A fine-grained human fatigue detection method and device based on embedded devices

Abstract

The invention discloses a fine-grained human body fatigue detection method and device based on an embedded device. The infrared light sensing device and an MCU control unit are used to build a human body fatigue detection device; Collect human eye state information; set the ADC conversion parameters of the MCU control unit to convert the analog signal into a digital signal; and initialize each photodiode to obtain the reference value of the human eye open state, and filter and analyze the reference value data Smoothing preprocessing; use the CUSUM algorithm to process the preprocessed data to determine the potential blink position in the time domain; use two matching methods to judge the real blinking behavior; use the PERCLOS method to estimate and judge the fatigue state, and complete the human fatigue detection. The present invention can more accurately collect the state information of human eyes, the duration of eye closure and the duration of blinking, and satisfies the long-term monitoring of fatigue for daily wear.

Description

technical field [0001] The invention belongs to the technical field of human fatigue detection, and in particular relates to a fine-grained human fatigue detection method and equipment based on an embedded device. Background technique [0002] Human fatigue detection has always been a research hotspot in many industries: In the transportation industry, the number of accidents caused by fatigue of automobile drivers and railway locomotive drivers will increase every year with the increase of vehicles and the continuous extension of locomotive traffic. At the same time, in the medical field, fatigue is the leading signal of some health problems, such as cancer, addictive mental diseases, etc., through daily monitoring of patient fatigue, so as to assist doctors to make timely early warning and judgment. There are many existing fatigue detection methods, and the common ones can be divided into methods based on human physical signals and methods based on human behavior signals. ...

AI Technical Summary

Problems solved by technology

However, the image method is not mainly used for the extraction of human eye state information after all, so the image method will be limited to: the interference of ambient light in daily applications, the detected person needs to be in the state of facing the camera for a long time, and the image accuracy is not high And the amount of calculation is huge, the price of high fps camera is too high, etc.

These limitations have caused the image to use human eye information to perform fatigue detection in the laboratory, which is difficult to promote.

Images