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

Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks

Henry, Corentin and Azimi, Seyedmajid and Merkle, Nina Marie (2018) Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks. IEEE Geoscience and Remote Sensing Letters, 15 (12), pp. 1867-1871. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/LGRS.2018.2864342 ISSN 1545-598X

[img] PDF

Official URL: https://ieeexplore.ieee.org/document/8447237


Remote sensing is extensively used in cartography. As transportation networks grow and change, extracting roads automatically from satellite images is crucial to keep maps up-to-date. Synthetic Aperture Radar satellites can provide high resolution topographical maps. However roads are difficult to identify in these data as they look visually similar to targets such as rivers and railways. Most road extraction methods on Synthetic Aperture Radar images still rely on a prior segmentation performed by classical computer vision algorithms. Few works study the potential of deep learning techniques, despite their successful applications to optical imagery. This letter presents an evaluation of Fully-Convolutional Neural Networks for road segmentation in SAR images. We study the relative performance of early and state-of-the-art networks after carefully enhancing their sensitivity towards thin objects by adding spatial tolerance rules. Our models shows promising results, successfully extracting most of the roads in our test dataset. This shows that, although Fully-Convolutional Neural Networks natively lack efficiency for road segmentation, they are capable of good results if properly tuned. As the segmentation quality does not scale well with the increasing depth of the networks, the design of specialized architectures for roads extraction should yield better performances.

Item URL in elib:https://elib.dlr.de/120552/
Document Type:Article
Title:Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Henry, CorentinCorentin.henry (at) dlr.dehttps://orcid.org/0000-0002-4330-3058
Azimi, SeyedmajidSeyedmajid.Azimi (at) dlr.dehttps://orcid.org/0000-0002-6084-2272
Merkle, Nina MarieNina.Merkle (at) dlr.dehttps://orcid.org/0000-0003-4177-1066
Date:December 2018
Journal or Publication Title:IEEE Geoscience and Remote Sensing Letters
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1109/LGRS.2018.2864342
Page Range:pp. 1867-1871
Publisher:IEEE - Institute of Electrical and Electronics Engineers
Keywords:Road extraction, synthetic aperture radar, high resolution SAR data, TerraSAR-X, deep learning, semantic segmentation
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - Vabene++ (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Henry, Corentin
Deposited On:22 Jun 2018 12:15
Last Modified:31 Jul 2019 20:18

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.