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

Learning water body segmentation from very high-resolution satellite and aerial images. Remote Sensing of Environment

Wieland, Marc and Martinis, Sandro and Kiefl, Ralph and Gstaiger, Veronika (2023) Learning water body segmentation from very high-resolution satellite and aerial images. Remote Sensing of Environment. Remote Sensing of Environment, 287, pp. 1-14. Elsevier. doi: 10.1016/j.rse.2023.113452. ISSN 0034-4257.

[img] PDF - Only accessible within DLR bis 6 January 2025 - Postprint version (accepted manuscript)

Official URL: https://www.sciencedirect.com/science/article/abs/pii/S0034425723000032


This study evaluates the performance of convolutional neural networks for semantic segmentation of water bodies in very high-resolution satellite and aerial images from multiple sensors with particular focus on flood emergency response applications. Different model architectures (U-Net and DeepLab-V3+) are combined with encoder backbones (MobileNet-V3, ResNet-50 and EfficientNet-B4) and tested for their ability to delineate inundated areas under varying environmental conditions and data availability scenarios. An unprecedented reference dataset of 1120 globally sampled images with quality checked binary water masks is introduced and used to train, validate and test the models for water body segmentation. Furthermore, independent test datasets are developed to test the generalization ability of the trained models across regions, sensors (IKONOS, GeoEye-1, WorldView-2, WorldView-3 and four different airborne camera systems) and tasks (normal water and flood water segmentation). Results indicate that across all tested scenarios a U-Net model with Mobilenet-V3 backbone pre-trained on ImageNet performs best. While using R-G-B image bands performs well, adding the near infrared band (if available) slightly improves prediction results. Similarly, adding slope information from an independent digital elevation model increases accuracies. Train-time augmentation and contrast enhancement could improve transferability across sensors and in particular between satellite and aerial images. Moreover, adding noisy training data from freely available online resources could further improve performance with minimal annotation effort.

Item URL in elib:https://elib.dlr.de/196219/
Document Type:Article
Title:Learning water body segmentation from very high-resolution satellite and aerial images. Remote Sensing of Environment
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Wieland, MarcUNSPECIFIEDhttps://orcid.org/0000-0002-1155-723XUNSPECIFIED
Martinis, SandroUNSPECIFIEDhttps://orcid.org/0000-0002-6400-361XUNSPECIFIED
Kiefl, RalphUNSPECIFIEDhttps://orcid.org/0000-0001-7622-5458UNSPECIFIED
Gstaiger, VeronikaUNSPECIFIEDhttps://orcid.org/0000-0001-7328-7485UNSPECIFIED
Date:13 January 2023
Journal or Publication Title:Remote Sensing of Environment
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:Yes
Page Range:pp. 1-14
Keywords:Convolutional neural networks; Semantic segmentation; Water; Emergency response; Rapid mapping
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 - Remote Sensing and Geo Research
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Geo Risks and Civil Security
Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Wieland, Dr Marc
Deposited On:31 Jul 2023 11:45
Last Modified:18 Oct 2023 13:31

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.