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

Ghost imaging method based on convolutional neural network

A convolutional neural network and ghost imaging technology, applied in the field of ghost imaging, can solve the problems of sampling rate, calculation efficiency and imaging quality, etc., and achieve the effects of shortening data acquisition time, good anti-interference ability, and fast imaging speed

Inactive Publication Date: 2020-03-27
XI AN JIAOTONG UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the existing ghost imaging technology cannot take into account sampling rate, calculation efficiency and imaging quality, the present invention provides a ghost imaging method based on convolutional neural network, which has short data acquisition time, fast imaging, high image quality and strong anti-interference ability

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
  • Ghost imaging method based on convolutional neural network
  • Ghost imaging method based on convolutional neural network
  • Ghost imaging method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] The experimental target is a toy airplane model, the distance between the target and the light source is 27.5 cm, the distance between the target and the receiver is 45 cm, and the distance between the light source and the receiver is 17.5 cm. The power of the light source is 30μW / cm 2 , Continuously project random speckles with different sizes of 64*64 pixels, receive 300,000 echo signals, randomly select 200 samples for testing, and then randomly select 100 samples for testing. The network was trained at 20% sampling rate and tested at 5%, 10%, 15% and 20% sampling rate.

[0047] The experimental results are as figure 2 As shown, from left to right are the input and output comparison results at a sampling rate of 5%-20%, and the rightmost is the original image of the target taken with a CCD. It can be seen that regardless of the sampling rate, the quality of the output image has been greatly improved relative to the input image, and as the sampling rate increases, the ...

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 ghost imaging method based on a convolutional neural network, and the method comprises the following steps: 1, taking a to-be-recognized or imaged object image as a target for network training, taking an original object image with low resolution and each angle posture as a sample for network training, and carrying out the training through the convolutional neural network;2, detecting a target area by using a random radiation field, receiving an echo signal, and obtaining a low-resolution target image; and 3, inputting the low-resolution target image into the trainednetwork, and quickly outputting a high-resolution target image. According to the invention, the data acquisition time is short, the requirement on the quality of an input image is very low, the imaging speed is high, a high-quality target image can still be obtained under the condition that the effect of the input image is very poor, and the anti-interference capability is strong.

Description

Technical field [0001] The invention belongs to the field of ghost imaging, and specifically relates to a ghost imaging method based on a convolutional neural network. Background technique [0002] Ghost imaging, also known as quantum imaging or correlation imaging, is a new imaging technology developed on the basis of quantum entanglement. In 1995, it was first completed by Chinese scientists Shi Yanhua and Pittman of the University of Maryland. Compared with traditional imaging technology, ghost imaging has the characteristics of lensless imaging, strong anti-disturbance and non-localization. It has good capabilities in remote sensing imaging, low light detection, medical imaging, security inspection, and imaging through scattering media. Application prospects. The mechanism of ghost imaging is different from traditional imaging, which uses the high-order correlation of photons to perform imaging. In the imaging process, the target is continuously irradiated with the detecti...

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): G06T5/00G06T9/00G01V8/10
CPCG06T9/002G01V8/10G06T2207/20081G06T2207/20084G06T5/77
Inventor 贺雨晨王高陈辉朱士涛徐卓
Owner XI AN JIAOTONG 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