Cargando…

New deep learning method for efficient extraction of small water from remote sensing images

Extracting water bodies from remote sensing images is important in many fields, such as in water resources information acquisition and analysis. Conventional methods of water body extraction enhance the differences between water bodies and other interfering water bodies to improve the accuracy of wa...

Descripción completa

Detalles Bibliográficos
Autores principales: Luo, Yuanjiang, Feng, Ao, Li, Hongxiang, Li, Danyang, Wu, Xuan, Liao, Jie, Zhang, Chengwu, Zheng, Xingqiang, Pu, Haibo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9355223/
https://www.ncbi.nlm.nih.gov/pubmed/35930531
http://dx.doi.org/10.1371/journal.pone.0272317
_version_ 1784763246537867264
author Luo, Yuanjiang
Feng, Ao
Li, Hongxiang
Li, Danyang
Wu, Xuan
Liao, Jie
Zhang, Chengwu
Zheng, Xingqiang
Pu, Haibo
author_facet Luo, Yuanjiang
Feng, Ao
Li, Hongxiang
Li, Danyang
Wu, Xuan
Liao, Jie
Zhang, Chengwu
Zheng, Xingqiang
Pu, Haibo
author_sort Luo, Yuanjiang
collection PubMed
description Extracting water bodies from remote sensing images is important in many fields, such as in water resources information acquisition and analysis. Conventional methods of water body extraction enhance the differences between water bodies and other interfering water bodies to improve the accuracy of water body boundary extraction. Multiple methods must be used alternately to extract water body boundaries more accurately. Water body extraction methods combined with neural networks struggle to improve the extraction accuracy of fine water bodies while ensuring an overall extraction effect. In this study, false color processing and a generative adversarial network (GAN) were added to reconstruct remote sensing images and enhance the features of tiny water bodies. In addition, a multi-scale input strategy was designed to reduce the training cost. We input the processed data into a new water body extraction method based on strip pooling for remote sensing images, which is an improvement of DeepLabv3+. Strip pooling was introduced in the DeepLabv3+ network to better extract water bodies with a discrete distribution at long distances using different strip kernels. The experiments and tests show that the proposed method can improve the accuracy of water body extraction and is effective in fine water body extraction. Compared with seven other traditional remote sensing water body extraction methods and deep learning semantic segmentation methods, the prediction accuracy of the proposed method reaches 94.72%. In summary, the proposed method performs water body extraction better than existing methods.
format Online
Article
Text
id pubmed-9355223
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93552232022-08-06 New deep learning method for efficient extraction of small water from remote sensing images Luo, Yuanjiang Feng, Ao Li, Hongxiang Li, Danyang Wu, Xuan Liao, Jie Zhang, Chengwu Zheng, Xingqiang Pu, Haibo PLoS One Research Article Extracting water bodies from remote sensing images is important in many fields, such as in water resources information acquisition and analysis. Conventional methods of water body extraction enhance the differences between water bodies and other interfering water bodies to improve the accuracy of water body boundary extraction. Multiple methods must be used alternately to extract water body boundaries more accurately. Water body extraction methods combined with neural networks struggle to improve the extraction accuracy of fine water bodies while ensuring an overall extraction effect. In this study, false color processing and a generative adversarial network (GAN) were added to reconstruct remote sensing images and enhance the features of tiny water bodies. In addition, a multi-scale input strategy was designed to reduce the training cost. We input the processed data into a new water body extraction method based on strip pooling for remote sensing images, which is an improvement of DeepLabv3+. Strip pooling was introduced in the DeepLabv3+ network to better extract water bodies with a discrete distribution at long distances using different strip kernels. The experiments and tests show that the proposed method can improve the accuracy of water body extraction and is effective in fine water body extraction. Compared with seven other traditional remote sensing water body extraction methods and deep learning semantic segmentation methods, the prediction accuracy of the proposed method reaches 94.72%. In summary, the proposed method performs water body extraction better than existing methods. Public Library of Science 2022-08-05 /pmc/articles/PMC9355223/ /pubmed/35930531 http://dx.doi.org/10.1371/journal.pone.0272317 Text en © 2022 Luo 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
Luo, Yuanjiang
Feng, Ao
Li, Hongxiang
Li, Danyang
Wu, Xuan
Liao, Jie
Zhang, Chengwu
Zheng, Xingqiang
Pu, Haibo
New deep learning method for efficient extraction of small water from remote sensing images
title New deep learning method for efficient extraction of small water from remote sensing images
title_full New deep learning method for efficient extraction of small water from remote sensing images
title_fullStr New deep learning method for efficient extraction of small water from remote sensing images
title_full_unstemmed New deep learning method for efficient extraction of small water from remote sensing images
title_short New deep learning method for efficient extraction of small water from remote sensing images
title_sort new deep learning method for efficient extraction of small water from remote sensing images
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9355223/
https://www.ncbi.nlm.nih.gov/pubmed/35930531
http://dx.doi.org/10.1371/journal.pone.0272317
work_keys_str_mv AT luoyuanjiang newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT fengao newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT lihongxiang newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT lidanyang newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT wuxuan newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT liaojie newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT zhangchengwu newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT zhengxingqiang newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages
AT puhaibo newdeeplearningmethodforefficientextractionofsmallwaterfromremotesensingimages