Cargando…

Unsupervised water scene dehazing network using multiple scattering model

In water scenes, where hazy images are subject to multiple scattering and where ideal data sets are difficult to collect, many dehazing methods are not as effective as they could be. Therefore, an unsupervised water scene dehazing network using atmospheric multiple scattering model is proposed. Unli...

Descripción completa

Detalles Bibliográficos
Autores principales: An, Shunmin, Huang, Xixia, Wang, Linling, Zheng, Zhangjing, Wang, Le
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8238221/
https://www.ncbi.nlm.nih.gov/pubmed/34181688
http://dx.doi.org/10.1371/journal.pone.0253214
_version_ 1783714857895329792
author An, Shunmin
Huang, Xixia
Wang, Linling
Zheng, Zhangjing
Wang, Le
author_facet An, Shunmin
Huang, Xixia
Wang, Linling
Zheng, Zhangjing
Wang, Le
author_sort An, Shunmin
collection PubMed
description In water scenes, where hazy images are subject to multiple scattering and where ideal data sets are difficult to collect, many dehazing methods are not as effective as they could be. Therefore, an unsupervised water scene dehazing network using atmospheric multiple scattering model is proposed. Unlike previous image dehazing methods, our method uses the unsupervised neural network and the atmospheric multiple scattering model and solves the problem of difficult acquisition of ideal datasets and the effect of multiple scattering on the image. In our method, in order to embed the atmospheric multiple scattering model into the unsupervised dehazing network, the unsupervised dehazing network uses four branches to estimate the scene radiation layer, transmission map layer, blur kernel layer and atmospheric light layer, the hazy image is then synthesized from the four output layers, minimizing the input hazy image and the output hazy image, where the output scene radiation layer is the final dehazing image. In addition, we constructed unsupervised loss functions which applicable to image dehazing by prior knowledge, i.e., color attenuation energy loss and dark channel loss. The method has a wide range of applications, with haze being thick and variable in marine, river and lake scenes, the method can be used to assist ship vision for target detection or forward road recognition in hazy conditions. Through extensive experiments on synthetic and real-world images, the proposed method is able to recover the details, structure and texture of the water image better than five advanced dehazing methods.
format Online
Article
Text
id pubmed-8238221
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-82382212021-07-09 Unsupervised water scene dehazing network using multiple scattering model An, Shunmin Huang, Xixia Wang, Linling Zheng, Zhangjing Wang, Le PLoS One Research Article In water scenes, where hazy images are subject to multiple scattering and where ideal data sets are difficult to collect, many dehazing methods are not as effective as they could be. Therefore, an unsupervised water scene dehazing network using atmospheric multiple scattering model is proposed. Unlike previous image dehazing methods, our method uses the unsupervised neural network and the atmospheric multiple scattering model and solves the problem of difficult acquisition of ideal datasets and the effect of multiple scattering on the image. In our method, in order to embed the atmospheric multiple scattering model into the unsupervised dehazing network, the unsupervised dehazing network uses four branches to estimate the scene radiation layer, transmission map layer, blur kernel layer and atmospheric light layer, the hazy image is then synthesized from the four output layers, minimizing the input hazy image and the output hazy image, where the output scene radiation layer is the final dehazing image. In addition, we constructed unsupervised loss functions which applicable to image dehazing by prior knowledge, i.e., color attenuation energy loss and dark channel loss. The method has a wide range of applications, with haze being thick and variable in marine, river and lake scenes, the method can be used to assist ship vision for target detection or forward road recognition in hazy conditions. Through extensive experiments on synthetic and real-world images, the proposed method is able to recover the details, structure and texture of the water image better than five advanced dehazing methods. Public Library of Science 2021-06-28 /pmc/articles/PMC8238221/ /pubmed/34181688 http://dx.doi.org/10.1371/journal.pone.0253214 Text en © 2021 An et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
An, Shunmin
Huang, Xixia
Wang, Linling
Zheng, Zhangjing
Wang, Le
Unsupervised water scene dehazing network using multiple scattering model
title Unsupervised water scene dehazing network using multiple scattering model
title_full Unsupervised water scene dehazing network using multiple scattering model
title_fullStr Unsupervised water scene dehazing network using multiple scattering model
title_full_unstemmed Unsupervised water scene dehazing network using multiple scattering model
title_short Unsupervised water scene dehazing network using multiple scattering model
title_sort unsupervised water scene dehazing network using multiple scattering model
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8238221/
https://www.ncbi.nlm.nih.gov/pubmed/34181688
http://dx.doi.org/10.1371/journal.pone.0253214
work_keys_str_mv AT anshunmin unsupervisedwaterscenedehazingnetworkusingmultiplescatteringmodel
AT huangxixia unsupervisedwaterscenedehazingnetworkusingmultiplescatteringmodel
AT wanglinling unsupervisedwaterscenedehazingnetworkusingmultiplescatteringmodel
AT zhengzhangjing unsupervisedwaterscenedehazingnetworkusingmultiplescatteringmodel
AT wangle unsupervisedwaterscenedehazingnetworkusingmultiplescatteringmodel