Multi-region Data Segmentation on Surfaces

In this project, we address the problem of segmenting data defined on a manifold into a set of regions with uniform properties. In particular, we propose a numerical method when the manifold is represented by a triangular mesh. Based on recent image segmentation models, our method minimizes a convex energy and then enjoys significant favorable properties: it is robust to initialization and avoid the problem of the existence of local minima present in many variational models. The contributions of this paper are threefold: firstly we adapt the convex image labeling model to manifolds; in particular the total variation formulation. Secondly we show how to implement the proposed method on triangular meshes, and finally we show how to use and combine the method in other computer vision problems, such as 3D reconstruction. We demonstrate the efficiency of our method by testing it on various data.

 

Related Publications

Icone de Delaunoy-etal-iccv09.jpg
Titre
Convex Multi-Region Segmentation on Manifolds
Auteurs
Delaunoy Amael; Fundana Ketut; Prados Emmanuel url; Heyden Anders
Détail
IEEE. The 12th IEEE International Conference on Computer Vision, September 2009, Kyoto, Japan. IEEE, pp. 662 - 669
Accès au texte intégral et bibtex
Delaunoy-etal-iccv2009.pdf BibTex
Icone de rfia2010.jpg
Titre
Segmentation convexe multi-région de données sur les surfaces
Auteurs
Delaunoy Amael; Prados Emmanuel url; Fundana Ketut; Heyden Anders
Détail
17ème Congrès de Reconnaissance des Formes et Intelligence Artificielle, January 2010, Caen, France.
Accès au texte intégral et bibtex
dpfh-rfia-2010.pdf BibTex