Speckle spectrum information reconstruction method and device based on deep learning

A technology of spectral information and deep learning, applied in the field of speckle spectral information reconstruction method and device

Inactive Publication Date: 2021-09-07
LASER FUSION RES CENT CHINA ACAD OF ENG PHYSICS
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The essence of imaging is the transmission and recombination of information. The photons scattered by the object carry the information of the object. The form of the scattered photon on the detector is related to the target, but it is difficult to quickly solve this problem with traditional analytical methods. Association relationship, with the rise of neural networks, it is possible to quickly solve this association relationship

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
  • Speckle spectrum information reconstruction method and device based on deep learning
  • Speckle spectrum information reconstruction method and device based on deep learning
  • Speckle spectrum information reconstruction method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0029] The present invention is based on the fact that the speckle field contains object surface profile information, and any area of ​​the speckle field theoretically contains the same amount of information, and the object surface profile can be reconstructed from the speckle image by using the powerful ability of the neural network to mine correlations Based on the principle of information, a method for reconstructing speckle spectrum information based on deep learning is proposed. The method is as follows: figure 1 shown, which includes the following steps:

[0030] A method for reconstructing speckle spectrum information based on deep learning, comprising the following steps:

[0031] Step S1, establishing a training data set of object image and speckle image spectrum;

[0032] Step S2, learning the training data set based on the convolutional neural network to obtain a trained neural network model;

[0033] Step S3, acquiring the speckle image spectrum of the target to ...

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 deep learning-based speckle spectrum information reconstruction method and device. The method comprises the following steps: S1, establishing a training data set of an object image and a speckle image spectrum; S2, learning the training data set based on a convolutional neural network to obtain a trained neural network model; and S3, obtaining a speckle image frequency spectrum of a to-be-detected target and inputting the speckle image frequency spectrum into the neural network model to obtain a reconstructed object image of the to-be-detected target. The incidence relation between the detector information and the target is established based on the deep learning technology, the target image is reconstructed, and the purpose of lens-free speckle imaging is achieved.

Description

technical field [0001] The invention belongs to the technical field of image reconstruction, and in particular relates to a method and device for reconstructing speckle spectrum information based on deep learning. Background technique [0002] When the optical information channel is severely distorted, especially when there is a strong scattering medium (transmission such as biological tissue, strong haze, etc., reflection such as walls, etc.), it is called a non-line-of-sight condition, and the target information will appear as speckle when it reaches the sensor. form, cannot be directly imaged. How to perform imaging under non-line-of-sight conditions is a cutting-edge technical issue and a complex problem in imaging science. The essence of imaging is the transmission and recombination of information. The photons scattered by the object carry the information of the object. The form of the scattered photon on the detector is related to the target, but it is difficult to qu...

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
IPC IPC(8): G06T11/00G06T5/10G06N3/04G06N3/08
CPCG06T11/00G06T5/10G06N3/04G06N3/08G06T2207/20081G06T2207/20084G06T2207/10141G06T2207/20056
Inventor 王德恩廖予祯邓学伟胡东霞耿远超郑胜亨杨英郭雨源张鑫韩伟田野袁强袁晓东
Owner LASER FUSION RES CENT CHINA ACAD OF ENG PHYSICS
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap