Fatigue driving detection method and system

Abstract

The invention discloses a fatigue driving detection method and system. The fatigue driving detection method comprises the following steps of acquiring steering wheel parameters, vehicle driving parameters and driver electrocardiosignals; analyzing the fatigue state of the driver by utilizing the steering wheel taking parameter, the vehicle driving parameter and the driver electrocardiosignal respectively; obtaining multiple fatigue parameters, taking the plurality of fatigue parameters as characteristics; taking a real fatigue value obtained by utilizing the brain wave data as a label, forminga data pair by one feature and one label, forming a data set by all the data pairs, randomly dividing the data set into a test set and a training set, and training a machine learning model by utilizing the training set to obtain a final fatigue judgment model; and inputting the steering wheel parameters, the vehicle driving parameters and the driver electrocardiosignals which are acquired in realtime into the fatigue judgment model to obtain a fatigue value. According to the invention, a plurality of fatigue characteristic parameters are combined, the influence of space, illumination, weather and the like is overcome, and the real-time performance and accuracy of the detection algorithm are improved.

Description

technical field [0001] The invention relates to fatigue driving detection technology, in particular to a fatigue driving detection method and system. Background technique [0002] There are many studies on fatigue driving detection, which can be generally divided into two categories. One is to analyze fatigue through the driver's physiological signals or driving behavior, and the other is to detect the fatigue state through the characteristics of the vehicle during driving. The representative methods or products in the existing research results are: [0003] 1) The "PERCLOS" fatigue driving detection method refers to the proportion of eyes closing time per unit time. When the driver is driving tired, the most direct and obvious physiological characteristics are accelerated blinking frequency, large eye closure degree, frequent nodding, etc. After trial and error, many experts and scholars in the world have proposed a change amount that directly reflects the driver's fatigu...

AI Technical Summary

Problems solved by technology

[0009] The best way to detect fatigue is through brainwave detection, but the sensor for brainwave detection needs to be worn on the head for detection, which is likely to cause discomfort to the driver, and the instrument is expensive; there is also eyelid detection, but the real-time detection of eyelid detection The performance is not very good, and the detection effect is greatly affected by the environment

Therefore, both EEG detection and eyelid detection are not suitable for real driving environment

[0010] In addition, there are methods suitable for real driving environments, such as detection through ECG signals, detection through steering wheel parameters, and detection through vehicle driving parameters, but most of them are not accurate enough.

Images