Research On Driver Fatigue Detection Technology Based On Computer Vision

With the rapid development of transport, the traffic safety has become an important issue be commonly concerned on a global scale. However, each year the figure of people killed in traffic accidents is remaining obstinately high, and all kinds of vicious traffic accidents are still occur. Study shows that most of them are caused by the drivers'fatigue, so driver fatigue has become a hazard to personal safety. Therefore, the study and design of safety assist systems specific to driver fatigue driving attracted much attention of researchers, and become a hotspot all over the world.For the problem, the paper select the computer vision as the judgment method to detect whether the occurrence of driver fatigue by recognition the state of eye and lip of the driver and give timely warning. The main work done in this paper is as follows:Firstly, a method of face detection based on skin color model is presented. On the basis of the common color space , this paper research a new color space YCgCb which has better color clustering effect. In the color space this paper constructs the Gaussian complexion model to collect skin color. Potent factor of face judgment is introduced to further removing non-face regions in the skin color segmentation results, so the searching regions for face detection reduce and the face is located at last.Secondly, in the process of locating and tracking eye uses detection of one eye. The area of interest for eye location is established in the face region. With the help of horizontal projection in gray image and vertical projection in binary image to locate the eye position efficiently and accurately. By analyzing the traditional Mean Shift algorithm, the texture features of Harris corner and the color features are combined with together effectively to describe the human eye and embedded Mean Shift algorithm for realizing eye tracking.Finally, by using the number of black pixels in binary image of the eye to determine the status of the eye, next the lip is detected according to the lips color, and the state of mouth is described by the aspect ratio of the lip. In order to make the algorithm more valid, we combined PERCLOS with yawning detection to detect driver's drowsy state, if yawning is detected at the same time, the driver will be judged to fatigue. Experimental results show that the proposed algorithm is effective and feasible, and robust to variations of background, illumination and pose.