Detecting parametric objects in large scenes by Monte Carlo sampling

Yannick Verdie 1 Florent Lafarge 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Point processes constitute a natural extension of Markov Random Fields (MRF), designed to handle parametric objects. They have shown efficiency and competitiveness for tackling object extraction problems in vision. Simulating these stochastic models is however a difficult task. The performances of the existing samplers are limited in terms of computation time and convergence stability, especially on large scenes. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits the Markovian property of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism so that the points are distributed in the scene in function of spatial information extracted from the input data. The performances of the sampler are analyzed through a set of experiments on various object detection problems from large scenes, including comparisons to the existing algorithms. The sampler is also tested as optimization algorithm for MRF-based labeling problems.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2014, 106 (1), pp.57-75. 〈10.1007/s11263-013-0641-0〉
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00843022
Contributeur : Florent Lafarge <>
Soumis le : mercredi 10 juillet 2013 - 10:47:27
Dernière modification le : jeudi 11 janvier 2018 - 16:17:42
Document(s) archivé(s) le : vendredi 11 octobre 2013 - 04:21:46

Fichiers

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

Identifiants

Collections

Citation

Yannick Verdie, Florent Lafarge. Detecting parametric objects in large scenes by Monte Carlo sampling. International Journal of Computer Vision, Springer Verlag, 2014, 106 (1), pp.57-75. 〈10.1007/s11263-013-0641-0〉. 〈hal-00843022〉

Partager

Métriques

Consultations de la notice

445

Téléchargements de fichiers

5010