University of Oulu

N. Bengana and J. Heikkilä, "Improving Land Cover Segmentation Across Satellites Using Domain Adaptation," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 1399-1410, 2021, doi: 10.1109/JSTARS.2020.3042887

Improving land cover segmentation across satellites using domain adaptation

Saved in:
Author: Bengana, Nadir1; Heikkilä, Janne1
Organizations: 1Faculty of Information Technology and Electrical Engineering, University of Oulu, 90014 Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 7.3 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-04-21


Land use and land cover mapping is essential to various fields of study, such as forestry, agriculture, and urban management. Generally, earth observation satellites facilitate and accelerate the mapping process. Subsequently, deep learning methods have been proven to be excellent in automating the mapping via semantic image segmentation. However, because deep neural networks require large amounts of labeled data, it is not easy to exploit the full potential of satellite imagery. Additionally, land cover tends to differ in appearance from one region to another; therefore, having labeled data from one location does not necessarily help map others. Furthermore, satellite images come in various multispectral bands, which range from RGB to over 12 bands. In this study, our aim is to use domain adaptation (DA) to solve the aforementioned problems. We applied a well-performing DA approach on the DeepGlobe land cover dataset as well as datasets that we built using RGB images from Sentinel-2, WorldView-2, and Pleiades-1B satellites with CORINE Land Cover as ground truth (GT) labels. The experiments revealed significant improvements over the results obtained without using DA. In some cases, an improvement of over 20% mean intersection over union was obtained. Sometimes, our model manages to correct errors in the GT labels.

see all

Series: IEEE journal of selected topics in applied Earth observations and remote sensing
ISSN: 1939-1404
ISSN-E: 2151-1535
ISSN-L: 1939-1404
Volume: 14
Pages: 1399 - 1410
DOI: 10.1109/JSTARS.2020.3042887
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Funding: This work was supported by the Business Finland under Grant 1259/31/2018.
Copyright information: © The Authors 2021. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see