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 Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
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.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01530460
Contributor : Emmanuel Maggiori <>
Submitted on : Wednesday, May 31, 2017 - 5:40:26 PM
Last modification on : Thursday, February 7, 2019 - 3:04:51 PM
Long-term archiving on : Wednesday, September 6, 2017 - 5:32:07 PM

File

Maggiori_ICIP2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01530460, version 1

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⟩

Share

Metrics

Record views

585

Files downloads

372