Xu, Yajin und Schuegraf, Philipp und Bittner, Ksenia (2023) Vertex Aided Building Polygonization from Satellite Imagery Applying Deep Learning. In: 2023 Joint Urban Remote Sensing Event, JURSE 2023, Seiten 1-4. IEEE. JURSE 2023, 2023-05-17 - 2023-05-19, Heraklion Crete, Griechenland. doi: 10.1109/JURSE57346.2023.10144146. ISBN 978-166549373-4. ISSN 2642-9535.
PDF
2MB |
Offizielle URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10144146
Kurzfassung
Building extraction is an important task in many fields. The use of convolutional neural networks has been proven to be of great success in building extraction from satellite images. This paper presents a deep learning based vertex aided building polygonization method, which takes RGB satellite images as input and outputs building polygons. Unlike other methods which rely on vertex extraction followed by polygonization, our method requires neither pre-defined number of vertices nor thresholding to obtain extracted vertices. The proposed method has the advantage of simplicity in sense of model complexity, and achieved good performance with average precision of 48.1% and intersection over union of 84.1%.
elib-URL des Eintrags: | https://elib.dlr.de/195245/ | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Poster) | ||||||||||||||||
Titel: | Vertex Aided Building Polygonization from Satellite Imagery Applying Deep Learning | ||||||||||||||||
Autoren: |
| ||||||||||||||||
Datum: | 8 Juni 2023 | ||||||||||||||||
Erschienen in: | 2023 Joint Urban Remote Sensing Event, JURSE 2023 | ||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||
Open Access: | Ja | ||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||
DOI: | 10.1109/JURSE57346.2023.10144146 | ||||||||||||||||
Seitenbereich: | Seiten 1-4 | ||||||||||||||||
Verlag: | IEEE | ||||||||||||||||
ISSN: | 2642-9535 | ||||||||||||||||
ISBN: | 978-166549373-4 | ||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||
Stichwörter: | building vectorization, building extraction, pattern recognition, deep learning, AI4BuildingModeling | ||||||||||||||||
Veranstaltungstitel: | JURSE 2023 | ||||||||||||||||
Veranstaltungsort: | Heraklion Crete, Griechenland | ||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||
Veranstaltungsbeginn: | 17 Mai 2023 | ||||||||||||||||
Veranstaltungsende: | 19 Mai 2023 | ||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||
HGF - Programm: | Verkehr | ||||||||||||||||
HGF - Programmthema: | Straßenverkehr | ||||||||||||||||
DLR - Schwerpunkt: | Verkehr | ||||||||||||||||
DLR - Forschungsgebiet: | V ST Straßenverkehr | ||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | V - V&V4NGC - Methoden, Prozesse und Werkzeugketten für die Validierung & Verifikation von NGC, R - Optische Fernerkundung, D - Digitaler Atlas 2.0 | ||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||
Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > Photogrammetrie und Bildanalyse | ||||||||||||||||
Hinterlegt von: | Bittner, Ksenia | ||||||||||||||||
Hinterlegt am: | 22 Jun 2023 13:45 | ||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:55 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags