Abnormal driving behavior detection method based on machine vision

Abstract

The invention discloses an abnormal driving behavior detection method based on machine vision. The method comprises the following steps that: a step of preparing a precursor;in hardware model selection 2, the selectionan image acquisition module 4 acquires is selected to acquire face information and hand posture information of a driver; then heart rate detection and hand posture detection of the driver are completed on the face of the driver through an algorithm design 1, and then an abnormal result processing module 15 integrates a heart rate result of heart rate detection and a result of hand posture abnormal detection, so that abnormal behavior stopping detection of the driver is achieved, and corresponding measures are taken. According to the invention, driving behavior classificationis carried out on the acquired driver motion characteristics by integrating the two detection results and designing the classifier, so that the abnormal driving behavior is identified, and the abnormal result processing module processes the abnormal result.

Description

technical field [0001] The present invention relates to the field of industrial intelligence and machine vision technology, and in particular to a machine vision-based abnormal driving behavior detection method, which is used to accurately detect the driver's behavior in real time. Background technique [0002] At present, the detection and monitoring of abnormal driving behavior at home and abroad has become a key research work in the field of intelligent transportation research. Timely monitoring of the driver's driving status is of great significance for improving the driver's safety work efficiency, reducing the accident rate, and improving the traffic environment. [0003] The current research on abnormal driving is mainly limited to the study of drunk driving, and for the research of drunk driving, there are on-site test methods, breath alcohol detection, blood alcohol detection, saliva alcohol detection, alcohol key detection, although these technologies can avoid some...

AI Technical Summary

Problems solved by technology

[0003] The current research on abnormal driving is mainly limited to the study of drunk driving, and for the research of drunk driving, there are on-site test methods, breath alcohol detection, blood alcohol detection, saliva alcohol detection, alcohol key detection, although these technologies can avoid some drunk driving accidents occur, but the feasibility is not strong, and these are likely to be detected after drunk driving, and the effect on preventing drunk driving is not significant

In addition to the above common technologies, sensor-based detection of driving state is also the current research direction, but the driver needs to wear a complex physiological state detector, and at the same time, more sensors need to be installed in the car, which is not very feasible , and the cost is higher

Images