Driver fatigue state detection method based on smart phone and smart watch

Abstract

The invention belongs to the technical field of traffic safety and discloses a driver fatigue state detection method based on a smart phone and a smart watch. The method comprises a step of collectingvehicle driving state data and driver operating behavior data through the smart phone and the smart watch, a step of separating superimposed vehicle driving state information in the driver operatingbehavior data collected by the smart watch to obtain data information capable of reflecting a driver operating behavior, a step of extracting a driver fatigue state characteristic value according to the vehicle driving state information and driver operating behavior information, and a step of removing a redundant characteristic index in the extracted driver fatigue state characteristic value basedon a genetic algorithm, taking a characteristic index combination with the removal of the redundant characteristic index as an input, and establishing a fatigue detection model based on a BP neural network to monitor the state of a driver.

Description

technical field [0001] The invention belongs to the technical field of traffic safety, and in particular relates to a detection method for a driver's fatigue state. Background technique [0002] With the continuous growth of the number of motor vehicles in our country, the problem of road traffic safety is becoming increasingly serious. Fatigue driving, as one of the common illegal driving behaviors, has brought huge safety hazards to the society. Fatigue driving refers to the disorder of physiological and psychological functions of the driver after driving continuously for a long time, and the phenomenon of objectively declining driving skills. If the driver continues to drive, it is easy for the driver to become sleepy or even doze off. , leading to serious traffic accidents. [0003] In order to prevent drivers from driving fatigue, my country's "Road Traffic Safety Law Implementation Regulations" clearly stipulates that drivers must not drive a motor vehicle continuousl...

AI Technical Summary

Problems solved by technology

[0004] The relatively mature fatigue detection methods in existing research mainly include non-contact detection methods based on computer vision and video image processing, but the algorithms of such detection methods are very complex and are easily disturbed by external environments such as lighting.

The detection method based on the driver's physiological indicators mainly collects physiological data such as the driver's EEG signal and ECG signal, and analyzes the migration law of physiological characteristics during the driving process to realize the detection of the driver's fatigue state. Installing data acquisition sensors on a certain part of the human body can easily lead to driver distraction or discomfort, and the equipment is very expensive, and its engineering practicability is quite limited

Images