Driver Attention Estimation Based on Temporal Sequence Classification of Distracting Contexts

Raluca Brehar, George Coblişan, Attila Füzes, Radu Dănescu

2023

Abstract

A framework for distracted driving level or the degree of attention which a driver pays to the act of driving, is presented in this paper. It uses visual based action recognition models applied on color images that capture the driver’s face and hands. The proposed approach contains a temporal sequence model that aggregates information from two object detectors which recognize distracting contexts generated by (1) distracting objects that appear in the images such as mobile devices and (2) the face orientation of the driver, the hands and their position with respect to the wheel. The driver’s attention score is predicted using the temporal sequence classification model, a long short term memory, that considers time series features computed based on object detection information.

Paper Citation

in Harvard Style

Brehar R., Coblişan G., Füzes A. and Dănescu R. (2023). Driver Attention Estimation Based on Temporal Sequence Classification of Distracting Contexts. In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-670-5, SciTePress, pages 578-585. DOI: 10.5220/0012160200003543

in Bibtex Style

@conference{icinco23,
author={Raluca Brehar and George Coblişan and Attila Füzes and Radu Dănescu},
title={Driver Attention Estimation Based on Temporal Sequence Classification of Distracting Contexts},
booktitle={Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2023},
pages={578-585},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012160200003543},
isbn={978-989-758-670-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Driver Attention Estimation Based on Temporal Sequence Classification of Distracting Contexts
SN - 978-989-758-670-5
AU - Brehar R.
AU - Coblişan G.
AU - Füzes A.
AU - Dănescu R.
PY - 2023
SP - 578
EP - 585
DO - 10.5220/0012160200003543
PB - SciTePress