A Novel Drive Status Monitoring System

This paper describes a novel drive status monitoring system. Two fixed cameras are used in the proposed system to capture the driver´s face image and the front road image to find the driver´s sight orientation, the lane path orientation, and the car heading direction, and these 3 orientation information are calculated for 2 correlation coefficients by using the soft-shape-context concept to indicate the driver´s steering control degrees. Three driving situations of the safe zone, risky zone, and unconscious zone are suggested according the combined coefficient of 2 correlation coefficients. This proposed system is capable to cooperate with other pre-crash systems based on the distance information to neighbor cars.