Deep learning wavefront restoration method based on single-frame focal plane light intensity image

Abstract

The invention discloses a deep learning wavefront restoration method based on a single-frame focal plane light intensity image, and aims to solve the problem that multiple solutions exist when a single far-field light spot inverts a near-field wavefront due to the fact that two groups of wavefronts which mutually rotate by 180 degrees and have a complex conjugate relationship in an adaptive optical system have the same far-field light spot distribution. The wavefront restoration method based on walsh function phase modulation can ensure that far-field light spot distribution corresponds to a unique near-field wavefront, but the calculation speed is still limited by the number of iterations and the single-step iterative calculation time. The deep learning algorithm can self-extract the deepfeature information of the image, so that the mapping relation from the far-field light intensity image to the near-field wavefront can be learned on the basis of phase modulation of the walsh function, the calculation from the far-field image to the near-field wavefront end-to-end is realized, and the iterative calculation process of the traditional wavefront restoration method can be avoided. Based on this, the iterative calculation process of a traditional wavefront restoration method is avoided by using a deep learning algorithm, the calculation efficiency is improved, and rapid wavefrontrestoration of a single-frame focal plane light intensity image is realized.

Description

technical field [0001] The present invention relates to a wavefront restoration method, in particular to a deep learning wavefront restoration method based on a single-frame focal plane light intensity image. Background technique [0002] In the adaptive optics system, Zernike polynomials are often used to characterize the wavefront in the circular domain, and different sets of Zernike coefficients can be selected to generate different random wavefront aberrations. However, when the two sets of wavefronts have a complex conjugate relationship of 180° rotation to each other, they will produce the same far-field spot distribution. In this case, the traditional wavefront restoration algorithm is used to invert the near-field wavefront phase from a single far-field spot. , the resulting corresponding wavefront is not unique, which will lead to wrong solutions or even failure to converge in the restoration calculation. The wavefront restoration algorithm based on walsh function ...

AI Technical Summary

Problems solved by technology

[0003] However, the effectiveness of the walsh function phase plate to modulate the far field to the wavefront restoration results not only depends on whether the correct shape of the walsh function with non-180° rotation and flip symmetry is selected, but also on the relationship between different order walsh functions and the phase step depth of the photo. The selection will also affect the accuracy of wavefront restoration

Moreover, the improved algorithm still continues the iterative solution of the traditional phase inversion method. Although the number of iterations is relatively reduced, there is still a lack of speed.

Images