An end-to-end sea fog removal network using multiple scattering model.
An end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. Compared with the atmospheric single scattering model, the atmospheric multiple scattering model could more c...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2021-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0251337 |
id |
doaj-2277633914e344dfa2a0e50112e1dd75 |
---|---|
record_format |
Article |
spelling |
doaj-2277633914e344dfa2a0e50112e1dd752021-05-29T04:31:29ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01165e025133710.1371/journal.pone.0251337An end-to-end sea fog removal network using multiple scattering model.Shunmin AnXixia HuangZhangjing ZhengLinling WangAn end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. Compared with the atmospheric single scattering model, the atmospheric multiple scattering model could more comprehensively consider the effect of multiple scattering, which was important to the dense fog scenes, such as in ocean scene. Therefore, we used the atmospheric multiple scattering model to avoid image blurring. The model can directly generate the dehazing results, and unify the three parameters of the transmission map, the atmospheric light and the blur kernel into one formula. The latest smooth dilation and sub-pixel techniques were used in the network model. The latest techniques can avoid the gridding artifacts and the halo artifacts, the multi-scale sub-network was used to consider the features of multi-scale. In addition, multiple loss functions were used in end-to-end network. In the experimental results, the model was superior to the state-of-the-art models in terms of quantitatively and qualitatively.https://doi.org/10.1371/journal.pone.0251337 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shunmin An Xixia Huang Zhangjing Zheng Linling Wang |
spellingShingle |
Shunmin An Xixia Huang Zhangjing Zheng Linling Wang An end-to-end sea fog removal network using multiple scattering model. PLoS ONE |
author_facet |
Shunmin An Xixia Huang Zhangjing Zheng Linling Wang |
author_sort |
Shunmin An |
title |
An end-to-end sea fog removal network using multiple scattering model. |
title_short |
An end-to-end sea fog removal network using multiple scattering model. |
title_full |
An end-to-end sea fog removal network using multiple scattering model. |
title_fullStr |
An end-to-end sea fog removal network using multiple scattering model. |
title_full_unstemmed |
An end-to-end sea fog removal network using multiple scattering model. |
title_sort |
end-to-end sea fog removal network using multiple scattering model. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2021-01-01 |
description |
An end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. Compared with the atmospheric single scattering model, the atmospheric multiple scattering model could more comprehensively consider the effect of multiple scattering, which was important to the dense fog scenes, such as in ocean scene. Therefore, we used the atmospheric multiple scattering model to avoid image blurring. The model can directly generate the dehazing results, and unify the three parameters of the transmission map, the atmospheric light and the blur kernel into one formula. The latest smooth dilation and sub-pixel techniques were used in the network model. The latest techniques can avoid the gridding artifacts and the halo artifacts, the multi-scale sub-network was used to consider the features of multi-scale. In addition, multiple loss functions were used in end-to-end network. In the experimental results, the model was superior to the state-of-the-art models in terms of quantitatively and qualitatively. |
url |
https://doi.org/10.1371/journal.pone.0251337 |
work_keys_str_mv |
AT shunminan anendtoendseafogremovalnetworkusingmultiplescatteringmodel AT xixiahuang anendtoendseafogremovalnetworkusingmultiplescatteringmodel AT zhangjingzheng anendtoendseafogremovalnetworkusingmultiplescatteringmodel AT linlingwang anendtoendseafogremovalnetworkusingmultiplescatteringmodel AT shunminan endtoendseafogremovalnetworkusingmultiplescatteringmodel AT xixiahuang endtoendseafogremovalnetworkusingmultiplescatteringmodel AT zhangjingzheng endtoendseafogremovalnetworkusingmultiplescatteringmodel AT linlingwang endtoendseafogremovalnetworkusingmultiplescatteringmodel |
_version_ |
1721422649551224832 |