Road Singularities Detection and Classification

Ana Paula Leitao (1) , Sorin Tilie (1) , Morgan Mangeas (1) , Jean-Philippe Tarel (1) , Vincent Vigneron (2) , Sylvie Lelandais (2)

1 LIVIC - Laboratoire sur les Interactions Véhicules-Infrastructure-Conducteurs
2 LSC - Laboratoire Systèmes Complexes

We propose a detection and classification system for various road situations, which is robust to light changes and different road markings. The road curves in an image are described with a Hough Transform, where histograms accumulate the contrast lines for each pixel. The resulting 2D histograms are used to train a Kohonen Neural Network. The final output classification can be used to improve road security, indicating dangerous situations to the driver or feeding a driving control system.

Mots clés: neural network selection; robust estimator; Bootstrap

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Ana Paula Leitao, Sorin Tilie, Morgan Mangeas, Jean-Philippe Tarel, Vincent Vigneron, et al.. Road Singularities Detection and Classification. 11th European Symposium on Artificial Neural Networks, Apr 2001, Bruges, Belgium. 6 p. ⟨hal-00147407⟩