외부조명 변화를 고려한 운전자 졸음 감지 시스템

Abstract

Drowsy driving is the greatest part in the cause of car accidents, accounts for approximately 31% of car accidents that occurred on expressways for the last three years, and approximately 23% thereof resulted from failing to watch the road forward, causing casualties. The reason of drowsy driving to have a fatal impact on driving as described above is that it causes slow response speed and inaccurate decision making. It is thus necessary to develop a system for identifying the state of driver’s drowsiness and alerting the driver of drowsiness to avoid car accidents for preventing drowsy driving resulting in the aforementioned risks. Therefore, car manufacturers and government organizations have studied how to directly and indirectly obtain and analyze data about driver’s drowsiness to prevent accidents due to drowsy driving in advance. Exemplary technologies to analyze driver’s drowsiness include contacting driver’s body to measure signals, analyzing driver’s eyes, analyzing whether driver’s eyes are open or closed, and analyzing car’s movement to examine driver’s state as an indirect method. In this study, a system is proposed for analyzing whether driver’s eyes are open or closed on the basis of images to determine driver’s drowsiness. The proposed system converts eye areas detected by a camera to a color space area to effectively detect eyes in a dark situation, for example, tunnels, and a bright situation due to a backlight. In addition, the system used a thickness distribution of a detected eye area as a feature value to analyze whether eyes are open or closed through the Support Vector Machine(SVM), representing 90.09% of accuracy. In the experiment for the images of driver wearing glasses, 83.83% of accuracy was obtained. In addition, in a comparative experiment with the existing PCA method by using Eigen-eye and Pupil Measuring System the detection rate is shown improved. After the experiment, driver’s drowsiness was identified accurately by using the method of summing up the state of driver’s eyes open and closes over time and the method of detecting driver’s eyes that continue to be closed to examine drowsy driving.