Research Of Driver's Fatigue State Real-Time Detection Based On Non-Contact Meathod

Driving in case of drowse is a most important factor of traffic accidents. And Studying out a method of driver's fatigue detection has a good prospect of engineering application and alarm device.Supported by Biometric Identification Technology and Machine Vision, this article starts from a consideration of Physiological Characteristics, gives the quantitative grades to the degree of driver's fatigue. We detect the degree of fatigue by driver's eye State. And then gives the alarm. At the same time, we design and build the system of driver's fatigue state detection.Video library of deliver's fatigue with multiple light environment and mental statement is set up first. Then we built the model of the quantitative grades to driver's fatigue through the analysis of the video library. After process the frame of the video, this article Combines the space land characteristic of the internal form of human eye, the Pseudo-Zernike moments of the land varied characteristic of the internal form of human eye, the technology of template matched, and using the sorter with the lattice degree of nearness to judge the eye state. And information fusion with perclos, aecf, tclose, topen, dutycycle, aeccov is used for the judgment of driver's fatigue. Finally, the system gives the alarm corresponding with the rank of drive's fatigue. Corresponding parameter is saved if needed.Many tests show that the system can detect blinking times and visible pupil area in real time. So it can detect the degree of fatigue efficaciously. The system can also give the alarm corresponding with the rank of drive's fatigue and the velocity can also meets the demands of the video's information processing.