DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Enabling country-scale land cover mapping with meter-resolution satellite imagery

Tong, Xin-Yi and Xia, Gui-Song and Zhu, Xiao Xiang (2023) Enabling country-scale land cover mapping with meter-resolution satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 196, pp. 178-196. Elsevier. doi: 10.1016/j.isprsjprs.2022.12.011. ISSN 0924-2716.

[img] PDF - Published version

Official URL: https://dx.doi.org/10.1016/j.isprsjprs.2022.12.011


High-resolution satellite images can provide abundant, detailed spatial information for land cover classification, which is particularly important for studying the complicated built environment. However, due to the complex land cover patterns, the costly training sample collections, and the severe distribution shifts of satellite imageries caused by, e.g., geographical differences or acquisition conditions, few studies have applied high-resolution images to land cover mapping in detailed categories at large scale. To fill this gap, we present a large-scale land cover dataset, Five-Billion-Pixels. It contains more than 5 billion labeled pixels of 150 high-resolution Gaofen-2 (4 m) satellite images, annotated in a 24-category system covering artificial-constructed, agricultural, and natural classes. In addition, we propose a deep-learning-based unsupervised domain adaptation approach that can transfer classification models trained on labeled dataset (referred to as the source domain) to unlabeled data (referred to as the target domain) for large-scale land cover mapping. Specifically, we introduce an end-to-end Siamese network employing dynamic pseudo-label assignment and class balancing strategy to perform adaptive domain joint learning. To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images. Over a total study area of 60,000 km2, the experiments show promising results even though the input images are entirely unlabeled. The proposed approach, trained with the Five-Billion-Pixels dataset, enables high-quality and detailed land cover mapping across the whole country of China and some other Asian countries at meter-resolution.

Item URL in elib:https://elib.dlr.de/193363/
Document Type:Article
Title:Enabling country-scale land cover mapping with meter-resolution satellite imagery
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Tong, Xin-YiUNSPECIFIEDhttps://orcid.org/0000-0001-9832-7973UNSPECIFIED
Xia, Gui-SongUNSPECIFIEDhttps://orcid.org/0000-0001-7660-6090UNSPECIFIED
Zhu, Xiao XiangUNSPECIFIEDhttps://orcid.org/0000-0001-5530-3613UNSPECIFIED
Date:10 January 2023
Journal or Publication Title:ISPRS Journal of Photogrammetry and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
Page Range:pp. 178-196
Keywords:Land cover mapping; High-spatial resolution; Classification; Deep learning; Transfer learning; Domain adaptation; Dataset; Gaofen-2; Gaofen-1; PlanetScope; Sentinel-2; Megacity
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Optical remote sensing, R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Tong, Xinyi
Deposited On:24 Jan 2023 12:34
Last Modified:02 Feb 2023 18:45

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.