Date of Award
2025
Document Type
Thesis
Publisher
Edith Cowan University
Degree Name
Doctor of Philosophy
School
School of Science
First Supervisor
Zulqarnain Gilani
Second Supervisor
David Suter
Abstract
This thesis investigates different approaches for detecting alcohol intoxication in drivers by analysing facial video data. Tackling this issue necessitates the creation of a novel dataset to overcome the limitations of existing datasets. The dataset constructed in this study is the first to include RGB video recordings of individual faces at varying levels of alcohol intoxication during simulated driving, featuring 60 participants with BAC levels ranging from 0 to 0.165 g/100ml. The constructed dataset not only supports this thesis, but also offers the broader scientific community a valuable resource for further study and development.
Building on this, this thesis presents a ‘proof of concept’ to validate the feasibility of detecting alcohol intoxication through analysis of facial cues captured by standard RGB cameras. Additionally, the author investigates methods to enhance detection accuracy and to create a more reliable system for real-world use by employing both handcrafted feature engineering and end-to-end deep learning techniques. To the best of the author’s knowledge, this thesis constitutes the first proposition of an alcohol detection system that relies exclusively on facial cues within RGB video footage. This approach holds significant promise for: improving road safety; eliminating the need for expensive and complex sensor-based technologies; and offering a more practical solution for real-world application.
DOI
10.25958/dt0p-3d85
Recommended Citation
Keshtkaran, E. (2025). Automated methods for estimating blood alcohol concentration level from facial cues. Edith Cowan University. https://doi.org/10.25958/dt0p-3d85
