Method, device and equipment for determining fatigue state of driver

Abstract

The invention provides a method, a device and equipment for determining a fatigue state of a driver, which are used for providing a more convenient detection scheme for fatigue detection of the driver on a vehicle and have remarkably improved practicability for practical application. The method comprises the steps of obtaining a plurality of initial images of a driving position on a vehicle; performing face recognition processing on the plurality of initial images to obtain a plurality of face images; extracting a plurality of human eye images according to the human face features corresponding to the plurality of human face images; sequentially inputting the plurality of eye images into an eye opening and closing identification model, and performing eye opening and closing identification processing on the eye images by the eye opening and closing identification model to obtain a plurality of eye opening and closing identification results output by the eye opening and closing identification model; in combination with image acquisition time points corresponding to the plurality of eye opening and closing identification results, judging whether a continuous eye closing identification result with a time point span greater than a preset duration exists in the plurality of eye opening and closing identification results or not; and if so, determining that the driver corresponding to the plurality of initial images is in a fatigue state.

Description

technical field [0001] The present application relates to the field of vehicles, in particular to a method, device and equipment for determining a driver's fatigue state. Background technique [0002] With the continuous improvement of living standards, the number of vehicles has been growing. To a certain extent, the more serious the road congestion, the higher the probability of vehicle collisions. Congested road conditions, in addition to vehicle driving skills, have a great impact on The driver's attention is also more demanding than the normal state of the road. [0003] In addition, studies have shown that at least 8,000 traffic accidents per year are caused by driver inattention or fatigue, and driver fatigue driving is one of the main factors leading to traffic accidents, so the research on driver fatigue detection is of great significance. Great significance. [0004] In the research process of the existing related technologies, the inventors found that the existi...

AI Technical Summary

Problems solved by technology

[0004] In the research process of the existing related technologies, the inventors found that the existing detection schemes of the driver's fatigue state mainly include two types, the first type of detection scheme, which uses EEG to judge whether the driver is in a fatigue state , has the characteristics of contact, but it may affect the driving operation of the driver; the second type of detection scheme uses the detection value of the physical quantity (Percentage of EyeIid CIosure over the PupiI over Time, PERCLOS) to measure fatigue / drowsiness. To measure the fatigue state of the driver, the detection value can be understood as the percentage of the time of the eyes closed state in the unit time to the total time. However, the total time generally needs to be taken as 1 minute or 30 seconds, and there is a problem that it takes a long time. From this It can be seen that the existing detection scheme has the problem of inconvenient application

Images