Commercial motor vehicle driver impairment due to drowsiness is known to be a major contributing factor in many crashes. This report details the steps taken to develop a prototype driver drowsiness monitoring system (DDMS). The first area of consideration was the basic design requirements that would pertain to all driver drowsiness monitors, such as the ideal functional specifications that designers and engineers would account for in the development of drowsy monitor designs. Next, the project reviewed salient driver-based and vehicle-based predictors of driver drowsiness based on a literature review and an analysis of data from two recent naturalistic commercial driving studies. The development of a prototype DDMS included the integration of a machine vision (MV) eye closure sensor and an MV lane position sensor. The operational performance of the prototype DDMS was assessed during a dynamic on-road evaluation under varying conditions of ambient illumination, eyewear, and skin complexion. This evaluation assessed the performance of the MV eye closure sensor, the MV lane position sensor, and the integrated prototype DDMS algorithms. The key finding of the on-road evaluation is that the multiple sensors integrated approach is necessary. The project provided seven recommendations to improve the operational performance of these sensors and topics for future DDMS development. As with any technology assessment, this evaluation was based on current state-of-the-art technology. As technology development efforts continue, performance of the sensors would be expected to improve. Therefore, the results presented here represent a single snapshot in time. (Author/publisher)
Abstract