Improved machine learning approach for wavefront sensing

doi:10.3390/s19163533

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 光电工程总体研究室（一室）

	Improved machine learning approach for wavefront sensing
	Guo, Hongyang 1,3,4; Xu, Yangjie 1,3,4; Li, Qing 1,2,3,4; Du, Shengping 1,4; He, Dong 1,4; Wang, Qiang 1,4; Huang, Yongmei 1,4
刊名	Sensors (Switzerland)
	2019-08-20
卷号	19 期号:16
关键词	adaptive optics machine learning convolutional neural network deconvolution
ISSN号	1424-8220
DOI	10.3390/s19163533
文献子类	期刊论文
英文摘要	In the adaptive optics (AO) system, to improve the e_ectiveness and accuracy of wavefront sensing-less technology, a phase-based sensing approach using machine learning is proposed. In contrast to the traditional gradient-based optimization methods, the model we designed is based on an improved convolutional neural network. Specifically, the deconvolution layer, which reconstructs unknown input by measuring output, is introduced to represent the phase maps of the point spread functions at the in focus and defocus planes. The improved convolutional neural network is utilized to establish the nonlinear mapping between the input point spread functions and the corresponding phase maps of the optical system. Once well trained, the model can directly output the aberration map of the optical system with good precision. Adequate simulations and experiments are introduced to demonstrate the accuracy and real-time performance of the proposed method. The simulations show that even when atmospheric conditions D/r0 = 20, the detection root-mean-square of wavefront error of the proposed method is 0.1307 λ, which has a better accuracy than existing neural networks. When D/r0 = 15 and 10, the root-mean-square error is respectively 0.0909 λ and 0.0718 λ. It has certain applicative value in the case of medium and weak turbulence. The root-mean-square error of experiment results with D/r0 = 20 is 0.1304 λ, proving the correctness of simulations. Moreover, this method only needs 12 ms to accomplish the calculation and it has broad prospects for real-time wavefront sensing. © 2019 by the authors. Licensee MDPI, Basel, Switzerland.
WOS关键词	PHASE-RETRIEVAL ALGORITHMS ; ADAPTIVE OPTICS ; SENSOR
WOS研究方向	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
语种	英语
出版者	MDPI AG, Postfach, Basel, CH-4005, Switzerland
WOS记录号	WOS:000484407200090
内容类型	期刊论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9802]
专题	光电技术研究所_光电工程总体研究室（一室）
作者单位	1.The Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu; 610209, China; 2.School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, No. 4 Section 2 North Jianshe Road, Chengdu; 610054, China 3.University of Chinese Academy of Sciences, Beijing; 100049, China; 4.Key Laboratory of Optical Engineering, Chinese Academy of Sciences, No.1 Guangdian Road, Chengdu; 610209, China;
推荐引用方式 GB/T 7714	Guo, Hongyang,Xu, Yangjie,Li, Qing,et al. Improved machine learning approach for wavefront sensing[J]. Sensors (Switzerland),2019,19(16).
APA	Guo, Hongyang.,Xu, Yangjie.,Li, Qing.,Du, Shengping.,He, Dong.,...&Huang, Yongmei.(2019).Improved machine learning approach for wavefront sensing.Sensors (Switzerland),19(16).
MLA	Guo, Hongyang,et al."Improved machine learning approach for wavefront sensing".Sensors (Switzerland) 19.16(2019).