Fatigue driving detection method and system based on machine learning and multi-feature fusion

Abstract

The invention discloses a fatigue driving detection method and a fatigue driving detection system based on machine learning and multi-feature fusion, and relates to the technical field of computer vision image processing. The method comprises the following steps: processing a driver face image obtained in real time, and extracting an eye image, a mouth image and head position information of a driver; respectively inputting the eye image, the mouth image and the head position information into corresponding trained classifiers to determine an eye classification result, a mouth classification result and a head classification result of the driver; performing fatigue feature extraction on the eye part classification result, the mouth part classification result and the head part classification result of the continuous multi-frame face images, and determining the fatigue degree of the driver according to the extracted fatigue features; wherein the fatigue characteristics comprise eye closingfrequency, yawn frequency and nodding frequency. The fatigue driving detection accuracy can be guaranteed under the condition that the eyes of a driver are shielded, and the function of guaranteeing the safety of a vehicle owner and surrounding pedestrians and vehicles through a perfect warning method is achieved.

Description

technical field [0001] The invention relates to the technical field of computer vision image processing, in particular to a fatigue driving detection method and system based on machine learning and multi-feature fusion. Background technique [0002] In recent years, with the increasing number of motor vehicles, the mileage of open roads and the growing speed of commodity logistics, the problem of fatigue driving has become more and more prominent. The British Automobile Association Charities Trust surveyed 20,561 motorists and found that 17 per cent of men experienced drowsiness while driving. Driving requires a high level of concentration and concentration, while fatigued drivers experience an increase in unresponsiveness, blurred vision, distraction and operational errors. According to research, 60% of traffic accidents lack only 0.5 seconds of reaction time before the accident. Fatigue driving undoubtedly greatly increases the risk of traffic accidents. For example, the...

AI Technical Summary

Problems solved by technology

[0003] Combined detection of multiple fatigue features has always been an important topic in the direction of fatigue driving detection. In the process of fatigue driving detection, the eyes are often blocked, which makes the detection accuracy difficult to guarantee.

Images