Real time and non-intrusive driver fatigue monitoring

This paper describes a real-time non-intrusive prototype driver fatigue monitor. It uses remotely located CCD cameras equipped with active IR illuminators to acquire video images of the driver. Various visual cues typically characterizing the alertness of the driver are extracted in real time and systematically combined to infer the fatigue level of the driver. The visual cues employed characterize the eyelid movement, gaze movement, head movement, and facial expression. A probabilistic model is developed to model human fatigue and to predict fatigue based on the observed visual cues and the available contextual information. The simultaneous use of multiple visual cues and their systematic combination yields a much more robust and accurate fatigue characterization than using a single visual cue. The feasibility of our system is demonstrated using the synthetic data. Further validation of our system under real life fatigue conditions with human subjects shows that it was reasonably robust, reliable and accurate in fatigue characterization.