Back to search

Carleton University

Methods for Classifying Driver Engagement in Autonomous Vehicles Using Physiological Sensors

Abstract

dc:description.abstract

Accurately measuring driver attention and tracking eye gaze in dynamic environments is crucial for advancing global road safety and the adoption of autonomous vehicles. Physiological sensors and machine learning models are employed to classify driver attention during real world autonomous and manual driving scenarios, demonstrating high accuracy identifying attentive drivers. Traditional gaze measurement techniques struggle with dynamic contexts, but advancements in deep learning offer promising solutions. This work introduces methods leveraging convolutional neural networks and transfer learning to enhance the segmentation of a driver's field of view into relevant areas, successfully segmenting thousands of video frames automatically. The automatic segmentation of video frames enabled the creation of novel gaze metrics. These innovations in gaze metrics further enhance the classification of driver attention with physiological metrics. Attention monitoring systems are crucial for ensuring safety and effective handover in semi-autonomous vehicles, offering substantial contributions to driver safety and attentiveness assessment methodologies.

Degree

thesis:*
Name thesis:degree_name
Master of Applied Science (M.App.Sc.)
Level thesis:degree_level
Master's
Discipline thesis:degree_discipline
Engineering, Electrical and Computer
Grantor dc:publisher
Carleton University
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Lochbihler, Aidan William

Subjects

dc:subject × 2

Rights

dc:rights
Statement dc:rights
  • Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
Language dc:language.iso
en

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Carleton University
Base URL
carleton.scholaris.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Lochbihler, Aidan William. Methods for Classifying Driver Engagement in Autonomous Vehicles Using Physiological Sensors. Master's thesis, Carleton University, 2024. https://hdl.handle.net/20.500.14718/43201