A new approach for robust road marking detection and tracking applied to multi-lane estimation

Abstract : In this paper, an original and inovative algorithm for multi-lane detection and estimation is proposed. Based on a three-step process, (1) road primitives extraction, (2) road markings detection and tracking, (3) lanes detection and estimation. This algorithm combines several advantages at each processing level and is quite robust to the extraction method and more specifically to the choice of the extraction threshold. The detection step is so efficient, by using robust poly-fitting based on the point intensity of extracted points, that correction step is almost not necessary anymore. This approach has been used in several project in real condition and its performances have been evaluated with the sensor data generated from SiVIC platform. This validation stage has been done with more than 2500 simulated and realistic images. . Results are very encouraging : more than 95% of marking lines are detected for less than 2% of false alarm, with 3 cm accuracy at a range of 60 m.
Type de document :
Communication dans un congrès
The 2013 IEEE Intelligent Vehicles Symposium, Jun 2013, Gold Coast, Australia. IEEE, pp.783 - 790, 2013, 〈10.1109/IVS.2013.6629562〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00917002
Contributeur : Evangeline Pollard <>
Soumis le : mercredi 11 décembre 2013 - 10:21:53
Dernière modification le : vendredi 25 mai 2018 - 12:02:03
Document(s) archivé(s) le : mercredi 12 mars 2014 - 02:10:14

Fichier

IV2013_0188_FI.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Marc Revilloud, Dominique Gruyer, Evangeline Pollard. A new approach for robust road marking detection and tracking applied to multi-lane estimation. The 2013 IEEE Intelligent Vehicles Symposium, Jun 2013, Gold Coast, Australia. IEEE, pp.783 - 790, 2013, 〈10.1109/IVS.2013.6629562〉. 〈hal-00917002〉

Partager

Métriques

Consultations de la notice

467

Téléchargements de fichiers

1203