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

Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata

Li, Qingyu and Shi, Yilei and Auer, Stefan and Roschlaub, Robert and Moest, Karin and Schmitt, Michael and Zhu, Xiao Xiang (2020) Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2, pp. 517-524. ISPRS 2020, 2020-08-31 - 2020-09-02, Nice, France ONLINE. doi: 10.5194/isprs-annals-V-2-2020-517-2020. ISSN 2194-9042.

[img] PDF
6MB

Official URL: https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2020/517/2020/

Abstract

Undocumented buildings are buildings which were built years ago, but were never recorded in official digital cadastral maps.Detection of undocumented buildings is of great importance for urban planning and monitoring. The state of Bavaria, Germany,pursues this task based on high resolution optical data and digital surface models, using semi-automatic detection methods, whichsuffer from a high false alarm rate. In order to study the influence of sampling strategies on the performance of building detection, we have firstly designed a transferability analysis experiment, which has not been adequately addressed in the current literature.In this experiment, we test whether the trained model from a district contains valuable information for building detection in adifferent district. It was found that the large-scale building detection results can be considerably improved when training samplesare collected from different districts. Based on the building detection results, we propose a novel framework for the detection ofundocumented buildings using Convolutional Neural Network (CNN) and official geodata. More specifically, buildings are identifiedas undocumented, when their pixels in the output of the CNN are predicted as ”building”, whereas they belong to the ”non-building”in the Digital Cadastral Map (DFK). The detected undocumented building pixels are subsequently divided into the class of old or newundocumented building with the aid of a Temporal Digital Surface Model (tDSM) in the stage of decision fusion. By doing so, aseamless map of undocumented buildings is generated for 1/4th of the state of Bavaria, Germany at a spatial resolution of 0.4 m,which has demonstrated the use of CNN for the robust detection of undocumented buildings at large-scale.

Item URL in elib:https://elib.dlr.de/138618/
Document Type:Conference or Workshop Item (Speech)
Title:Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Li, QingyuUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Shi, YileiUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Auer, StefanUNSPECIFIEDhttps://orcid.org/0000-0001-9310-2337UNSPECIFIED
Roschlaub, RobertBavarian Agency for Digitisation, High Speed Internet and Surveying, 80538 MünchenUNSPECIFIEDUNSPECIFIED
Moest, KarinBavarian Agency for Digitisation, High Speed Internet and Surveying, 80538 MünchenUNSPECIFIEDUNSPECIFIED
Schmitt, MichaelUNSPECIFIEDhttps://orcid.org/0000-0002-0575-2362UNSPECIFIED
Zhu, Xiao XiangUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:2020
Journal or Publication Title:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:V-2
DOI:10.5194/isprs-annals-V-2-2020-517-2020
Page Range:pp. 517-524
ISSN:2194-9042
Status:Published
Keywords:Building Detection, Convolutional Neural Network, Deep Learning, Semantic Segmentation, Decision Fusion
Event Title:ISPRS 2020
Event Location:Nice, France ONLINE
Event Type:international Conference
Event Start Date:31 August 2020
Event End Date:2 September 2020
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 - Vorhaben hochauflösende Fernerkundungsverfahren (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Li, Qingyu
Deposited On:03 Dec 2020 13:51
Last Modified:24 Apr 2024 20:40

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.