Improving pan-European speed-limit signs recognition with a new “global number segmentation” before digit recognition

Abstract : In this paper, we present an improved European speed-limit sign recognition system based on an original “global number segmentation” (inside detected circles) before digit segmentation and recognition. The global speed-limit sign detection and correct recognition rate, currently evaluated on videos recorded on a mix of French and German roads, is around 94 %, with a misclassification rate below 1%, and not a single validated false alarm in several hours of recorded videos. Our greyscale-based system is intrinsically insensitive to colour variability and quite robust to illumination variations, as shown by an on-road evaluation under bad weather conditions (cloudy and rainy) which yielded 84% good detection and recognition rate, and by a first night-time on-road evaluation with 75% correct detection rate. Due to recognition occurring at digit level, our system has the potential to be very easily extended to handle properly all variants of speed-limit signs from various European countries. Regarding computation load, videos with images of 640x480 pixels can be processed in real-time at ~20frames/s on a standard 2.13GHz dual-core laptop.
Type de document :
Communication dans un congrès
IEEE Intelligent Vehicles Symposium (IV'08), Jun 2008, Eindhoven, Netherlands. 2008
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00320003
Contributeur : Fabien Moutarde <>
Soumis le : mercredi 10 septembre 2008 - 21:02:35
Dernière modification le : jeudi 2 août 2018 - 12:02:05
Document(s) archivé(s) le : vendredi 4 juin 2010 - 11:09:40

Fichier

sls_IV2008.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00320003, version 1

Collections

Citation

Alexandre Bargeton, Fabien Moutarde, Fawzi Nashashibi, Benazouz Bradai. Improving pan-European speed-limit signs recognition with a new “global number segmentation” before digit recognition. IEEE Intelligent Vehicles Symposium (IV'08), Jun 2008, Eindhoven, Netherlands. 2008. 〈inria-00320003〉

Partager

Métriques

Consultations de la notice

443

Téléchargements de fichiers

264