Fatigue driving detection method and device

Abstract

The invention discloses a fatigue driving detection method and device. The method comprises the following steps of: locating a face region based on a collected head image of a driver; detecting a nose frame region based on the face region, wherein the nose frame region is a region where a connecting part for connecting a left spectacle frame and a right spectacle frame of a pair of spectacles is spanned on the nose bridge of the driver; if detecting the nose frame region, acquiring an eye region based on the nose frame region; if not detecting the nose frame region, locating the eye region based on the face region; analyzing the closing state of eyes based on the eye region, and comparing the closing state of the eyes with a fatigue standard to judge whether the driver is in a fatigue state. Through the scheme for searching the nose frame region, the defect that directly searching eyes in the traditional eye searching method based on machine vision is easy to be interfered by objects such as spectacles / sunglasses and the like is overcome, and the accuracy for judging the close of the eyes of the driver is improved, furthermore, the accuracy for judging fatigue driving is improved,and better adaptability is obtained.

Description

technical field [0001] The invention relates to the technical field of safe driving of vehicles, in particular to the technical field of fatigue driving monitoring. Background technique [0002] The development direction of advanced automotive safety technology is active safety technology, that is, through the detection of the driver, vehicle and surrounding environment, it can judge possible dangers in advance and take preventive measures. The driver fatigue driving warning technology is a typical active safety technology. When the driver is in a state of fatigue, the ability to perceive the surrounding environment, the ability to judge the situation, and the ability to control the vehicle are all reduced to varying degrees, and traffic accidents are prone to occur. Therefore, the research and development of high-performance driver attention real-time monitoring and early warning technology can effectively reduce the hidden dangers caused by fatigue driving and other behav...

AI Technical Summary

Problems solved by technology

There is a serious problem with this method: for drivers without any additional objects on the face, traditional eye detection and positioning methods based on machine vision can better locate the eye area, but for drivers wearing various styles of glasses / sunglasses For the driver, because the glasses affect some parameters of the image in this area, the precise positioning of the eyes is greatly disturbed, thus making the detection results of the eye state invalid

[0004] Therefore, the traditional fatigue driving detection method based on machine vision has obvious limitations in actual use, and it is difficult to achieve better robustness requirements.

Images