Fatigue driving estimation and early-warning method and device of multi-sensor information fusion

Abstract

The invention relates to a fatigue driving estimation and early-warning method and device of multi-sensor information fusion. The method comprises the following steps of: detecting the state of the face and eyes of the driver to obtain the face image information of the driver, and acquiring the driveway image information; performing fatigue estimation of the driver according to the obtained face image information of the driver; establishing a mathematical model according to the driveway image information, and judging whether the vehicle is over the line; establishing a mathematical model according to the driveway image information, and judging whether the vehicle deviates for a large angle; estimating the driving safety level according to the information obtained by the abovementioned steps; and making a decision and performing early warning according to the driving safety level. The device comprises a first image acquisition unit, a driver fatigue estimation unit, a second image acquisition unit, an over-line judging unit, a deviation judging unit, a driving estimation unit and a central processing unit. Through the invention, the traffic accidents caused by fatigue driving can be effectively reduced.

Description

technical field [0001] The invention relates to the technical field of vehicle safety driving, in particular to a fatigue driving assessment and early warning method and device based on multi-sensor information fusion. Background technique [0002] Fatigue driving is one of the important hidden dangers of today's traffic safety. When the driver is fatigued, his ability to perceive the surrounding environment, the ability to judge the situation and the ability to control the vehicle all decline to varying degrees, so traffic accidents are prone to occur. The number of deaths caused by traffic accidents in the world reaches 600,000 every year, and the direct economic loss is about 12.5 billion US dollars. Among these accidents, 57% of catastrophic accidents are related to driver fatigue. From 2007 to 2008, the number of deaths directly caused by fatigue driving in my country accounted for 11.35%, 10.91% and 12.5% ​​of the total death toll of motor vehicle drivers in traffic a...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing driver fatigue state monitoring methods are based on a single index. Although they can achieve a certain accuracy under limited conditions, there are still problems in their accuracy and reliability in the actual complex and changeable driving environment. meet expectations

[0004] The study found that the driver's fatigue state is affected by many factors. So far, no very effective indicators or models have been found at home and abroad that can accurately evaluate the fatigue level

Most of the existing detection methods cannot accurately and completely extract the driver's fatigue information due to the limitation of detection conditions and the influence of the complex environment. As a result, the fatigue driving warning system currently developed is often unable to quickly judge and respond to the fatigue state. Detection sensitivity low, poor reliability

Images