 |
ECOLE SUPÉRIEURE D'ÉLECTRICITÉ Une grande école d'ingénieurs au cœur des sciences de l'information,de l'énergie et des systèmes |
 |
Conference papers
Learning viewpoint planning in active recognition on a small sampling budget: a Kriging approach
Abstract : 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.
Cited literature [15 references]
https://hal-supelec.archives-ouvertes.fr/hal-00520814
Contributor : Julien Marzat Connect in order to contact the contributor
Submitted on : Thursday, September 8, 2011 - 10:09:35 AM
Last modification on : Thursday, June 17, 2021 - 3:46:30 AM
Long-term archiving on: : Tuesday, November 13, 2012 - 10:06:19 AM
Contributor : Julien Marzat Connect in order to contact the contributor
Submitted on : Thursday, September 8, 2011 - 10:09:35 AM
Last modification on : Thursday, June 17, 2021 - 3:46:30 AM
Long-term archiving on: : Tuesday, November 13, 2012 - 10:06:19 AM
File
DTIM1041.1291040181.pdf
Files produced by the author(s)