Road Detection Using Convolutional Neural Networks

Aparajit Narayan, Elio Tuci, Frédéric Labrosse, Muhanad Hayder Mohammed Alkilabi

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

Abstract

The work presented in this paper aims to address the problem of autonomous driving (especially along ill-defined roads) by using convolutional neural networks to predict the position and width of roads from camera input images. The networks are trained with supervised learning (i.e., back-propagation) using a dataset of annotated road images. We train two different network architectures for images corresponding to six colour models. They are tested “off-line” on a road detection task using image sequences not used in training. To benchmark our approach, we compare the performance of our networks with that of a different image processing method that relies on differences in colour distribution between the road and non-road areas of the camera input. Finally, we use a trained convolutional network to successfully navigate a Pioneer 3-AT robot on 5 distinct test paths. Results show that the network can safely guide the robot in this navigation task and that it is robust enough to deal with circumstances much different from those encountered during training.

Original languageEnglish
Title of host publicationProceedings of the 14th European Conference on Artificial Life, ECAL 2017
EditorsCarole Knibbe, Guillaume Beslon, David P. Parsons, Dusan Misevic, Jonathan Rouzaud-Cornabas, Nicolas Bredèche, Salima Hassas, Olivier Simonin, Hédi Soula
PublisherMIT Press
Pages314 - 321
Number of pages8
ISBN (Electronic)9780262346337
ISBN (Print)978-0-262-34633-7
Publication statusPublished - 2017
Externally publishedYes

Publication series

NameProceedings of the 14th European Conference on Artificial Life, ECAL 2017

Fingerprint

Dive into the research topics of 'Road Detection Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this