Co-training of context models for real-time object detection - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

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

Résumé

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.
Fichier principal
Vignette du fichier
gepperth2012.pdf (860.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00763676 , version 1 (11-12-2012)

Identifiants

  • HAL Id : hal-00763676 , version 1

Citer

Alexander Gepperth. Co-training of context models for real-time object detection. IEEE Symposium on Intelligent Vehicles, Jun 2012, Madrid, Spain. ⟨hal-00763676⟩
123 Consultations
306 Téléchargements

Partager

Gmail Facebook X LinkedIn More