A novel information fusion based FTT algorithm for a driver fatigue monitoring system

This paper presents a novel feature triangle tracking (FTT) algorithm to track the eyes, mouth and head gestures of a fatigued driver. The proposed method uses the motion information to localise the face region at an YCrCb colour space to determine the locations of eyes and mouth. According to geometrical relationships of facial components and various head gestures of a driver, the system derives from both the isosceles feature triangle and the right feature triangle. The FTT algorithm effectively removes the confusing triangle from the tracking of the video sequence. The experimental results show that the proposed algorithm precisely tracks the various head gestures of a fatigued driver in real-time video frames.