Classification of Wide-Area SAR Mosaics: Deep Learning Approach for Corine Based Mapping of Finland Using Multitemporal Sentinel-1 Data

Oleg Antropov, Yrjö Rauste, Sanja Šćepanović, Vladimir Ignatenko, Anne Lönnqvist, Jaan Praks

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Here, we examine a deep learning approach to perform land cover classification using country-wide SAR mosaics compiled using multitemporal Sentinel-1 imagery. We capitalize on our earlier study [1], demonstrating the suitability of deep learning models for land cover mapping using satellite C-band SAR images. A set of SAR mosaics compiled from consecutive Sentinel-1 IW mode acquisitions covering the whole territory of Finland was used in production of the whole-country land cover map. The imagery were used as an input to the state-of-the-art deep-learning model for semantic segmentation called FC-DenseNet. This model was pre-trained on the ImageNet dataset and further fine-tuned in this study. CORINE land cover map was used as a reference, and the model was trained to distinguish between 5 Level-1 CORINE classes. Upon the evaluation and benchmarking, we found that the FC-DenseNet model is able to achieve nearly 90% overall classification accuracy. These results indicate the suitability of deep learning approaches to support efficient operational wide-area mapping using satellite SAR imagery.
Original languageEnglish
Title of host publication2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Subtitle of host publicationProceedings
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages4283-4286
ISBN (Electronic)978-1-7281-6374-1
ISBN (Print)978-1-7281-6375-8
DOIs
Publication statusPublished - 17 Feb 2020
MoE publication typeA4 Article in a conference publication
EventIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020: Online - Virtual, Waikoloa, United States
Duration: 26 Sep 20202 Oct 2020

Publication series

SeriesIEEE International Geoscience and Remote Sensing Symposium Proceedings
ISSN2153-6996

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
CountryUnited States
CityWaikoloa
Period26/09/202/10/20

Keywords

  • C-band
  • CORINE
  • deep learning
  • image classification
  • land cover mapping
  • semantic segmentation
  • Sentinel-1 data
  • synthetic aperture radar

Fingerprint Dive into the research topics of 'Classification of Wide-Area SAR Mosaics: Deep Learning Approach for Corine Based Mapping of Finland Using Multitemporal Sentinel-1 Data'. Together they form a unique fingerprint.

Cite this