Autonomous Vehicle Steering Wheel Estimation from a Video using Multichannel Convolutional Neural Networks

Arthur Emidio T. Ferreira, Ana Paula G. S. de Almeida, Flavio de Barros Vidal

2018

Abstract

The navigation technology in autonomous vehicles is an artificial intelligence application which remains unsolved and has been significantly explored by the automotive and technological industries. Many image processing and computer vision techniques allow significant improvements on such recent technologies. Using this motivation as a basis, this work proposes a novel methodology based on Multichannel Convolutional Neural Networks (M-CNN) capable of estimating the steering angle of an autonomous vehicle, having as only input images captured by a camera attached to the vehicle’s frontal area. We propose five Convolutional Neural Network architectures: 1-channel, 2-channel and 3-channel in the convolution step. Based on the performed tests using a public video dataset, it is presented a quantitative comparison between the proposed models.

Paper Citation

in Harvard Style

Ferreira A., Almeida A. and Vidal F. (2018). Autonomous Vehicle Steering Wheel Estimation from a Video using Multichannel Convolutional Neural Networks.In Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-758-321-6, pages 517-524. DOI: 10.5220/0006920605170524

in Bibtex Style

@conference{icinco18,
author={Arthur Emidio T. Ferreira and Ana Paula G. S. de Almeida and Flavio de Barros Vidal},
title={Autonomous Vehicle Steering Wheel Estimation from a Video using Multichannel Convolutional Neural Networks},
booktitle={Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2018},
pages={517-524},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006920605170524},
isbn={978-989-758-321-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Autonomous Vehicle Steering Wheel Estimation from a Video using Multichannel Convolutional Neural Networks
SN - 978-989-758-321-6
AU - Ferreira A.
AU - Almeida A.
AU - Vidal F.
PY - 2018
SP - 517
EP - 524
DO - 10.5220/0006920605170524