Cargando…
Single image mixed dehazing method based on numerical iterative model and DehazeNet
As one of the most common adverse weather phenomena, haze has caused detrimental effects on many computer vision systems. To eliminate the effect of haze, in the field of image processing, image dehazing has been studied intensively, and many advanced dehazing algorithms have been proposed. Physical...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8323906/ https://www.ncbi.nlm.nih.gov/pubmed/34329312 http://dx.doi.org/10.1371/journal.pone.0254664 |
_version_ | 1783731329540554752 |
---|---|
author | Jiao, Wenjiang Jia, Xingwu Liu, Yuetong Jiang, Qun Sun, Ziyi |
author_facet | Jiao, Wenjiang Jia, Xingwu Liu, Yuetong Jiang, Qun Sun, Ziyi |
author_sort | Jiao, Wenjiang |
collection | PubMed |
description | As one of the most common adverse weather phenomena, haze has caused detrimental effects on many computer vision systems. To eliminate the effect of haze, in the field of image processing, image dehazing has been studied intensively, and many advanced dehazing algorithms have been proposed. Physical model-based and deep learning-based methods are two competitive methods for single image dehazing, but it is still a challenging problem to achieve fidelity and effectively dehazing simultaneously in real hazy scenes. In this work, a mixed iterative model is proposed, which combines a physical model-based method with a learning-based method to restore high-quality clear images, and it has good performance in maintaining natural attributes and completely removing haze. Unlike previous studies, we first divide the image into different regions according to the density of haze to accurately calculate the atmospheric light for restoring haze-free images. Then, dark channel prior and DehazeNet are used to jointly estimate the transmission to promote the final clear haze-free image that is more similar to the real scene. Finally, a numerical iterative strategy is employed to further optimize the atmospheric light and transmission. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods on synthetic datasets and real-world datasets. Moreover, to indicate the universality of the proposed method, we further apply it to the remote sensing datasets, which can also produce visually satisfactory results. |
format | Online Article Text |
id | pubmed-8323906 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-83239062021-07-31 Single image mixed dehazing method based on numerical iterative model and DehazeNet Jiao, Wenjiang Jia, Xingwu Liu, Yuetong Jiang, Qun Sun, Ziyi PLoS One Research Article As one of the most common adverse weather phenomena, haze has caused detrimental effects on many computer vision systems. To eliminate the effect of haze, in the field of image processing, image dehazing has been studied intensively, and many advanced dehazing algorithms have been proposed. Physical model-based and deep learning-based methods are two competitive methods for single image dehazing, but it is still a challenging problem to achieve fidelity and effectively dehazing simultaneously in real hazy scenes. In this work, a mixed iterative model is proposed, which combines a physical model-based method with a learning-based method to restore high-quality clear images, and it has good performance in maintaining natural attributes and completely removing haze. Unlike previous studies, we first divide the image into different regions according to the density of haze to accurately calculate the atmospheric light for restoring haze-free images. Then, dark channel prior and DehazeNet are used to jointly estimate the transmission to promote the final clear haze-free image that is more similar to the real scene. Finally, a numerical iterative strategy is employed to further optimize the atmospheric light and transmission. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods on synthetic datasets and real-world datasets. Moreover, to indicate the universality of the proposed method, we further apply it to the remote sensing datasets, which can also produce visually satisfactory results. Public Library of Science 2021-07-30 /pmc/articles/PMC8323906/ /pubmed/34329312 http://dx.doi.org/10.1371/journal.pone.0254664 Text en © 2021 Jiao 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 Jiao, Wenjiang Jia, Xingwu Liu, Yuetong Jiang, Qun Sun, Ziyi Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title | Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title_full | Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title_fullStr | Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title_full_unstemmed | Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title_short | Single image mixed dehazing method based on numerical iterative model and DehazeNet |
title_sort | single image mixed dehazing method based on numerical iterative model and dehazenet |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8323906/ https://www.ncbi.nlm.nih.gov/pubmed/34329312 http://dx.doi.org/10.1371/journal.pone.0254664 |
work_keys_str_mv | AT jiaowenjiang singleimagemixeddehazingmethodbasedonnumericaliterativemodelanddehazenet AT jiaxingwu singleimagemixeddehazingmethodbasedonnumericaliterativemodelanddehazenet AT liuyuetong singleimagemixeddehazingmethodbasedonnumericaliterativemodelanddehazenet AT jiangqun singleimagemixeddehazingmethodbasedonnumericaliterativemodelanddehazenet AT sunziyi singleimagemixeddehazingmethodbasedonnumericaliterativemodelanddehazenet |