Driver Fatigue Detection System Based on Eye Movements

Abstract

Driver fatigue is a hazard which can easily lead to traffic accidents. To detect driver fatigue in real time, a novel fatigue detection system using support vector machine (SVM) based on eye movements is proposed. Eye movement data was collected using the SmartEye system in a driving simulator experiment. Characteristic parameters which include blinking frequency, gaze direction, fixation time and PERCLOS were extracted based on the data using statistical method. The characteristic parameters were used to train and test SVM model. Experimental results show that this system achieves a satisfied performance, which demonstrate that eye movements can be used to detect driver fatigue in real time.