Co-training of context models for real-time object detection

Alexander Gepperth 1, *
* Auteur correspondant
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : We describe a simple way to reduce the amount of required training data in context-based models of real- time object detection. We demonstrate the feasibility of our approach in a very challenging vehicle detection scenario comprising multiple weather, environment and light conditions such as rain, snow and darkness (night). The investigation is based on a real-time detection system effectively composed of two trainable components: an exhaustive multiscale object detector ("signal-driven detection"), as well as a module for generating object-specific visual attention ("context models") controlling the signal-driven detection process. Both parts of the system require a significant amount of ground-truth data which need to be generated by human annotation in a time-consuming and costly process. Assuming sufficient training examples for signal-based detection, we demonstrate that a co-training step can eliminate the need for separate ground-truth data to train context models. This is achieved by directly training context models with the results of signal-driven detection. We show that this process is feasible for different qualities of signal-driven detection, and maintains the performance gains from context models. As it is by now widely accepted that signal-driven object detection can be significantly improved by context models, our method allows to train strongly improved detection systems without additional labor, and above all, cost.
Type de document :
Communication dans un congrès
IEEE Symposium on Intelligent Vehicles, Jun 2012, Madrid, Spain. 2012
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00763676
Contributeur : Alexander Gepperth <>
Soumis le : mardi 11 décembre 2012 - 11:46:30
Dernière modification le : jeudi 16 novembre 2017 - 17:12:03
Document(s) archivé(s) le : mardi 12 mars 2013 - 04:35:08

Fichier

gepperth2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00763676, version 1

Collections

Citation

Alexander Gepperth. Co-training of context models for real-time object detection. IEEE Symposium on Intelligent Vehicles, Jun 2012, Madrid, Spain. 2012. 〈hal-00763676〉

Partager

Métriques

Consultations de la notice

275

Téléchargements de fichiers

136