A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network

This paper proposed an improved U-Net fully convolutional neural network to automatically extract a single landslide deformation information under time series based on the physical model experiments. This method extracts time series information for three different landslide deformation ranges. Compa...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bibo Dai, Yunmin Wang, Chunyang Ye, Qihang Li, Canming Yuan, Song Lu, Yuyang Li
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	landslide U-Net neural network superpixel method point cloud evaluation indicators Science Q
Acceso en línea:	https://doaj.org/article/d0297fcc3af344cda65647cd13742d37
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d0297fcc3af344cda65647cd13742d37
record_format	dspace
spelling	oai:doaj.org-article:d0297fcc3af344cda65647cd13742d372021-12-03T07:14:52ZA Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network2296-646310.3389/feart.2021.785476https://doaj.org/article/d0297fcc3af344cda65647cd13742d372021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/feart.2021.785476/fullhttps://doaj.org/toc/2296-6463This paper proposed an improved U-Net fully convolutional neural network to automatically extract a single landslide deformation information under time series based on the physical model experiments. This method extracts time series information for three different landslide deformation ranges. Compared to U-Net and mainstream superpixel method, evaluation indicators of DSC, VOE and RVD verify the high recognition accuracy and strong robustness of our method.Bibo DaiBibo DaiBibo DaiYunmin WangYunmin WangChunyang YeQihang LiCanming YuanSong LuSong LuYuyang LiFrontiers Media S.A.articlelandslideU-Net neural networksuperpixel methodpoint cloudevaluation indicatorsScienceQENFrontiers in Earth Science, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	landslide U-Net neural network superpixel method point cloud evaluation indicators Science Q
spellingShingle	landslide U-Net neural network superpixel method point cloud evaluation indicators Science Q Bibo Dai Bibo Dai Bibo Dai Yunmin Wang Yunmin Wang Chunyang Ye Qihang Li Canming Yuan Song Lu Song Lu Yuyang Li A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
description	This paper proposed an improved U-Net fully convolutional neural network to automatically extract a single landslide deformation information under time series based on the physical model experiments. This method extracts time series information for three different landslide deformation ranges. Compared to U-Net and mainstream superpixel method, evaluation indicators of DSC, VOE and RVD verify the high recognition accuracy and strong robustness of our method.
format	article
author	Bibo Dai Bibo Dai Bibo Dai Yunmin Wang Yunmin Wang Chunyang Ye Qihang Li Canming Yuan Song Lu Song Lu Yuyang Li
author_facet	Bibo Dai Bibo Dai Bibo Dai Yunmin Wang Yunmin Wang Chunyang Ye Qihang Li Canming Yuan Song Lu Song Lu Yuyang Li
author_sort	Bibo Dai
title	A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
title_short	A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
title_full	A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
title_fullStr	A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
title_full_unstemmed	A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network
title_sort	novel method for extracting time series information of deformation area of a single landslide based on improved u-net neural network
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/d0297fcc3af344cda65647cd13742d37
work_keys_str_mv	AT bibodai anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT bibodai anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT bibodai anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yunminwang anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yunminwang anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT chunyangye anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT qihangli anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT canmingyuan anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT songlu anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT songlu anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yuyangli anovelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT bibodai novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT bibodai novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT bibodai novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yunminwang novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yunminwang novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT chunyangye novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT qihangli novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT canmingyuan novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT songlu novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT songlu novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork AT yuyangli novelmethodforextractingtimeseriesinformationofdeformationareaofasinglelandslidebasedonimprovedunetneuralnetwork
_version_	1718373841103749120

A Novel Method for Extracting Time Series Information of Deformation Area of a Single Landslide Based on Improved U-Net Neural Network

Ejemplares similares