technology

Xirui ZHONG is a B.E. candidate of Xi’an University of Technology. His major is communication engineering. His main research field is wireless optical communication technology
Received Date: 2022-01-17
Accepted Date: 2022-05-27

Available Online: 2022-07-13

Publish Date: 2023-03-05

Abstract

Abstract

In adaptive optics systems, the bad spot detected by the wavefront detector affects the wavefront reconstruction accuracy. A convolutional neural network (CNN) model is established to estimate the missing information on bad points, reduce the reconstruction error of the distorted wavefront. By training 10,000 groups of spot array images and the corresponding 30th order Zernike coefficient samples, learns the relationship between the light intensity image and the Zernike coefficient, and predicts the Zernike mode coefficient based on the spot array image to restore the wavefront. Following the wavefront restoration of 1,000 groups of test set samples, the root mean square (RMS) error between the predicted value and the real value was maintained at approximately 0.2 μ m. Field wavefront correction experiments were carried out on three links of 600 m, 1.3 km, and 10 km. The wavefront peak-to-valley values corrected by the CNN decreased from 12.964 µ m, 13.958 µ m, and 31.310 µ m to 0.425 µ m, 3.061 µ m, and 11.156 µ m, respectively, and the RMS values decreased from 2.156 µ m, 9.158 µ m, and 12.949 µ m to approximately 0.166 µ m, 0.852 µ m, and 6.963 µ m, respectively. The results show that the CNN method predicts the missing wavefront information of the sub-aperture from the bad spot image, reduces the wavefront restoration error, and improves the wavefront correction performance.
- Adaptive optics,
- Wavefront reconstruction,
- Deep learning,
- Convolutional neural network

FullText(HTML)

References(33)

References

[1]	X. Z. Ke, S. J. Yang, J. L. Wu, et al., “Research progress on adaptive optics for wireless optical communication system at Xi’an University of Technology,” Intense Lasers and Particle Beams, vol.33, no.8, pp.30–52, 2021.
[2]	X. Z. Ke, J. L. Wu, and S. J. Yang, “Research progress and prospects of atmospheric turbulence for wireless optical communication,” Chinese Journal of Radio Science, vol.36, no.3, pp.323–339, 2021. (in Chinese)
[3]	Na Ji, “Adaptive optical fluorescence microscopy,” Nature Methods, vol.14, pp.374–380, 2017. doi: 10.1038/nmeth.4218
[4]	M. J. Booth, “Adaptive optical microscopy: The ongoing quest for a perfect image,” Light: Science & Applications, vol.3, no.4, pp.1–7, 2014.
[5]	S. Hippler, M. Feldt, T. Bertram, et al., “Single conjugate adaptive optics for the ELT instrument METIS,” Experimental Astronomy, vol.47, pp.65–105, 2019. doi: 10.1007/s10686-018-9609-y
[6]	S. Thater, D. Krajnovic, M. Cappellari, et al., “Six new supermassive black hole mass determinations from adaptive-optics assisted SINFONI observations,” Astronomy & Astrophysics, vol.625, pp.1–30, 2019.
[7]	G. C-F. Chen, C. D. Fassnacht, S. H. Suyu, C. E. Rusu, et al., “A SHARP view of H0LiCOW: H₀ from three time-delay gravitational lens systems with adaptive optics imaging,” Monthly Notices of the Royal Astronomical Society, vol.490, no.2, pp.1743–1773, 2019. doi: 10.1093/mnras/stz2547
[8]	J. Mompean, J. L. Aragon, P. M. Prieto, et al., “GPU-based processing of Hartmann-Shack images for accurate and high-speed ocular wavefront sensing,” Future Generation Computer Systems, vol.91, pp.177–190, 2019. doi: 10.1016/j.future.2018.09.010
[9]	D. L. Fried, “Least-square fitting a wave-front distortion estimate to an array of phase-difference measurements,” Journal of the Optical Society of America, vol.67, no.3, pp.370–375, 1977. doi: 10.1364/JOSA.67.000370
[10]	R. Cubalchini, “Modal wave-front estimation from phase derivative measurements,” Journal of the Optical Society of America, vol.69, no.7, pp.972–977, 1979. doi: 10.1364/JOSA.69.000972
[11]	L. J. Hu, S. W. Hu, W. Gong, et al., “Learning-based Shack-Hartmann wavefront sensor for high-order aberration detection,” Optics Express, vol.27, no.23, pp.33504–33517, 2019. doi: 10.1364/OE.27.033504
[12]	Y. L. Cun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol.521, no.7553, pp.436–444, 2015. doi: 10.1038/nature14539
[13]	Z. X. Xu, P. Yang, K. Hu, et al., “Deep learning control model for adaptive optics systems,” Applied Optics, vol.58, no.8, pp.1998–2009, 2019. doi: 10.1364/AO.58.001998
[14]	H. Guo, N. Korablinova, Q. Ren, et al., “Wavefront reconstruction with artificial neural networks,” Optics Express, vol.14, no.14, pp.6456–6462, 2006. doi: 10.1364/OE.14.006456
[15]	J. Osborn, D. Guzman, F. J. deCosJuez, et al., “Open-loop tomography with artificial neural networks on CANARY: On-sky results,” Monthly Notices of the Royal Astronomical Society, vol.441, no.3, pp.2508–2514, 2014. doi: 10.1093/mnras/stu758
[16]	Robin Swanson, Masen Lamb, Carlos Correia, et al., “Wavefront reconstruction and prediction with convolutional neural networks,” Adaptive Optics Systems VI, vol.10703, article no.107031F, 2018. doi: 10.1117/12.2312590
[17]	C. W. Li, B. M. Li, and S. J. Zhang, “Phase retrieval using a modified Shack-Hartmann wavefront sensor with defocus,” Applied Optics, vol.53, no.4, pp.618–624, 2014. doi: 10.1364/AO.53.000618
[18]	A. Krizhevsky, I. Sutskever, and G. E. Hinto, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol.60, no.6, pp.84–90, 2017. doi: 10.1145/3065386
[19]	H. M. Ma, H. Q. Liu, Y. Qiao, et al., “Numerical study of adaptive optics compensation based on convolutional neural networks,” Optics Communications, vol.433, pp.283–289, 2019. doi: 10.1016/j.optcom.2018.10.036
[20]	S. Christian, V. Vincent, L. Sergey, et al., “Rethinking the inception architecture for computer vision,” in Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp.2818–2826, 2016.
[21]	S. W. Paine and J. R. Fienup, “Machine learning for improved image-based wavefront sensing,” Optics Letters, vol.43, no.6, pp.1235–1238, 2018. doi: 10.1364/OL.43.001235
[22]	Y. Nishizaki, M. Valdivia, R. Horisaki, et al., “Deep learning wavefront sensing,” Optics Express, vol.27, no.1, pp.240–251, 2019. doi: 10.1364/OE.27.000240
[23]	Y. Wu, Y. M. Guo, H. Bao, et al., “Sub-millisecond phase retrieval for phase-diversity wavefront sensor,” Sensors, vol.20, no.17, pp.4877–4890, 2020. doi: 10.3390/s20174877
[24]	S. W. Hu, L. J. Hu, W. Gong, et al., “Deep learning based wavefront sensor for complex wavefront detection in adaptive optical microscopes,” Frontiers of Information Technology and Electronic Engineering, vol.22, no.10, pp.1277–1288, 2021. doi: 10.1631/FITEE.2000422
[25]	Robert J. Noll, “Zernicke polynomials and atmospheric turbulence,” Journal of the Optical Society of America, vol.66, no.3, pp.207–211, 1976. doi: 10.1364/JOSA.66.000207
[26]	A. L. Xia and C. W. Ma, “An improved centroid detection method based on higher moment for Shack-Hartmann wave front sensor,” in Proc. SPIE 7850, Optoelectronic Imaging and Multimedia Technology, SPIE, article no.78501Q, 2010.
[27]	K. Q. Wang, M. M. Zhang, J. Tang, et al., “Deep learning wavefront sensing and aberration correction in atmospheric turbulence,” PhotoniX, vol.2, article no.8, 2021. doi: 10.1186/s43074-020-00023-9
[28]	I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Posts & Telecom Press, Beijing, pp.100–128, 2017.
[29]	H. Guo, Y. Xu, Q. Li, et al., “Improved machine learning approach for wavefront sensing,” Sensors, vol.19, no.16, article no.3533, 2019. doi: 10.3390/s19163533
[30]	R. Horisaki, R. Takagi, and J. Tanida, “Deep-learning-generated holography,” Applied Optics, vol.57, no.14, pp.3859–3863, 2018. doi: 10.1364/AO.57.003859
[31]	P. Boer, D. P. Kroese, S. Mannor, et al., “A tutorial on the cross-entropy method,” Annals of Operations Research, vol.134, no.1, pp.19–67, 2005. doi: 10.1007/s10479-005-5724-z
[32]	D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back propagating errors,” Nature, vol.323, no.6088, pp.533–536, 1986. doi: 10.1038/323533a0
[33]	D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” The 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA, arXiv:1412.6980, 2015.