Assessment of driver’s distraction using perceptual evaluations, self assessments and multimodal feature analysis

Developing feedback systems that can detect the attention level of the driver can play a key role in preventing accidents by alerting the driver about possible hazardous situations. Monitoring driver’s distraction is an important research problem, especially with new forms of technology that are made available to drivers, which can interfere with the primary driving task. An important question is how to define reference labels that can be used as ground truth to train machine learning algorithms to detect distracted drivers. The answer to this question is not simple since drivers are affected by visual, cognitive, auditory, psychological and physical distractions. This paper explores and compares three different approaches to characterize driver’s distraction: perceptual evaluation from external evaluators, self evaluations collected from post driving questionnaires, and analysis of the differences observed across multimodal features from normal patterns.