Road Detection using Convolutional Neural Networks

Aparajit Narayan, Elio Tuci, Frédéric Labrosse, Muhanad H. Mohammed Alkilabi

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddTrafodion Cynhadledd (Nid-Cyfnodolyn fathau)


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.

Iaith wreiddiolSaesneg
TeitlProceedings of the 14th European Conference on Artificial Life, ECAL 2017
CyhoeddwrMIT Press Journals
Nifer y tudalennau8
ISBN (Electronig)9780262346337
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 2017
Digwyddiad14th European Conference on Artificial Life, ECAL 2017 - Lyon, Ffrainc
Hyd: 04 Medi 201708 Medi 2017

Cyfres gyhoeddiadau

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


Cynhadledd14th European Conference on Artificial Life, ECAL 2017
Cyfnod04 Medi 201708 Medi 2017

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Road Detection using Convolutional Neural Networks'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn