Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Two-step phase-free imaging method for electromagnetic inverse scattering problem based on neural network

A neural network, inverse scattering technology, applied in the field of two-step phase-free imaging, to achieve the effect of easy calculation

Active Publication Date: 2021-10-01
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the advantages and disadvantages of full-wave data inversion algorithm and phaseless inversion algorithm, and propose a two-step phaseless imaging method based on neural network to solve electromagnetic inverse scattering problem

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
  • Two-step phase-free imaging method for electromagnetic inverse scattering problem based on neural network
  • Two-step phase-free imaging method for electromagnetic inverse scattering problem based on neural network
  • Two-step phase-free imaging method for electromagnetic inverse scattering problem based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] This example uses experimental simulation data to validate the proposed imaging method. In the simulation, the Austrian scatterer is used as the unknown scatterer. The Austrian scatterer is a relatively complex scatterer structure, which includes two dielectric circles and a dielectric ring ( Figure 4a shown). Set the target area to be detected as a rectangular domain of interest of 2λ×2λ, and the background is air. The Austrian scatterer is placed inside it, and the radii of the two medium circles are both 0.2λ, and their centers are located at (-0.3λ, 0.6λ) and (0.3λ, 0.6λ) respectively. The inner diameter of the medium ring is 0.3λ, the outer diameter is 0.6λ, and its center is located at (0λ, 0.2λ). The inversion result of this example is as follows Figure 4b As shown in , it can be seen that the inversion result is quite good, indicating that the test of this example is very successful.

Embodiment 2

[0086]Although the results verified by simulation data are good, in order to consider the actual situation, it is necessary to verify the measured data. The so-called actual measurement data is the scattered field measured by the instrument, rather than obtained by computer simulation. The Institute Fresnel laboratory has spent a lot of energy and rigorous experimental environment to measure the measured data, and can directly use their data for verification. Such as Figure 5a As shown, the scatterer used in this laboratory is FoamDielExt, which consists of two dielectric circles, a small dielectric circle with a diameter of 8cm and a dielectric constant of 1.45, and a small dielectric circle with a diameter of 3.1cm and a dielectric constant of 3.0 Large medium circle. Data for FoamDielExt in the TM case was collected using 8 incident antennas, 241 receiving antennas and 9 frequencies (2-10 GHz) in a 20 cm x 20 cm domain of interest. All numerical experiments were carried...

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 two-step phase-free imaging method for solving the problem of electromagnetic inverse scattering based on a neural network. In the field of electromagnetic inverse scattering imaging, the full-wave data inversion algorithm needs to use the full-wave data, but the actual measurement of the full-wave data is quite difficult; the phaseless inversion algorithm only needs to use the phase-free total field data, and the phase-free total field data The actual measurement is much easier, but the non-phase inversion algorithm has a higher degree of nonlinearity, and the calculation is more difficult. The present invention is based on the advantages and disadvantages of the full-wave data inversion algorithm and the non-phase inversion algorithm. Combined with CNN, the phase-free data is first restored, and then combined with the full-wave data inversion algorithm to reconstruct the image.

Description

technical field [0001] The invention belongs to the technical field of electromagnetic inverse scattering imaging, in particular to a two-step phase-free imaging method for solving the problem of electromagnetic inverse scattering based on a neural network. Background technique [0002] Electromagnetic wave inverse scattering imaging is an important method for non-destructive and non-contact acquisition of electromagnetic or physical properties of objects. Electromagnetic detection methods have been widely used in positioning, microwave remote sensing, geophysical detection, non-destructive testing, biomedical imaging and other fields. In general, the problem of electromagnetic inverse scattering is to use the scattering of the incident wave by the measured object to invert or reconstruct the physical and geometric characteristics of the object, including its position and size, by measuring the scattered field outside the object or its far-field mode. , quantity, boundary a...

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 Patents(China)
IPC IPC(8): G01B7/00G01S13/89G01R29/08G06N3/04G06N3/08
CPCG01B7/00G01S13/89G01R29/08G06N3/08G06N3/045
Inventor 吴亮徐魁文马振超张璐
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com