Driver state monitoring device based on computer vision

Abstract

The invention discloses a driver state monitoring device based on computer vision. The device comprises at least one vehicle-mounted camera for acquiring a real-time face image of a driver and recording acquisition time; edge equipment used for processing the input image and time data, and composed of the following steps: calculating a real-time face image of the driver according to a face recognition algorithm and outputting a face recognition result; inputting the face recognition result into a deep neural network for processing to obtain an expression recognition result; taking the expression recognition result and the corresponding acquisition time as expression data, and sequentially recording the expression data into an expression database; and obtaining a plurality of expression data from an expression database, and obtaining a judgment result of emotion recognition and fatigue degree of the driver according to analysis. According to the invention, grading judgment and processing can be carried out according to the driver state and the on-site condition, interactive high-risk vehicle supervision linkage can be realized, the response time is effectively shortened, and the traffic accident rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of vehicle driving safety monitoring, in particular to a computer vision-based driver state monitoring device. Background technique [0002] With the rapid development of automobile industry technology, traffic accidents caused by vehicles occur from time to time, some of which are caused by driver fatigue. [0003] Existing main means for preventing traffic accidents such as fatigue driving include: 1. Control the driver's single driving time, mainly by counting the actual driving time of the vehicle. Its shortcoming is that the evaluation standard is too single, it cannot comprehensively analyze the real-time situation of the driver, and the prevention effect is not good. 2. Fatigue driving monitoring technology, which monitors the physiological characteristics of the driver through a contact device, so as to determine whether there is a dangerous behavior of fatigue driving. The disadvantage of the cont...

AI Technical Summary

Problems solved by technology

However, most of the existing fatigue monitoring methods based on computer vision can only obtain some facial features such as the position of human eyes, but cannot extract feature points for all feature information of the face.

Therefore, it is only possible to simply judge the fatigue of the driver, but not the emotional state of the driver.

As a result, it is impossible to quickly and accurately capture high-risk vehicle information and realize interactive re-rating and online and offline supervision linkage according to the overall mental state of the driver, which is not conducive to effectively shortening the response time and reducing the traffic accident rate

Images