Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Phase aliasing error removing method and device based on end-to-end convolutional neural network

A technology of convolutional neural network and aliasing error, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of too large bandwidth of carrier wave added phase spectrum, achieve good universality and expand the measurement range Effect

Active Publication Date: 2020-02-04
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the defects of the prior art, the technical problem to be solved in the present invention is to provide a phase aliasing error removal method based on end-to-end convolutional neural network, which solves the problem of Fourier transform method or digital moiré shift. In the process of solving a single interferogram by the phase method, the phase spectrum aliasing problem caused by improper carrier addition or excessive phase spectrum bandwidth of the surface shape error can eliminate the phase spectrum aliasing error, realize the solution of the wide-spectrum phase interferogram, and expand the single Measuring range of phase interferogram method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Phase aliasing error removing method and device based on end-to-end convolutional neural network
  • Phase aliasing error removing method and device based on end-to-end convolutional neural network
  • Phase aliasing error removing method and device based on end-to-end convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 As shown, this end-to-end convolutional neural network-based phase aliasing error removal method includes the following steps:

[0030] (1) Aiming at the position randomness and scale randomness of aliasing error, design a multi-scale convolutional neural network;

[0031] (2) Use the computer to simulate the wide-spectrum phase interferogram, and based on the Fourier transform method or the digital Moire phase-shift method, the phase diagram containing the phase-spectrum aliasing error is obtained, which is consistent with the original wide-spectrum phase Figure 1 Same as the aliasing training set;

[0032] (3) Using aliasing training set to train multi-scale convolutional neural network;

[0033] (4) Use the trained multi-scale convolutional neural network to process the real phase image with phase spectrum aliasing error, and obtain high-precision phase dephasing results without phase spectrum aliasing error.

[0034] The multi-scale convolutiona...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a phase aliasing error removing method and device based on an end-to-end convolutional neural network. The method solves the problems that in the process of solving a single interferogram through a Fourier transform method or a digital Moire phase shift method, the phase spectrum aliasing caused by improper carrier addition or overlarge surface shape error phase spectrum bandwidth exists. The phase spectrum aliasing error can be eliminated, the solution of the wide spectrum phase interferogram is realized, and the measurement range of the single interferogram phase unscrambling method is expanded. The method comprises the following steps: (1) designing a multi-scale convolutional neural network; (2) simulating a wide-spectrum phase interferogram, solving a phase diagram containing a phase spectrum aliasing error based on a Fourier transform method or a digital Moire phase shift method, and taking the phase diagram containing the phase spectrum aliasing error andan original wide-spectrum phase diagram as an aliasing training set; (3) training a multi-scale convolutional neural network by using the aliasing training set; and (4) processing a real phase diagram containing the phase spectrum aliasing error by using the trained multi-scale convolutional neural network to obtain a high-precision phase solution result without the phase spectrum aliasing error.

Description

technical field [0001] The present invention relates to the technical field of optical measurement and image processing, in particular to a phase aliasing error removal method based on an end-to-end convolutional neural network and a phase aliasing error removal device based on an end-to-end convolutional neural network. Background technique [0002] High-precision optical components determine the imaging quality of the system in modern optical systems such as astronomical observation, target detection, lighting systems and projection displays. Among them, due to the polyhedral degree of freedom of the aspheric surface, one aspheric mirror can achieve the effect of a lens group composed of multiple spherical mirrors, which can greatly reduce the size and quality of the optical system and improve the imaging quality of the system. However, due to its highly free surface shape, high-precision aspheric surface shape detection often encounters certain difficulties. [0003] Int...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 胡摇郝群袁诗翥
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products