Semantic Segmentation of 3D Textured Meshes for Urban Scene Analysis

Mohammad Rouhani 1 Florent Lafarge 1 Pierre Alliez 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Classifying 3D measurement data has become a core problem in photogram-metry and 3D computer vision, since the rise of modern multiview geometry techniques, combined with affordable range sensors. We introduce a Markov Random Field-based approach for segmenting textured meshes generated via multi-view stereo into urban classes of interest. The input mesh is first partitioned into small clusters, referred to as superfacets, from which geometric and photometric features are computed. A random forest is then trained to predict the class of each superfacet as well as its similarity with the neighboring superfacets. Similarity is used to assign the weights of the Markov Random Field pairwise-potential and accounts for contextual information between the classes. The experimental results illustrate the efficacy and accuracy of the proposed framework.
Type de document :
Article dans une revue
ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, 2017, 123, pp.124 - 139. 〈10.1016/j.isprsjprs.2016.12.001〉
Liste complète des métadonnées

Littérature citée [45 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01469502
Contributeur : Florent Lafarge <>
Soumis le : jeudi 16 février 2017 - 15:03:43
Dernière modification le : jeudi 11 janvier 2018 - 15:51:37
Document(s) archivé(s) le : mercredi 17 mai 2017 - 18:33:03

Fichiers

JPRS_2017_Rouhani.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Mohammad Rouhani, Florent Lafarge, Pierre Alliez. Semantic Segmentation of 3D Textured Meshes for Urban Scene Analysis. ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, 2017, 123, pp.124 - 139. 〈10.1016/j.isprsjprs.2016.12.001〉. 〈hal-01469502〉

Partager

Métriques

Consultations de la notice

966

Téléchargements de fichiers

1741