Detection Of Fatigue Driving Based On Face Detection

With the development of society,motor vehicles increase quickly. Motor driver fatigue is increasingly reported as a problem concerning the road traffic safety. According to the transport sector statistics, our country is the fn’st that the highest number of deaths in road traffic accidents has been for several years in the world. Drivers’ fatigue driving is one of major cause oftraffic accidents. Therefore, it’s important to research on methods whichcall effectively detect the state ofdriver fatigue. Although there are some simple driving fatigue detection methods, but with the vehicle, non-contact,real-time driver fatigue monitoring methodology have not yet been resolved satisfactorily.In order to ensure the timeliness and reliability of driver fatigue detection system, combined with the most effective method for fatigue detection PERCLOS, this article is designed based on face detection driver fatigue detection system, mainly to complete the following work:1.Driver driving the process affected the light, angle, motion state and other factors, the traditional face and eye detection error rate is high, and the complex mix of real-time detection technology is poor. To solve this problem, we propose a suitable driver’s face detection and tracking algorithm to quickly locate the eyes, the method from coarse to fine, the integrated use of OpenCV-based face recognition, improved gray integral projection, Susan operator corner Detection and Kalman filter tracking technology, completed quickly locate the driver eye tracking.2. Analysis of the current method PERCLOS related fatigue detection based on the principle of combining PERCLOS, raised the percentage of black pixels in the eye area fatigue detection method based on real-time than the existing methods and accuracy are improved.3.Simulation and real-time detection through on-site combination of a comprehensive analysis of the system, taking into account the practicality of fatigue driving system, a brief introduction of DSP-based driver fatigue detection system and make the next step to continue to study and solve problems.