Fatigue driving detection method and system

Abstract

The invention discloses a fatigue driving detection method, which comprises the following steps of authenticating the driver identity, accumulating the driving time, extracting the expression state, extracting the body state, collecting the road condition information, extracting the vehicle control state and detecting the fatigue driving. The invention also provides a fatigue driving detection system. According to the invention, the facial expression and the body movement of a driver is tracked through the face recognition, and the driver becomes fatigue from a normal state, for example, the eye-closed time is getting longer, the nod frequency is increased, and the like; the vehicle control state of the driver is tracked and judged whether to become bad along with the time, for example, the steering wheel rotation variance is getting larger, so the driver is detected whether to be in a fatigue driving state. The fatigue driving detection method and system avoid presetting a define threshold, and the accuracy can not be affect by the individual differences of drivers.

Description

technical field [0001] The invention belongs to the field of automobile driving, and in particular relates to a fatigue driving detection method and system. Background technique [0002] In recent years, with the increase in the use of automobiles, the incidence of traffic accidents has increased year by year, and driving safety has become an increasingly concerned issue. In the traffic accidents caused by dangerous driving behavior, fatigue driving accounts for a considerable proportion. According to the statistics of relevant state departments, the traffic accidents caused by fatigue driving account for about 20%. Therefore, driving fatigue detection has been a research hotspot in academia and industry for many years. So far, the existing fatigue driving detection methods can be classified into three categories: [0003] The first category: detection of human biological signals, such as by analyzing specific frequency bands in the driver's EEG / ECG, to detect whether the ...

AI Technical Summary

Problems solved by technology

[0006] The inventors of the present invention have found through research that among the existing three types of fatigue driving detection methods, the detection method based on human biological signals has relatively high accuracy, but requires the driver to wear some contact electronic equipment, such as detecting brain fatigue. Electrically signaled headgear devices to which drivers are generally disgusted and repelled

The detection methods based on "facial expressions and body movements" or "vehicle handling status" are convenient and easy to implement, but for different drivers, when distinguishing fatigue or non-fatigue, there are differences in the boundaries of these signals (ie, thresholds) , so these detection methods currently proposed are usually based on a general model that has nothing to do with the individual, and its accuracy varies greatly among different drivers

Images