DIME
Full title: Driver Impairment Multimodal Evaluation
The Driver Impairment Multimodal Evaluation (DIME) project addresses the challenge of identifying intoxication, particularly when drivers attempt to conceal it. This will be achieved through creating an advanced multi-modal system, designed for commercial deployment by 2028. For this, the University of Gothenburg and Smart Eye, in close collaboration, will leverage deep learning techniques to develop Smart Eye’s Driver Monitoring System to combine: i) in-cabin driver behavior; ii) intoxication-related speech patterns; and iii) biobehavioral measures for automated detection of intoxicated states in drivers.
Traffic safety benefit: Vision Zero – reduced accidents by 2028; Sustainability – fewer (unsafe) drivers on the road
Key words: Intoxication, driver impairment, multi-modal detection, speech pattern detection.
