Cargando…
A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks
Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7188251/ https://www.ncbi.nlm.nih.gov/pubmed/32377033 http://dx.doi.org/10.1016/j.isprsjprs.2020.01.028 |
_version_ | 1783527280367108096 |
---|---|
author | Qiu, Chunping Schmitt, Michael Geiß, Christian Chen, Tzu-Hsin Karen Zhu, Xiao Xiang |
author_facet | Qiu, Chunping Schmitt, Michael Geiß, Christian Chen, Tzu-Hsin Karen Zhu, Xiao Xiang |
author_sort | Qiu, Chunping |
collection | PubMed |
description | Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization. |
format | Online Article Text |
id | pubmed-7188251 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-71882512020-05-04 A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks Qiu, Chunping Schmitt, Michael Geiß, Christian Chen, Tzu-Hsin Karen Zhu, Xiao Xiang ISPRS J Photogramm Remote Sens Article Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization. Elsevier 2020-05 /pmc/articles/PMC7188251/ /pubmed/32377033 http://dx.doi.org/10.1016/j.isprsjprs.2020.01.028 Text en © 2020 The Authors http://creativecommons.org/licenses/by/4.0/ This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Qiu, Chunping Schmitt, Michael Geiß, Christian Chen, Tzu-Hsin Karen Zhu, Xiao Xiang A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title | A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title_full | A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title_fullStr | A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title_full_unstemmed | A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title_short | A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks |
title_sort | framework for large-scale mapping of human settlement extent from sentinel-2 images via fully convolutional neural networks |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7188251/ https://www.ncbi.nlm.nih.gov/pubmed/32377033 http://dx.doi.org/10.1016/j.isprsjprs.2020.01.028 |
work_keys_str_mv | AT qiuchunping aframeworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT schmittmichael aframeworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT geißchristian aframeworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT chentzuhsinkaren aframeworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT zhuxiaoxiang aframeworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT qiuchunping frameworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT schmittmichael frameworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT geißchristian frameworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT chentzuhsinkaren frameworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks AT zhuxiaoxiang frameworkforlargescalemappingofhumansettlementextentfromsentinel2imagesviafullyconvolutionalneuralnetworks |