Wavefront sensing using deep learning for Shack Hartmann and pyramidal sensors

David Escobar, Esteban Vera

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The use of Deep Learning in wavefront sensing has become a tremendous tool that provides an innovative approach to estimate the phase of an aberrated wavefront. Different methods have been developed in this field in order to find the best strategy according to the application. In this paper, a comparison between two wavefront sensing applications is carried out using various CNN Deep Learning architectures to obtain the closest representation of it in terms of Zernike Coefficients. A database of 110 000 40x40 images is created per application using the OOMAO Matlab toolbox where the sensor's images were generated using 200 Zernike Coefficients to produce a wavefront. The proposed network SH-P Net for the Shack Hartmann and Pyramid sensor fits with lower RMSE than the others evaluated in this document. The database generated with uniform distribution allows the neural network to learn better and faster. The computation time of the networks was about 1 s for 22 000 images and the root mean square wavefront error between the estimation and the input was about 0.00664 rad approximately.

Original languageEnglish
Title of host publication2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665408738
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021 - Virtual, Online, Chile
Duration: 6 Dec 20219 Dec 2021

Publication series

Name2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021

Conference

Conference2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021
Country/TerritoryChile
CityVirtual, Online
Period6/12/219/12/21

Keywords

  • Adaptive optics
  • Deep learning
  • Pyramid sensor
  • Shack-Hartmann sensor
  • Wavefront sensing
  • Zernike coefficients

Fingerprint

Dive into the research topics of 'Wavefront sensing using deep learning for Shack Hartmann and pyramidal sensors'. Together they form a unique fingerprint.

Cite this