Embedded computer vision detection fatigue driving method and device

Abstract

The invention discloses an embedded computer vision detection fatigue driving method. The method includes shooting a head picture of a driver, and carrying out face recognition and tracking; carryingout key point positioning, recording the feature points of eyes and mouth, and converting the feature points into a two-dimensional array, calculating the aspect ratio of the eyes and the mouth through a formula; according to the characteristics of different drivers' eyes, setting an aspect ratio threshold value of the eyes and the mouth, the frame aspect ratio threshold value of blinking generated by the condition that the continuous length-to-width ratio is smaller than the threshold value, and the frames of yawning generated by the condition that the continuous length-to-width ratio is greater than the threshold value; comparing the blinking times in a certain period with a normal standard value, and combining the yawning times, determining whether the driver is in the fatigue state, ifyes, starting a voice alarm device to carry out the voice prompt. The infrared night vision camera is adopted, and a picture can be shot clearly at night. The method is simple in step, high in operability, simple in device, convenient to install and carry and capable of realizing good fatigue driving detection.

Description

technical field [0001] The invention belongs to the technical field of fatigue driving detection, and in particular relates to an embedded computer vision detection method and device for fatigue driving. Background technique [0002] With the discovery of the automobile industry, cars have become the most commonly used means of transportation for people, and in the process of daily driving, we often encounter situations such as too little sleep time and poor sleep quality the day before. When driving, the bumps of the vehicle itself and the noise outside the vehicle can easily cause the driver's fatigue, thereby causing traffic accidents. At present, in many cars, many fatigue monitoring systems have been developed and used. The fatigue monitoring system equipped by Volkswagen is a fatigue recognition system, which judges the degree of fatigue according to the recorded operation behavior of the driver; the fatigue monitoring system equipped by Mercedes-Benz is an attention ...

AI Technical Summary

Problems solved by technology

The disadvantage is that it cannot be completely determined that it is fatigue driving only by opening and closing the mouth, and there are also possible situations such as talking and sneezing

Its shortcoming is that the invention mainly analyzes the face image, judges the fatigue state through the positioning of the eye area, and the pixel points after the circle fitting, only for the number of eye blinks, and other conditions such as eye discomfort cannot be ruled out. Accurately judge fatigue driving status

Images