Machine-learned 3D building vectorization from satellite imagery

Yi Wang, Stefano Zorzi, Ksenia Bittner

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. Taking a single-channel photogrammetric digital surface model (DSM) and a panchromatic (PAN) image as input, we first filter out non-building objects and refine the building shapes of the input DSM with a conditional generative adversarial network (cGAN). The refined DSM and the input PAN image are then used through a semantic segmentation network to detect edges and corners of building roofs. Later, a set of vectorization algorithms are proposed to build roof polygons. Finally, the height information from refined DSM is processed and added to the polygons to obtain a fully vectorized level of detail (LoD)-2 building model. We verify the effectiveness of our method on large-scale satellite images, where we obtain state-of-the-art performance.

Originalspracheenglisch
TitelProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Herausgeber (Verlag)IEEE Computer Society
Seiten1072-1081
Seitenumfang10
ISBN (elektronisch)9781665448994
DOIs
PublikationsstatusVeröffentlicht - Juni 2021
Veranstaltung2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2021 - Virtuell, USA / Vereinigte Staaten
Dauer: 19 Juni 202125 Juni 2021

Publikationsreihe

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (elektronisch)2160-7516

Konferenz

Konferenz2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
KurztitelCVPRW 2021
Land/GebietUSA / Vereinigte Staaten
OrtVirtuell
Zeitraum19/06/2125/06/21

ASJC Scopus subject areas

  • Maschinelles Sehen und Mustererkennung
  • Elektrotechnik und Elektronik

Dieses zitieren