Road rage detection algorithm based on fatigue driving and facial feature point location

In order to monitor whether a driver is tired or prone to road rage in real time and avoid some traffic accidents, a real-time detection method of driver's facial expression based on the facial feature point location is proposed. First, we use the AdaBoost face detection algorithm based on Haar characteristics to detect the presence of a face and use the face feature point localization algorithm to obtain the required face feature points. Then, the value of eye aspect ratio is calculated according to the feature point data of the face-eye region, which indicates the opening degree of eyes. The driver is detected whether he (she) is in fatigue driving according to the appropriate threshold. We improve the detection method of fatigue driving and apply it to the road rage detection algorithm. We first propose the ratios of the brow-eye distance and mouth closure (RBEM) as indicators to determine whether the driver has road rage characteristics. Experimental results verify the effectiveness of the method.