Cargando…

Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning

Underwater ghost imaging based on deep learning can effectively reduce the influence of forward scattering and back scattering of water. With the help of data-driven methods, high-quality results can be reconstructed. However, the training of the underwater ghost imaging requires enormous paired und...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Xu, Yu, Zhongyang, Jiang, Pengfei, Xu, Lu, Hu, Jiemin, Wu, Long, Zou, Bo, Zhang, Yong, Zhang, Jianlong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9412451/
https://www.ncbi.nlm.nih.gov/pubmed/36015921
http://dx.doi.org/10.3390/s22166161
_version_ 1784775497508454400
author Yang, Xu
Yu, Zhongyang
Jiang, Pengfei
Xu, Lu
Hu, Jiemin
Wu, Long
Zou, Bo
Zhang, Yong
Zhang, Jianlong
author_facet Yang, Xu
Yu, Zhongyang
Jiang, Pengfei
Xu, Lu
Hu, Jiemin
Wu, Long
Zou, Bo
Zhang, Yong
Zhang, Jianlong
author_sort Yang, Xu
collection PubMed
description Underwater ghost imaging based on deep learning can effectively reduce the influence of forward scattering and back scattering of water. With the help of data-driven methods, high-quality results can be reconstructed. However, the training of the underwater ghost imaging requires enormous paired underwater datasets, which are difficult to obtain directly. Although the Cycle-GAN method solves the problem to some extent, the blurring degree of the fuzzy class of the paired underwater datasets generated by Cycle-GAN is relatively unitary. To solve this problem, a few-shot underwater image generative network method is proposed. Utilizing the proposed few-shot learning image generative method, the generated paired underwater datasets are better than those obtained by the Cycle-GAN method, especially under the condition of few real underwater datasets. In addition, to reconstruct high-quality results, an underwater deblurring ghost imaging method is proposed. The reconstruction method consists of two parts: reconstruction and deblurring. The experimental and simulation results show that the proposed reconstruction method has better performance in deblurring at a low sampling rate, compared with existing underwater ghost imaging methods based on deep learning. The proposed reconstruction method can effectively increase the clarity degree of the underwater reconstruction target at a low sampling rate and promotes the further applications of underwater ghost imaging.
format Online
Article
Text
id pubmed-9412451
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-94124512022-08-27 Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning Yang, Xu Yu, Zhongyang Jiang, Pengfei Xu, Lu Hu, Jiemin Wu, Long Zou, Bo Zhang, Yong Zhang, Jianlong Sensors (Basel) Article Underwater ghost imaging based on deep learning can effectively reduce the influence of forward scattering and back scattering of water. With the help of data-driven methods, high-quality results can be reconstructed. However, the training of the underwater ghost imaging requires enormous paired underwater datasets, which are difficult to obtain directly. Although the Cycle-GAN method solves the problem to some extent, the blurring degree of the fuzzy class of the paired underwater datasets generated by Cycle-GAN is relatively unitary. To solve this problem, a few-shot underwater image generative network method is proposed. Utilizing the proposed few-shot learning image generative method, the generated paired underwater datasets are better than those obtained by the Cycle-GAN method, especially under the condition of few real underwater datasets. In addition, to reconstruct high-quality results, an underwater deblurring ghost imaging method is proposed. The reconstruction method consists of two parts: reconstruction and deblurring. The experimental and simulation results show that the proposed reconstruction method has better performance in deblurring at a low sampling rate, compared with existing underwater ghost imaging methods based on deep learning. The proposed reconstruction method can effectively increase the clarity degree of the underwater reconstruction target at a low sampling rate and promotes the further applications of underwater ghost imaging. MDPI 2022-08-17 /pmc/articles/PMC9412451/ /pubmed/36015921 http://dx.doi.org/10.3390/s22166161 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yang, Xu
Yu, Zhongyang
Jiang, Pengfei
Xu, Lu
Hu, Jiemin
Wu, Long
Zou, Bo
Zhang, Yong
Zhang, Jianlong
Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title_full Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title_fullStr Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title_full_unstemmed Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title_short Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
title_sort deblurring ghost imaging reconstruction based on underwater dataset generated by few-shot learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9412451/
https://www.ncbi.nlm.nih.gov/pubmed/36015921
http://dx.doi.org/10.3390/s22166161
work_keys_str_mv AT yangxu deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT yuzhongyang deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT jiangpengfei deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT xulu deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT hujiemin deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT wulong deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT zoubo deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT zhangyong deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning
AT zhangjianlong deblurringghostimagingreconstructionbasedonunderwaterdatasetgeneratedbyfewshotlearning