Exploration Strategies for Incremental Learning of Object-Based Visual Saliency - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Exploration Strategies for Incremental Learning of Object-Based Visual Saliency

Résumé

Searching for objects in an indoor environment can be drastically improved if a task-specific visual saliency is available. We describe a method to learn such an object-based visual saliency in an intrinsically motivated way using an environment exploration mechanism. We first define saliency in a geometrical manner and use this definition to discover salient elements given an attentive but costly observation of the environment. These elements are used to train a fast classifier that predicts salient objects given large-scale visual features. In order to get a better and faster learning, we use intrinsic motivation to drive our observation selection, based on uncertainty and novelty detection. Our approach has been tested on RGB-D images, is real-time, and outperforms several state-of-the-art methods in the case of indoor object detection.
Fichier principal
Vignette du fichier
ICDL_celine_craye_final.pdf (1.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01170532 , version 1 (01-07-2015)

Identifiants

  • HAL Id : hal-01170532 , version 1

Citer

Céline Craye, David Filliat, Jean-François Goudou. Exploration Strategies for Incremental Learning of Object-Based Visual Saliency. Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Aug 2015, Providence, United States. ⟨hal-01170532⟩
127 Consultations
317 Téléchargements

Partager

Gmail Facebook X LinkedIn More