Detection of Blink State Based on Fatigued Driving

Lei Chao,Shi Lu,Li Guang,Wang Changyuan

doi:10.21307/ijanmc-2019-067

Abstract

Abstract In recent years, with the improvement of the national economy, the penetration rate of automobiles has been increasing, and traffic accidents have also increased. Fatigue driving is the main factor in many traffic accidents. Fatigue driving can cause the driver’s inattention, slow response, and make wrong decisions on danger signals, which affect the driver’s personal safety. In modern development, driving safety is developing towards intelligence and safety. Therefore, the detection of driver fatigue has become a generally accepted demand. This paper proposes a method to calculate the threshold of blinking, which can detect the blinking state of the driver in real time through video. During the driving process, when the driver is in the closed eye state for a long time, an early warning is issued to avoid the accident. This paper uses Python language to achieve the first, through the digital image technology call Dlib open source library to detect 68 feature points of the face, and then measure the aspect ratio between the length and width of the human eye, and finally through the Kmeans clustering algorithm to collect the ratio The analysis yields the blink threshold. The experimental results show that the recognition rate is 92.5% when the video frame rate is 30, and the recognition accuracy is 92.5%. The experimental results show that the method designed in this paper can quickly detect the fatigue characteristics of the human eye, has a higher recognition rate and accuracy for fatigue driving, and helps reduce the occurrence of traffic accidents.

Highlights

With the improvement of people's material living standards, cars have become the main means of transportation for people, but the growing number of vehicles has led to more traffic accidents
Fatigue driving is the main cause of traffic accidents[1,2].Under normal circumstances, the medical community believes that there are two reasons for fatigue driving, one is because the driver's attention is too concentrated, and the other is that the body does not rest well
Fatigue detection mainly through facial features, eye and mouth features, human electrical signal characteristics and convolutional neural network characteristics[3,4,5].The detection of facial features is generally based on the frequency of blinking eyes, the degree of mouth opening, and the frequency of head movements due to fatigue

Summary

INTRODUCTION

With the improvement of people's material living standards, cars have become the main means of transportation for people, but the growing number of vehicles has led to more traffic accidents. Fatigue detection mainly through facial features, eye and mouth features, human electrical signal characteristics and convolutional neural network characteristics[3,4,5].The detection of facial features is generally based on the frequency of blinking eyes, the degree of mouth opening, and the frequency of head movements due to fatigue. Convolutional neural networks generally extract facial features through image processing methods, and extract the main features through convolutional layers, pooling layers, and fully connected layers to analyze and determine whether fatigue. This paper chooses Dlib open source library to detect human eye features. The 68 face feature points provided by the Dlib open source library are used to accurately calibrate the position of the face and the human eye, and the aspect ratio between the length and the width of the human eye is measured.

Blink detection and threshold analysis methods

Blinking formula

THE EXPERIMENT

Findings

CONCLUSION