Research On Driving Fatigue Detection Methods Based On Face Recognition

With the rapid development of economy and the rising number of vehicle, the rising trendof traffic accidents has brought great harm to people’s life and property safety. Driving fatigue isone of the major factors of traffic accidents. Thus the detection and control of traffic accidentscaused by driving fatigue is not only valuable in academy, but also important in social sense.In this thesis, driving fatigue detection methods are introduced firstly, and the feasibility andreliability of the driving fatigue detection based on face recognition are pointed out. Then thefront face images of three simulation drivers are collect as the experimental image data insimulated driving environment. Furthermore, the algorithms are designed for the processing andanalysis of the image data in the simulations, and the fatigue states of the drivers are detected.Concretely, the drivers’ faces are detected using AdaBoost algorithm first and the drivers’ eyesare located using template matching algorithm. Then the eye feature vector is extracted, and weput it into the support vector machine for classification. The experimental results show that theeyes’ discrimination using the combination of AdaBoost and template matching algorithmreaches around90%. The classification of the eyes states reaches over91%using support vectormachine. The driving fatigue states can be judged successfully. The experiments based on facerecognition are designed in this thesis, and the driving fatigue detection is bascially realized.