A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
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.
I: I S P R S Journal of Photogrammetry and Remote Sensing, Bind 163, 2020, s. 152.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks
AU - Qiu, Chunping
AU - Schmitt, Michael
AU - Geiß, Christian
AU - Chen, Tzu-Hsin Karen
AU - Zhu, Xiao Xiang
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
KW - Faculty of Science
KW - built-up area
KW - convolutional neural networks
KW - human Settlements
KW - Sentinel-2
KW - urbanization
U2 - https://doi.org/10.1016/j.isprsjpr
DO - https://doi.org/10.1016/j.isprsjpr
M3 - Journal article
VL - 163
SP - 152
JO - ISPRS Journal of Photogrammetry and Remote Sensing
JF - ISPRS Journal of Photogrammetry and Remote Sensing
SN - 0924-2716
ER -
ID: 238600443