Improved Machine Learning Approach for Wavefront Sensing

In the adaptive optics (AO) system, to improve the effectiveness 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.

[1]  James R Fienup,et al.  Machine learning for improved image-based wavefront sensing. , 2018, Optics letters.

[2]  B. Vohnsen,et al.  A direct comparison between a MEMS deformable mirror and a liquid crystal spatial light modulator in signal-based wavefront sensing , 2013 .

[3]  D R Williams,et al.  Supernormal vision and high-resolution retinal imaging through adaptive optics. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[4]  Jun Tanida,et al.  Deep learning wavefront sensing. , 2019, Optics express.

[5]  J R Fienup,et al.  Phase-retrieval algorithms for a complicated optical system. , 1993, Applied optics.

[6]  Anne Margarette S Maallo,et al.  Fast-convergent algorithm for speckle-based phase retrieval and a design for dynamic wavefront sensing. , 2009, Applied optics.

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Wilson,et al.  New modal wave-front sensor: a theoretical analysis , 2000, Journal of the Optical Society of America. A, Optics, image science, and vision.

[9]  Chao Liu,et al.  Performance evaluation of adaptive optics for atmospheric coherent laser communications. , 2014, Optics express.

[10]  F. Roddier,et al.  Wave-front reconstruction from defocused images and the testing of ground-based optical telescopes , 1993 .

[11]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[12]  Xin Qi,et al.  Feature-based phase retrieval wavefront sensing approach using machine learning. , 2018, Optics express.

[13]  Alexander J. Smola,et al.  Efficient mini-batch training for stochastic optimization , 2014, KDD.

[14]  Jeffrey W. Yu,et al.  Hubble Space Telescope prescription retrieval. , 1993, Applied optics.

[15]  Martin T. Hagan,et al.  Neural network design , 1995 .

[16]  A. Greenaway,et al.  Model-based Aberration Correction in a Closed-loop Wavefront-sensor-less Adaptive Optics System References and Links , 2022 .

[17]  J. H. Seldin,et al.  Hubble Space Telescope characterized by using phase-retrieval algorithms. , 1993, Applied optics.

[18]  Jaume Pujol,et al.  Comparison of the retinal image quality with a Hartmann-Shack wavefront sensor and a double-pass instrument. , 2006, Investigative ophthalmology & visual science.

[19]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[20]  Joris De Schutter,et al.  An Accurate and Efficient Gaussian Fit Centroiding Algorithm for Star Trackers , 2013 .

[21]  J. Hardy,et al.  Adaptive Optics for Astronomical Telescopes , 1998 .

[22]  J. Angel,et al.  Adaptive optics for array telescopes using neural-network techniques , 1990, Nature.

[23]  F Roddier,et al.  Curvature sensing and compensation: a new concept in adaptive optics. , 1988, Applied optics.

[24]  James R Fienup,et al.  Phase retrieval algorithms: a personal tour [Invited]. , 2013, Applied optics.

[25]  Joseph J. Green,et al.  Testbed for extended-scene Shack-Hartmann and phase retrieval wavefront sensing , 2005, SPIE Optics + Photonics.

[26]  David J. Lee,et al.  Comparison of Shack-Hartmann wavefront sensing and phase-diverse phase retrieval , 1997, Optics & Photonics.