Through an industry engagement PhD with Powerfleet®, this research explores the development of an innovative system for detecting alcohol intoxication in drivers using AI and machine learning applied to facial video data. The study introduces a pioneering dataset, the first to feature RGB video recordings of facial expressions at varying levels of alcohol intoxication during simulated driving. It aims to validate the feasibility of detecting intoxication through facial cues captured by standard cameras with an aim to create a cost-effective, reliable solution that eliminates the need for complex sensor-based systems, offering practical applications to enhance road safety.
Find more information: