Polygonal Building Segmentation by Frame Field Learning - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Polygonal Building Segmentation by Frame Field Learning

Résumé

While state of the art image segmentation models typically output segmentations in raster format, applications in geographic information systems often require vector polygons. We propose adding a frame field output to a deep image segmentation model for extracting buildings from remote sensing images. This improves segmentation quality and provides structural information, facilitating more accurate polygonization. To this end, we train a deep neural network, which aligns a predicted frame field to ground truth contour data. In addition to increasing performance by leveraging multi-task learning, our method produces more regular segmentations. We also introduce a new polygonization algorithm, which is guided by the frame field corresponding to the raster segmentation.
Fichier principal
Vignette du fichier
archive.pdf (10.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02548545 , version 1 (27-04-2020)
hal-02548545 , version 2 (31-03-2021)

Identifiants

  • HAL Id : hal-02548545 , version 1

Citer

Nicolas Girard, Dmitriy Smirnov, Justin Solomon, Yuliya Tarabalka. Polygonal Building Segmentation by Frame Field Learning. 2020. ⟨hal-02548545v1⟩

Collections

OPAL
356 Consultations
390 Téléchargements

Partager

Gmail Facebook X LinkedIn More