Fatigue Driving Detection Method Based On The Technology Of Eye Location

With the development of the automobile industry continuously, the social problems are more and more severe. The traffic accidents not only cause great harm to the people, but also bring heavy burden and effect to society. Because fatigue driving is a major reason that caused traffic accidents. Therefore, research a reasonable and effective real-time and non-contact device due to the detection of driver fatigue driving has great significance for reducing traffic accidents and raising road safety.This thesis focuses on the determination of fatigue based on face detection and eye location and eye tracking, complies a fatigue driving warning system base on the location of human eye, the algorithm consists of three main modules, the eye location algorithm, real-time tracking of the state of the human eye, the detection of eyes opened or closed and the algorithm of the determination of fatigue.The main work is followed.1.Elaborate the classic AdaBoost algorithm of face detection and eye location, including extraction of the haar-like features, image preprocessing, the creation of the AdaBoost classifier and building a complete solution system to the human face detection and the eye location.2. Use the Mean-shift algorithm to locate eyes, by building eye’s color and gray scale distribution to explain the eye, then achieve a algorithm that continuous detection and real-time tracking of eye.3. Comply the feature extraction and status analysis of eye. Detect and locate the inside and outside corners of the eye and find the position of the eyelid middle point. Then fit the contours of the upper eyelid curve, and calculate the distance between the eyelid middle point and the link between inside and outside corner to achieve quantitative analysis of eye state.4.Select PERCLOS which is recognized as the most effective fatigue driving measure and the eye blink frequency as the standard of determining driver fatigue, realize the analysis of driver fatigue.