elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata

Li, Qingyu und Shi, Yilei und Auer, Stefan und Roschlaub, Robert und Moest, Karin und Schmitt, Michael und 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, Seiten 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

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

Kurzfassung

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.

elib-URL des Eintrags:https://elib.dlr.de/138618/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Detection of Undocumented Buildings using Convolutional Neural Network and Official Geodata
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Li, QingyuQingyu.Li (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Shi, Yileiyilei.shi (at) tum.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Auer, StefanStefan.Auer (at) dlr.dehttps://orcid.org/0000-0001-9310-2337NICHT SPEZIFIZIERT
Roschlaub, RobertBavarian Agency for Digitisation, High Speed Internet and Surveying, 80538 MünchenNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Moest, KarinBavarian Agency for Digitisation, High Speed Internet and Surveying, 80538 MünchenNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Schmitt, Michaelm.schmitt (at) tum.dehttps://orcid.org/0000-0002-0575-2362NICHT SPEZIFIZIERT
Zhu, Xiao Xiangxiao.zhu (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:2020
Erschienen in:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
Band:V-2
DOI:10.5194/isprs-annals-V-2-2020-517-2020
Seitenbereich:Seiten 517-524
ISSN:2194-9042
Status:veröffentlicht
Stichwörter:Building Detection, Convolutional Neural Network, Deep Learning, Semantic Segmentation, Decision Fusion
Veranstaltungstitel:ISPRS 2020
Veranstaltungsort:Nice, France ONLINE
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:31 August 2020
Veranstaltungsende:2 September 2020
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Vorhaben hochauflösende Fernerkundungsverfahren (alt)
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > EO Data Science
Institut für Methodik der Fernerkundung > Photogrammetrie und Bildanalyse
Hinterlegt von: Li, Qingyu
Hinterlegt am:03 Dez 2020 13:51
Letzte Änderung:24 Apr 2024 20:40

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.