Combining adaBoost with a Hill-Climbing evolutionary feature search for efficient training of performant visual object detector - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Combining adaBoost with a Hill-Climbing evolutionary feature search for efficient training of performant visual object detector

Fabien Moutarde
Bogdan Stanciulescu
Bruno Steux
  • Fonction : Auteur
  • PersonId : 955111

Résumé

This paper presents an efficient method for automatic training of performant visual object detectors, and its successful application to training of a back-view car detec- tor. Our method for training detectors is adaBoost applied to a very general family of visual features (called “control-point” features), with a specific feature-selection weak-learner: evo-HC, which is a hybrid of Hill-Climbing and evolutionary-search. Very good results are obtained for the car-detection application: 95% positive car detection rate with less than one false positive per image frame, computed on an independant validation video. It is also shown that our original hybrid evo-HC weak-learner allows to obtain detection performances that are unreachable in rea- sonable training time with a crude random search. Finally our method seems to be potentially efficient for training detectors of very different kinds of objects, as it was already previously shown to provide state-of-art performance for pedestrian-detection tasks.
Fichier principal
Vignette du fichier
evoHC-Boost_FLINS06.pdf (428.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00435700 , version 1 (24-11-2009)

Identifiants

  • HAL Id : hal-00435700 , version 1

Citer

Yotam Abramson, Fabien Moutarde, Bogdan Stanciulescu, Bruno Steux. Combining adaBoost with a Hill-Climbing evolutionary feature search for efficient training of performant visual object detector. FLINS2006 on Applied Artificial Intelligence, Aug 2006, Genova, Italy. ⟨hal-00435700⟩
107 Consultations
179 Téléchargements

Partager

Gmail Facebook X LinkedIn More