A method for predicting the risk of virtual crashes in a simulated driving task using behavioural and subjective drowsiness measures

Abstract

This study proposed a procedure for predicting the point in time with high risk of virtual crash using a control chart methodology for behavioural measures during a simulated driving task. Tracking error, human back pressure, sitting pressure and horizontal and vertical neck bending angles were measured during the simulated driving task. The time with a high risk of a virtual crash occurred in 9 out of 10 participants. The time interval between the successfully detected point in time with high risk of virtual crash and the point in time of virtual crash ranged from 80 to 324 s. The proposed procedure for predicting the point in time with a high risk of a crash is promising for warning drivers of the state of high risk of crash.

Practitioner Summary: Many fatal crashes occur due to drowsy driving. We proposed a method to predict the point in time with high risk of virtual crash before such a virtual crash occurs. This is done using behavioural measures during a simulated driving task. The effectiveness of the method is also demonstrated.     

基于脉搏波检测的驾驶员睡意预警装置

随着驾驶员人数的不断增加,不文明的驾驶行为也越来越多,其中由于疲劳驾驶所引发的交通事故占据相当大的比例,给人民的生命和财产造成了巨大的损失,因此,对于驾驶员睡意预警装置的技术研究具有非常重要的意义和实用价值。通过对人体脉搏波信号进行分析处理,采用能够反映驾驶员睡意状态的脉搏频率特征信号作为依据,由STC89C52单片机、按键、数码管、光电传感器、时钟模块、滤波电路、集成运放等构成系统,设计了驾驶员睡意预警装置。调试结果显示该装置识别准确率高,数值可靠,能够有效的检测驾驶员的睡意状态,并在睡意状态时发出预警。对比市场同类型产品,该装置具有成本低廉,操作简单,能够实现车载等特点,为驾驶员睡意预警技术的相关研究提供了一定的技术和实验基础。     

基于人眼状态的瞌睡识别算法

已有瞌睡识别算法多数基于机器学习或深度学习,没有考虑到人眼闭合状态序列与瞌睡之间的关系。针对上述问题,提出了一种基于人眼状态的瞌睡识别算法。首先,提出了人眼分割和面积计算模型,基于人脸68个特征点,根据人眼特征点构成的极大多边形分割出眼睛区域,并利用眼睛像素点的总数代表眼睛面积大小;其次,计算极大状态下的人眼面积,并利用关键帧挑选算法挑选出最能代表睁眼程度的4帧,根据这4帧的人眼面积与极大状态下的人眼面积计算睁眼阈值,从而构建眼睛闭合度得分模型来确定人眼闭合状态;最后,根据输入视频的人眼闭合得分序列,构建了基于连续多帧序列分析的瞌睡识别模型。在两个国际常用的打哈欠检测数据集（YawDD）和NTHU-DDD数据集上进行瞌睡状态识别,实验结果表明,所提算法在两个数据集上的识别准确率均在80%以上,尤其是在YawDD数据集上,识别准确率达到94%以上。该算法可应用于驾驶员驾驶状态检测、学习者课中状态分析等。     

基于单片机的瞌睡感应报警系统

系统用于监测司机的瞌睡程度并适时发出警报,使驾驶员时刻保持清醒,保证驾驶安全。系统根据眨眼时间与瞌睡程度的生理关系,利用光电手段对眨眼过程进行实时监测,监测结果交由微型单片机处理。当眨眼时间满足瞌睡条件时,单片机发出警报,驱除司机的瞌睡。经过测试,此设计可以对驾驶员的疲劳程度做出比较准确的判断和告警,在一定程度上预防相关事故的发生。     

驾驶员疲劳度的实时检测

驾驶员疲劳驾驶是机动车事故发生的一个重要原因,基于驾驶员疲劳度检测方法的疲劳度检测系统可以减少交通事故的发生率。然而很多算法在实现上太复杂或者难以实现。产生睡意的情况下,眼睛睁开幅度比正常情况下要小,而且每次睁开的幅度很固定。根据这种特点,设计了一种实时检测驾驶员疲劳时眼部状态的方法,采用红外线CCD摄像头采集图像,在DSPTMS3206416芯片的基础上实时处理。可以不受光线干扰,快速实时有效地识别出驾驶员疲劳时眼部状态。     

The effects of physical vibration on heart rate variability as a measure of drowsiness

We investigated the effects of low frequency whole body vibration on heart rate variability (HRV), a measure of autonomic nervous system activation that differentiates between stress and drowsiness. Fifteen participants underwent two simulated driving tasks for 60?min each: one involved whole-body 4–7?Hz vibration delivered through the car seat, and one involved no vibration. The Karolinska Sleepiness Scale (KSS), a subjective measure of drowsiness, demonstrated a significant increase in drowsiness during the task. Within 15–30?min of exposure to vibration, autonomic (sympathetic) activity increased (p?p?drowsiness contours leading to improvements in road safety.

Practitioner summary: The effects of physical vibration on driver drowsiness have not been well investigated. This laboratory-controlled study found characteristic changes in heart rate variability (HRV) domains that indicated progressively increasing neurological effort in maintaining alertness in response to low frequency vibration, which becomes significant within 30?min.

Abbreviations: ANS: autonomic nervous system; Ctrl: control; EEG: electroencephalography; HF: the power in high frequency range (0.15 Hz-0.4Hz) in the PSD relected parasympathetic activity only; HRV: heart rate variability; KSS: karolinska sleepiness scale; LF: the power in low frequency range (0.04 Hz-0.15Hz) in the PSD reflected both sympathetic and parasympathetic activity of the autonomic nervous system; LF/HF ratio: the ratio of LF to HF indicated the balance between sympathetic and parasympathetic activity; RMSSD: the root mean square of difference of adjacent RR interval; pNN50: the number of successive RR interval pairs that differed by more than 50 ms divided by the total number of RR intervals; RR interval: the differences between successive R-wave occurrence times; PSD: power spectral density; RTP: research training program; SD: standard deviation; SEM: standard error of the Mean; Vib: vibration     

Driver's drowsiness detection using an enhanced image processing technique inspired by the human visual system

Unfit drivers are the cause of tens of thousands of incidents on the roads which lead to injuries and deaths. Therefore, it is very important to take preventive measures against such incidents. One of the unfit driving conditions is driving while being drowsy. Using image processing techniques, drowsiness of the driver could be detected and hence such incidents could be prevented. In this work, inspired by how images are processed by the human visual system, an enhancement for driver's drowsiness detection is suggested. Furthermore, to improve the robustness of the drowsiness detection system, the mechanism for using energy levels in frames is changed. Lastly, a better decision making process is proposed. To measure the merit of the system, it is applied to a set of drivers' data. Test results show that using the proposed system, success rate of the drowsiness detection system is 90%.     

面部多特征融合的驾驶员疲劳检测方法

为了监测驾驶员的疲劳状态,提出了一种基于面部多种疲劳参数的驾驶员状态检测算法。首先利用Gabor滤波和梯度信息增强眼睛和嘴部的边缘信息以进行准确定位,然后采用一种旋转不变的LBP金字塔特征对眼睛进行特征描述,训练线性SVM分类器判别眼睛的开闭状态;并根据嘴部的张开面积及宽高比判断嘴部的开闭状态,同时通过统计眼睛在垂直方向上的运动确定头部位置的变化。最后基于眼睛和嘴部的状态、头部的位置,计算出4个能够描述驾驶员状态的疲劳参数,利用模糊系统推理得出驾驶员最终的疲劳状态。实验结果证明检测和状态判别的算法都有较高的准确率,其中眼睛状态的识别率平均在97%,嘴部状态的识别率也能达到92%;模糊系统的合理性也在实验中得以验证。     

Highly-Sensitive Skin-Attachable Eye-Movement Sensor Using Flexible Nonhazardous Piezoelectric Thin Film

Accurate and continuous monitoring of eye movements using compact, low-power-consuming, and easily-wearable sensors is necessary in personal and public health and safety, selected medical diagnosis techniques (point-of-care diagnostics), and personal entertainment systems. In this study, a highly sensitive, noninvasive, and skin-attachable sensor made of a stable flexible piezoelectric thin film that is also free of hazardous elements to overcome the limitations of current computer-vision-based eye-tracking systems and piezoelectric strain sensors is developed. The sensor fabricated from single-crystalline III-N thin film by a layer-transfer technique is highly sensitive and can detect subtle movements of the eye. The flexible eye movement sensor converts the mechanical deformation (skin deflection by eye blinking and eyeball motion) with various frequencies and levels into electrical outputs. The sensor can detect abnormal eye flickering and conditions caused by fatigue and drowsiness, including overlong closure, hasty eye blinking, and half-closed eyes. The abnormal eyeball motions, which may be the sign of several brain-related diseases, can also be measured, as the sensor generates discernable output voltages from the direction of eyeball movements. This study provides a practical solution for continuous sensing of human eye blinking and eyeball motion as a critical part of personal healthcare, safety, and entertainment systems.     

Customization of Wavelet Function for Pupil Fluctuation Analysis to Evaluate Levels of Sleepiness

This paper proposes a method to customize a wavelet function for the analysis of pupil diameter fluctuation in the detection of drowsiness states under a driving simulation. The methodology relies on a genetic algorithm-based optimization and lifting schemes, which are a flexible and fast implementation of the discrete wavelet transform. To customize the wavelet function a clustering separability metric is employed as a fitness function so that the feature space created by the wavelet analysis exhibits the maximum class separability favorable for classification. Therefore, a completely new wavelet function is created, having unique characteristics customized to pupil diameter fluctuation analysis. It is demonstrated that the customized wavelet function own distinguished frequency and temporal responses suitable specifically for pupil diameter fluctuation analysis （namely, application-dependent）, and in the classification they outperform classical wavelet families including Daubechies, Coiflet and Symlet, which are assumed to be application-independent. Thus the proposed method is useful for analysis of pupil fluctuation in evaluating sleepiness levels, as has been demonstrated in other applications.