Driving behavior analysis method and device

Abstract

The invention relates to the technical field of vehicle safety, in particular to a driving behavior analysis method and a device, and the method comprises the steps: obtaining an environment feature factor of a current driving environment of a vehicle, a state feature factor of a current driving state of the vehicle, and a biological feature factor of a driver in the current driving state; determining correlation coefficients between every two of the environment feature factor, the state feature factor and the biological feature factor, and generating a correlation coefficient sequence; performing fusion processing on the environment feature factor, the state feature factor and the biological feature factor based on the correlation coefficient sequence to obtain a driving behavior featurefactor of the driver; and determining the driving behavior state of the driver according to the driving behavior feature factor. According to the driving behavior analysis method, the driving behaviorstate is comprehensively analyzed from the aspects of the vehicle driving environment, the vehicle driving state, the driver biological feature and the like, and the accuracy of driving behavior state analysis can be improved.

Description

technical field [0001] The invention relates to the technical field of vehicle safety, in particular to a driving behavior analysis method and device. Background technique [0002] With the rapid development of our country's economy and the improvement of people's living standards, the growth rate of the number of motor vehicles and the number of new road mileages is accelerating. At the same time, road traffic accidents, especially vicious traffic accidents, are on the rise. How to reduce the incidence of traffic accidents has become one of the huge problems in today's transportation industry. [0003] During vehicle driving, especially during long-distance driving, the driver is prone to fatigue, decreased thinking ability, and slow response due to poor physical condition or long-term driving; on the other hand, when the driver's sight is not on the road, the vehicle It will also deviate from the lane and be prone to car accidents. There is a direct causal relationship b...

AI Technical Summary

Problems solved by technology

Since the images captured by the camera are all images of the driver and the same field of view in the car, the shooting area is limited. When the driver's actions exceed the shooting area, it is difficult to identify the driving state, resulting in inaccurate recognition of the driver's behavior; In addition, due to the ever-changing behavior of drivers, the images of different driving behaviors captured have similar global background information and different local information, and the quality of captured images is greatly affected by natural factors such as lighting, which brings great difficulties to recognition. Certain difficulties lead to low driving behavior recognition accuracy

Images