| It is very important to detect driver's status and decrease accidence rate, especially in the vocational and occasions needed the operators with good mental status. Here ,the point is the car's drivers . In fact, driver fatigue is one of the chief causes of traffic accident. The determination of the fatigue standards and the recognition of the fatigue status are the most important problem to construct the fatigue detecting system.First of all, On the basis of the research of the foreign products and the comparison of recognition model it detected the face based on the face model method. In order to detect the eyes from the graph got by the campus, this thesis summarized and analysised the current algorithm firstly. It proposed physiological characteristics and template synthesis method to detect the eyes with better precise and speed. By comparison, the later one would avoid the effection from the change of the lightness. Furthermore, it is advanced for the following work.Secondly, it is necessary to keep trace of the eyes to get the states of the eyes in the next step. This thesis proposed Kalman method with template synthesis .You could get the broadly position of the eye by the Kalman filter and precise graph with the template.Thirdly, after detecting and tracking the eye feature, the next step is to recognize the eyes state. In this paper we put forward a method that can recognize the eyes state accurately from the parameters what are the time of the eyes close and the PERCLOS. In addition, this paper designed the system of drowsy detection based on the information of eye images based on the former theory.Contrast to the old method of driver fatigue detection on eye movement, the tracking speed and precision have been improved considerably. A serial of experiment have been implemented to verify the effection of the method supported by the papers, which can satisfied with the requisition of the real time system and have been more precisely. |
