Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors

Rapid and accurate extraction of water bodies from high-spatial-resolution remote sensing images is of great value for water resource management, water quality monitoring and natural disaster emergency response. For traditional water body extraction methods, it is difficult to select image texture a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yanjun Wang, Shaochun Li, Yunhao Lin, Mengjie Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	water body extraction multisensor high-resolution image lightweight deep neural network MobileNetv2 deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/f7b0ee7c1ddd40088936faeea54e1c05
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f7b0ee7c1ddd40088936faeea54e1c05
record_format	dspace
spelling	oai:doaj.org-article:f7b0ee7c1ddd40088936faeea54e1c052021-11-11T19:19:17ZLightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors10.3390/s212173971424-8220https://doaj.org/article/f7b0ee7c1ddd40088936faeea54e1c052021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7397https://doaj.org/toc/1424-8220Rapid and accurate extraction of water bodies from high-spatial-resolution remote sensing images is of great value for water resource management, water quality monitoring and natural disaster emergency response. For traditional water body extraction methods, it is difficult to select image texture and features, the shadows of buildings and other ground objects are in the same spectrum as water bodies, the existing deep convolutional neural network is difficult to train, the consumption of computing resources is large, and the methods cannot meet real-time requirements. In this paper, a water body extraction method based on lightweight MobileNetV2 is proposed and applied to multisensor high-resolution remote sensing images, such as GF-2, WorldView-2 and UAV orthoimages. This method was validated in two typical complex geographical scenes: water bodies for farmland irrigation, which have a broken shape and long and narrow area and are surrounded by many buildings in towns and villages; and water bodies in mountainous areas, which have undulating topography, vegetation coverage and mountain shadows all over. The results were compared with those of the support vector machine, random forest and U-Net models and also verified by generalization tests and the influence of spatial resolution changes. First, the results show that the F1-score and Kappa coefficients of the MobileNetV2 model extracting water bodies from three different high-resolution images were 0.75 and 0.72 for GF-2, 0.86 and 0.85 for Worldview-2 and 0.98 and 0.98 for UAV, respectively, which are higher than those of traditional machine learning models and U-Net. Second, the training time, number of parameters and calculation amount of the MobileNetV2 model were much lower than those of the U-Net model, which greatly improves the water body extraction efficiency. Third, in other more complex surface areas, the MobileNetV2 model still maintained relatively high accuracy of water body extraction. Finally, we tested the effects of multisensor models and found that training with lower and higher spatial resolution images combined can be beneficial, but that using just lower resolution imagery is ineffective. This study provides a reference for the efficient automation of water body classification and extraction under complex geographical environment conditions and can be extended to water resource investigation, management and planning.Yanjun WangShaochun LiYunhao LinMengjie WangMDPI AGarticlewater body extractionmultisensor high-resolution imagelightweight deep neural networkMobileNetv2deep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7397, p 7397 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	water body extraction multisensor high-resolution image lightweight deep neural network MobileNetv2 deep learning Chemical technology TP1-1185
spellingShingle	water body extraction multisensor high-resolution image lightweight deep neural network MobileNetv2 deep learning Chemical technology TP1-1185 Yanjun Wang Shaochun Li Yunhao Lin Mengjie Wang Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
description	Rapid and accurate extraction of water bodies from high-spatial-resolution remote sensing images is of great value for water resource management, water quality monitoring and natural disaster emergency response. For traditional water body extraction methods, it is difficult to select image texture and features, the shadows of buildings and other ground objects are in the same spectrum as water bodies, the existing deep convolutional neural network is difficult to train, the consumption of computing resources is large, and the methods cannot meet real-time requirements. In this paper, a water body extraction method based on lightweight MobileNetV2 is proposed and applied to multisensor high-resolution remote sensing images, such as GF-2, WorldView-2 and UAV orthoimages. This method was validated in two typical complex geographical scenes: water bodies for farmland irrigation, which have a broken shape and long and narrow area and are surrounded by many buildings in towns and villages; and water bodies in mountainous areas, which have undulating topography, vegetation coverage and mountain shadows all over. The results were compared with those of the support vector machine, random forest and U-Net models and also verified by generalization tests and the influence of spatial resolution changes. First, the results show that the F1-score and Kappa coefficients of the MobileNetV2 model extracting water bodies from three different high-resolution images were 0.75 and 0.72 for GF-2, 0.86 and 0.85 for Worldview-2 and 0.98 and 0.98 for UAV, respectively, which are higher than those of traditional machine learning models and U-Net. Second, the training time, number of parameters and calculation amount of the MobileNetV2 model were much lower than those of the U-Net model, which greatly improves the water body extraction efficiency. Third, in other more complex surface areas, the MobileNetV2 model still maintained relatively high accuracy of water body extraction. Finally, we tested the effects of multisensor models and found that training with lower and higher spatial resolution images combined can be beneficial, but that using just lower resolution imagery is ineffective. This study provides a reference for the efficient automation of water body classification and extraction under complex geographical environment conditions and can be extended to water resource investigation, management and planning.
format	article
author	Yanjun Wang Shaochun Li Yunhao Lin Mengjie Wang
author_facet	Yanjun Wang Shaochun Li Yunhao Lin Mengjie Wang
author_sort	Yanjun Wang
title	Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
title_short	Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
title_full	Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
title_fullStr	Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
title_full_unstemmed	Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors
title_sort	lightweight deep neural network method for water body extraction from high-resolution remote sensing images with multisensors
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f7b0ee7c1ddd40088936faeea54e1c05
work_keys_str_mv	AT yanjunwang lightweightdeepneuralnetworkmethodforwaterbodyextractionfromhighresolutionremotesensingimageswithmultisensors AT shaochunli lightweightdeepneuralnetworkmethodforwaterbodyextractionfromhighresolutionremotesensingimageswithmultisensors AT yunhaolin lightweightdeepneuralnetworkmethodforwaterbodyextractionfromhighresolutionremotesensingimageswithmultisensors AT mengjiewang lightweightdeepneuralnetworkmethodforwaterbodyextractionfromhighresolutionremotesensingimageswithmultisensors
_version_	1718431563852546048

Lightweight Deep Neural Network Method for Water Body Extraction from High-Resolution Remote Sensing Images with Multisensors

Ejemplares similares