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

Facade Segmentation from Oblique UAV Imagery

Zhuo, Xiangyu and Mönks, Milena and Esch, Thomas and Reinartz, Peter (2019) Facade Segmentation from Oblique UAV Imagery. In: 2019 Joint Urban Remote Sensing Event, JURSE 2019, pp. 1-4. IEEE. JURSE 2019, 22-24 May 2019, Vannes, France. DOI: 10.1109/JURSE.2019.8809024 ISBN 978-172810009-8

[img] PDF

Official URL: https://ieeexplore.ieee.org/document/8809024


Building semantic segmentation is a crucial task for building information modeling (BIM). Current research generally exploits terrestrial image data, which provides only limited view of a building. By contrast, oblique imagery acquired by unmanned aerial vehicle (UAV) can provide richer information of both the building and its surroundings at a larger scale. In this paper, we present a novel pipeline for building semantic segmentation from oblique UAV images using a fully convolutional neural network (FCN). To cope with the lack of UAV image annotations at facade level, we leverage existing ground-view facades databases to simulate various aerial-view images based on estimated homography, yielding abundant synthetic aerial image annotations as training data. The FCN is trained end-to-end and tested on full-tile UAV images. Experiments demonstrate that the incorporation of simulated views can significantly boost the prediction accuracy of the network on UAV images and achieve reasonable segmentation performance.

Item URL in elib:https://elib.dlr.de/129075/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:Facade Segmentation from Oblique UAV Imagery
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Zhuo, XiangyuXiangyu.Zhuo (at) dlr.deUNSPECIFIED
Mönks, MilenaMilena.Moenks (at) dlr.dehttps://orcid.org/0000-0002-1603-1173
Esch, ThomasThomas.Esch (at) dlr.deUNSPECIFIED
Reinartz, Peterpeter.reinartz (at) dlr.dehttps://orcid.org/0000-0002-8122-1475
Date:May 2019
Journal or Publication Title:2019 Joint Urban Remote Sensing Event, JURSE 2019
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1109/JURSE.2019.8809024
Page Range:pp. 1-4
Keywords:Semantic segmentation, UAV imagery, fully convolutional neural network (FCN), deep learning, building information model
Event Title:JURSE 2019
Event Location:Vannes, France
Event Type:international Conference
Event Dates:22-24 May 2019
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Remote sensing and geoscience
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
German Remote Sensing Data Center > Land Surface Dynamics
Deposited By: Mönks, Milena
Deposited On:18 Sep 2019 10:58
Last Modified:10 Jul 2020 12:57

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.