Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning
Deep learning has been proven to provide solutions for computational ghost imaging (CGI). However, in current CGI techniques, the quality of the reconstructed image is adversely affected by the position and intensity of the scattering medium. In this study, the feasibility of using a deep neural net...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Photonics Journal |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9200747/ |
id |
doaj-e030168ce76b48df9cf61ed179ed350c |
---|---|
record_format |
Article |
spelling |
doaj-e030168ce76b48df9cf61ed179ed350c2021-03-29T18:06:07ZengIEEEIEEE Photonics Journal1943-06552020-01-0112511510.1109/JPHOT.2020.30249689200747Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep LearningZiqi Gao0Xuemin Cheng1https://orcid.org/0000-0003-2150-776XKe Chen2Anqi Wang3Yao Hu4Shaohui Zhang5https://orcid.org/0000-0002-5078-6799Qun Hao6Shenzhen International Graduate School, Tsinghua University, Shenzhen, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen, ChinaSchool of Optics and Photonic, Beijing Institute of Technology, Beijing, ChinaSchool of Optics and Photonic, Beijing Institute of Technology, Beijing, ChinaSchool of Optics and Photonic, Beijing Institute of Technology, Beijing, ChinaDeep learning has been proven to provide solutions for computational ghost imaging (CGI). However, in current CGI techniques, the quality of the reconstructed image is adversely affected by the position and intensity of the scattering medium. In this study, the feasibility of using a deep neural network (DNN) by using the hybrid simulated data to facilitate CGI through a scattering medium is demonstrated, particularly when the scattering medium is in front of an object. Under a specific order of the measurement matrix, the CGI measurement equation is introduced along with a disturbance factor of the scattering effect to generate simulation data, thereby representing imaging situations with the scattering medium at different positions. The selection of disturbance parameters is determined by the correlation between the simulation signal and the experimental signal. Then an end-to-end DNN is trained using experimentally obtained light intensity signals, and it shows that the quality of the reconstruction results is improved when there is a scattering medium in the emission path. The reported technique effectively solves the problem of CGI reconstruction under different scattering paths with a common DNN, and may have broad applications in fast adaptive CGI for new and uncertain scenarios.https://ieeexplore.ieee.org/document/9200747/Computational ghost imagingscattering pathneural networkadaptive imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ziqi Gao Xuemin Cheng Ke Chen Anqi Wang Yao Hu Shaohui Zhang Qun Hao |
spellingShingle |
Ziqi Gao Xuemin Cheng Ke Chen Anqi Wang Yao Hu Shaohui Zhang Qun Hao Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning IEEE Photonics Journal Computational ghost imaging scattering path neural network adaptive imaging |
author_facet |
Ziqi Gao Xuemin Cheng Ke Chen Anqi Wang Yao Hu Shaohui Zhang Qun Hao |
author_sort |
Ziqi Gao |
title |
Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning |
title_short |
Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning |
title_full |
Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning |
title_fullStr |
Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning |
title_full_unstemmed |
Computational Ghost Imaging in Scattering Media Using Simulation-Based Deep Learning |
title_sort |
computational ghost imaging in scattering media using simulation-based deep learning |
publisher |
IEEE |
series |
IEEE Photonics Journal |
issn |
1943-0655 |
publishDate |
2020-01-01 |
description |
Deep learning has been proven to provide solutions for computational ghost imaging (CGI). However, in current CGI techniques, the quality of the reconstructed image is adversely affected by the position and intensity of the scattering medium. In this study, the feasibility of using a deep neural network (DNN) by using the hybrid simulated data to facilitate CGI through a scattering medium is demonstrated, particularly when the scattering medium is in front of an object. Under a specific order of the measurement matrix, the CGI measurement equation is introduced along with a disturbance factor of the scattering effect to generate simulation data, thereby representing imaging situations with the scattering medium at different positions. The selection of disturbance parameters is determined by the correlation between the simulation signal and the experimental signal. Then an end-to-end DNN is trained using experimentally obtained light intensity signals, and it shows that the quality of the reconstruction results is improved when there is a scattering medium in the emission path. The reported technique effectively solves the problem of CGI reconstruction under different scattering paths with a common DNN, and may have broad applications in fast adaptive CGI for new and uncertain scenarios. |
topic |
Computational ghost imaging scattering path neural network adaptive imaging |
url |
https://ieeexplore.ieee.org/document/9200747/ |
work_keys_str_mv |
AT ziqigao computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT xuemincheng computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT kechen computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT anqiwang computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT yaohu computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT shaohuizhang computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning AT qunhao computationalghostimaginginscatteringmediausingsimulationbaseddeeplearning |
_version_ |
1724196885576548352 |