Abstract:According to the comparisons among those commonly used detecting and evaluating techniques for motor driver fatigue, the PERCLOS (percentage of eyelid closure over the pupil over time) is the most closely correlated with driver fatigue in the study of simulating driving instrument. Meanwhile, a feasible driver fatigue monitoring system design based on PERCLOS and DSP (digital signal processing) is presented and the drowsy driver detection system DDDS is developed. The methods of image difference, grey processing, erosion, dilation and so on are all used to locate the driver's eyes in the image and to detect the eyelid closure over the pupil over time to measure the driver fatigue degree. The results show that this scheme's veracity to detect driver fatigue is 86.89%.