Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm

The accurate classification of wetland vegetation is essential for rapid assessment and management. The Honghe National Nature Reserve (HNNR), located in Northeast China, was studied. The multi-scale remote sensing data of a new generation of Chinese high-spatial-resolution earth observation satelli...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Man Liu, Bolin Fu, Shuyu Xie, Hongchang He, Feiwu Lan, Yuyang Li, Peiqing Lou, Donglin Fan
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Marsh vegetation DeepLabV3 Plus Satellite images Intelligent classification Spatial resolution Spectral range Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/27c6acbe6bdc4d818ec690e6da3590cd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:27c6acbe6bdc4d818ec690e6da3590cd
record_format	dspace
spelling	oai:doaj.org-article:27c6acbe6bdc4d818ec690e6da3590cd2021-12-01T04:48:10ZComparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm1470-160X10.1016/j.ecolind.2021.107562https://doaj.org/article/27c6acbe6bdc4d818ec690e6da3590cd2021-06-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21002272https://doaj.org/toc/1470-160XThe accurate classification of wetland vegetation is essential for rapid assessment and management. The Honghe National Nature Reserve (HNNR), located in Northeast China, was studied. The multi-scale remote sensing data of a new generation of Chinese high-spatial-resolution earth observation satellites Gaofen-1 (GF-1), Gaofen-2 (GF-2), Ziyuan-3 (ZY-3), and international earth observation satellites Sentinel-2A and Landsat 8 OLI were selected as sources. Based on the DeepLabV3 Plus deep learning model, 12 intelligent marsh vegetation classification models were constructed. We quantitatively analyzed the applicability and identification ability of DeepLabV3 Plus for classifying complex marsh vegetation. We discuss the differences in accuracy of marsh vegetation classification with different remote sensing data sets. The spatial resolution of remote sensing data sets ranges from 30 m to 0.8 m, and spectral bands range from blue bands (450 nm) to shortwave infrared bands (2280 nm). The specific conclusions of this study are as follows: (1) The DeepLabV3 Plus model better identified marsh vegetation, but there were significant differences in the classification accuracy of 12 DeepLabV3 Plus intelligent identification models. (2) Under the same conditions of the spectral bands (four Blue ~ NIR bands), the accuracy of deep-water marsh vegetation classification gradually increased as spatial resolution improved. For shallow-water marsh vegetation, when the accuracy of vegetation classification increased to a certain level, the classification accuracy decreased with the improvement of spatial resolution, which indicated that high-resolution images reduced pixel mixing to a certain extent, but for some vegetation types, the internal spectral difference increased, which made classification more difficult. (3) The increase of spectral bands improved the classification of marsh vegetation, while the classification accuracy of models with spectral indices was better than that of models only including spectral bands. (4) The accuracy of marsh vegetation classification was greatly improved by combining spectral bands and spectral indices. (5) The classification of the five sensor satellite images had statistical differences between models with different spatial resolutions and models with different spectral ranges.Man LiuBolin FuShuyu XieHongchang HeFeiwu LanYuyang LiPeiqing LouDonglin FanElsevierarticleMarsh vegetationDeepLabV3 PlusSatellite imagesIntelligent classificationSpatial resolutionSpectral rangeEcologyQH540-549.5ENEcological Indicators, Vol 125, Iss , Pp 107562- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Marsh vegetation DeepLabV3 Plus Satellite images Intelligent classification Spatial resolution Spectral range Ecology QH540-549.5
spellingShingle	Marsh vegetation DeepLabV3 Plus Satellite images Intelligent classification Spatial resolution Spectral range Ecology QH540-549.5 Man Liu Bolin Fu Shuyu Xie Hongchang He Feiwu Lan Yuyang Li Peiqing Lou Donglin Fan Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
description	The accurate classification of wetland vegetation is essential for rapid assessment and management. The Honghe National Nature Reserve (HNNR), located in Northeast China, was studied. The multi-scale remote sensing data of a new generation of Chinese high-spatial-resolution earth observation satellites Gaofen-1 (GF-1), Gaofen-2 (GF-2), Ziyuan-3 (ZY-3), and international earth observation satellites Sentinel-2A and Landsat 8 OLI were selected as sources. Based on the DeepLabV3 Plus deep learning model, 12 intelligent marsh vegetation classification models were constructed. We quantitatively analyzed the applicability and identification ability of DeepLabV3 Plus for classifying complex marsh vegetation. We discuss the differences in accuracy of marsh vegetation classification with different remote sensing data sets. The spatial resolution of remote sensing data sets ranges from 30 m to 0.8 m, and spectral bands range from blue bands (450 nm) to shortwave infrared bands (2280 nm). The specific conclusions of this study are as follows: (1) The DeepLabV3 Plus model better identified marsh vegetation, but there were significant differences in the classification accuracy of 12 DeepLabV3 Plus intelligent identification models. (2) Under the same conditions of the spectral bands (four Blue ~ NIR bands), the accuracy of deep-water marsh vegetation classification gradually increased as spatial resolution improved. For shallow-water marsh vegetation, when the accuracy of vegetation classification increased to a certain level, the classification accuracy decreased with the improvement of spatial resolution, which indicated that high-resolution images reduced pixel mixing to a certain extent, but for some vegetation types, the internal spectral difference increased, which made classification more difficult. (3) The increase of spectral bands improved the classification of marsh vegetation, while the classification accuracy of models with spectral indices was better than that of models only including spectral bands. (4) The accuracy of marsh vegetation classification was greatly improved by combining spectral bands and spectral indices. (5) The classification of the five sensor satellite images had statistical differences between models with different spatial resolutions and models with different spectral ranges.
format	article
author	Man Liu Bolin Fu Shuyu Xie Hongchang He Feiwu Lan Yuyang Li Peiqing Lou Donglin Fan
author_facet	Man Liu Bolin Fu Shuyu Xie Hongchang He Feiwu Lan Yuyang Li Peiqing Lou Donglin Fan
author_sort	Man Liu
title	Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
title_short	Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
title_full	Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
title_fullStr	Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
title_full_unstemmed	Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm
title_sort	comparison of multi-source satellite images for classifying marsh vegetation using deeplabv3 plus deep learning algorithm
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/27c6acbe6bdc4d818ec690e6da3590cd
work_keys_str_mv	AT manliu comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT bolinfu comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT shuyuxie comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT hongchanghe comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT feiwulan comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT yuyangli comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT peiqinglou comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm AT donglinfan comparisonofmultisourcesatelliteimagesforclassifyingmarshvegetationusingdeeplabv3plusdeeplearningalgorithm
_version_	1718405715029131264

Comparison of multi-source satellite images for classifying marsh vegetation using DeepLabV3 Plus deep learning algorithm

Ejemplares similares