Human and Vehicle-Driver Drowsiness Detection by Facial Expression

This paper presents the drowsiness detection method for using in vehicles. Our method is executed according to the following flow: taking a driver´s facial image, tracing the facial features by image processing, and classifying the driver´s drowsiness level by pattern classification. We found that facial expression had the highest linear correlation with brain waves as the general index of drowsiness during monotonous driving. We determined 17 feature points on face for detecting driver drowsiness, according to the facial muscle activities. Especially, we discovered that eyebrows rise caused by contraction of frontal is muscle was important feature to detect drowsiness during driving. A camera set on a dashboard recorded the driver´s facial image. We applied Active Appearance Model (AAM) for measuring the 3-dimensional coordinates of the feature points on the facial image. In order to classify drowsiness into 6 levels, we applied k-Nearest-Neighbor method. As a result, the average Root Mean Square Errors (RMSE) among 13 participants was less than 1.0 level. We added smile and speaking detection to our method as the first step of emotion detection.