Fatigue driving detection method based on train cab scene

Abstract

The invention belongs to the technical field of face detection. The invention particularly relates to a fatigue driving detection method based on a train cab scene. The method comprises the followingsteps: firstly, carrying out face detection by utilizing a deep learning method, detecting 68 key points of face key points, calculating a distance between two eyes of an eye region and a distance between lips by utilizing 68 points, and calculating a head turning state by utilizing a 68-point turning Euler angle so as to carry out first-step judgment on a fatigue state; then, visual features of the eye parts are extracted to establish a visual model for eye opening and closing judgment so as to improve the distinguishing capability of the visual features; then yawn judgment is carried out bycombining the opening and closing characteristics of the lip area; and whether the driver is fatigue or not is further judged according to the eye opening and closing frequency and the yawn frequency,misjudgment of a single feature is reduced, and false alarm signals caused by misjudgment are reduced, so that a scheme of combining two optimization strategies is adopted in the aspect of detectionaccuracy, and the fatigue state of the human face can be accurately detected.

Description

technical field [0001] The invention belongs to the technical field of face detection, and in particular relates to a fatigue driving detection method based on a train cab scene. Background technique [0002] With the rapid development of the economy, the large-scale construction of urban roads, the mileage of highways such as trains and high-speed rails has increased year by year, and the incidence of traffic accidents has also increased. Fatigue, so fatigue driving has become the main cause of traffic accidents. [0003] How to effectively prevent fatigue driving, scholars at home and abroad use different technologies to study the existing fatigue driving detection methods, which can be divided into two categories according to fatigue characteristics: methods based on physiological characteristics and methods based on behavioral characteristics, based on physiological characteristics including physiological signals Features and physiological response characteristics, base...

AI Technical Summary

Problems solved by technology

[0005] The above fatigue driving detection methods have achieved certain effects and progress, but there are still great limitations. Although the detection method based on physiological signal features has high accuracy, it requires the driver to have direct physical contact with the detection equipment. Acquisition of signals, which may interfere with the driver's driving operation and the cost of the equipment is too high, is more suitable for the laboratory environment, not suitable for practical applications; the detection method based on behavioral characteristics does not require the driver to directly contact the detection device and is compatible with existing devices in the car On the basis of low demand for equipment, it is very practical and easy to promote, but it will be limited by the driver's personal habits, road conditions and vehicle models. In rainy and snowy weather or when the road condition is not ideal, the detection accuracy is low; In the case of ensuring a certain accuracy and good real-time performance, the method of processing physiological response characteristics based on computer vision is easier to promote, but the feature resolution ability of artificial design is poor and relying on a single one, visual features may encounter difficulties such as driving When people wear glasses, the glasses reflect light, which may cause the camera to fail to capture eye movements. In addition, the degree of opening and closing of the eyes may vary from person to person, and irregular head movements may cause false alarms, etc.

Images