We present an automotive-grade, real-time, vision-based driver state monitor. Upon detecting and tracking the driver's facial features, the system analyzes eye-closures and head pose to infer his/her fatigue or distraction. This information is used to warn the driver and to modulate the actions of other safety systems. The purpose of this monitor is to increase road safety by preventing drivers from falling asleep or from being overly distracted, and to improve the effectiveness of other safety systems.

This article shows cutting-edge computer vision methods employed in advanced vision sensing technologies for medical, safety and security applications, where the human eye represents the object of interest for both the imager and the computer. As the eye scans the environment, or focuses on particular objects in the scene, the processor simultaneously localizes the eye position, tracks its position and movement over time, and infers counter measures such as fatigue level, attention level, and gaze direction in real-time and automatically. The focus of this demonstration is placed on four different algorithms: auto-initialization (RHED), eye position tracking (SIRAT), eye closure recognition (HRA), driver head pose categorization.