Efficient Monte Carlo sampler for detecting parametric objects in large scenes

Yannick Verdie 1, 2 Florent Lafarge 1
1 GEOMETRICA - Geometric computing
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
Abstract : Point processes have demonstrated e fficiency and competitiveness when addressing object recognition problems in vision. However, simulating these mathematical models is a diffi cult task, especially on large scenes. Existing samplers suff er from average performances in terms of computation time and stability. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits Markovian properties of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism such that the points are non-uniformly distributed in the scene. The performances of the sampler are analyzed through a set of experiments on various object recognition problems from large scenes, and through comparisons to the existing algorithms.
Type de document :
Communication dans un congrès
ECCV 2012, Oct 2012, Firenze, Italy. Springer, 7574, pp.539-552, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33712-3_39〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00742770
Contributeur : Yannick Verdie <>
Soumis le : mercredi 17 octobre 2012 - 11:10:49
Dernière modification le : jeudi 11 janvier 2018 - 16:49:01
Document(s) archivé(s) le : vendredi 18 janvier 2013 - 03:45:03

Fichier

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

Identifiants

Collections

Citation

Yannick Verdie, Florent Lafarge. Efficient Monte Carlo sampler for detecting parametric objects in large scenes. ECCV 2012, Oct 2012, Firenze, Italy. Springer, 7574, pp.539-552, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33712-3_39〉. 〈hal-00742770〉

Partager

Métriques

Consultations de la notice

402

Téléchargements de fichiers

542