Polygonization of Remote Sensing Classification Maps by Mesh Approximation

Emmanuel Maggiori 1 Yuliya Tarabalka 1 Guillaume Charpiat 2 Pierre Alliez 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
2 TAU - TAckling the Underspeficied
Inria Saclay - Ile de France
Abstract : The ultimate goal of land mapping from remote sensing image classification is to produce polygonal representations of Earth's objects, to be included in geographic information systems. This is most commonly performed by running a pix-elwise image classifier and then polygonizing the connected components in the classification map. We here propose a novel polygonization algorithm, which uses a labeled triangular mesh to approximate the input classification maps. The mesh is optimized in terms of an 1 norm with respect to the classifiers's output. We use a rich set of optimization operators , which includes a vertex relocator, and add a topology preservation strategy. The method outperforms current approaches , yielding better accuracy with fewer vertices.
Type de document :
Communication dans un congrès
ICIP 2017 - IEEE International Conference on Image Processing, Sep 2017, Beijing, China. pp.5
Liste complète des métadonnées

https://hal.inria.fr/hal-01530460
Contributeur : Emmanuel Maggiori <>
Soumis le : mercredi 31 mai 2017 - 17:40:26
Dernière modification le : mardi 21 novembre 2017 - 01:22:40
Document(s) archivé(s) le : mercredi 6 septembre 2017 - 17:32:07

Fichier

Maggiori_ICIP2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01530460, version 1

Collections

Citation

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez. Polygonization of Remote Sensing Classification Maps by Mesh Approximation. ICIP 2017 - IEEE International Conference on Image Processing, Sep 2017, Beijing, China. pp.5. 〈hal-01530460〉

Partager

Métriques

Consultations de la notice

181

Téléchargements de fichiers

99