Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach

Résumé

This paper focuses on viewpoint planning for 3D active object recognition. The objective is to design a planning policy into a Q-learning framework with a limited number of samples. Most existing stochastic techniques are therefore inapplicable. We propose to use Kriging and Bayesian Optimization coupled with Q-learning to obtain a computationally-efficient viewpoint-planning design, under a restrictive sampling budget. Experimental results on a representative database, including a comparison with classical approaches, show promising results for this strategy.
Fichier principal
Vignette du fichier
DTIM1041.1291040181.pdf (1.57 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00520814 , version 1 (08-09-2011)

Identifiants

  • HAL Id : hal-00520814 , version 1

Citer

Joseph Defretin, Julien Marzat, Hélène Piet-Lahanier. Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach. 9th IEEE Conference on Machine Learning and Applications, ICMLA 2010, Dec 2010, Washington, D.C., United States. pp.169-174. ⟨hal-00520814⟩
255 Consultations
284 Téléchargements

Partager

Gmail Facebook X LinkedIn More