驾驶分心综述

葛慧敏; 郑明强; 吕能超; 陆颖; 孙辉

doi:10.19818/j.cnki.1671-1637.2021.02.004

驾驶分心综述

doi: 10.19818/j.cnki.1671-1637.2021.02.004

1.
江苏大学汽车与交通工程学院，江苏镇江 212013
2.
武汉理工大学智能交通系统研究中心，湖北武汉 430070

基金项目:

国家自然科学基金项目 51905224

国家自然科学基金项目 51605197

详细信息

作者简介:
葛慧敏(1979-)，女，江苏连云港人，江苏大学副教授，工学博士，从事驾驶行为研究

中图分类号: U491.254
计量
- 文章访问数: 2092
- HTML全文浏览量: 676
- PDF下载量: 411
- 被引次数: 0
出版历程
- 收稿日期: 2020-09-10
- 刊出日期: 2021-04-01

Review on driving distraction

1.
School of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China
2.
Intelligent Transportation System Research Center, Wuhan University of Technology, Wuhan 430070, Hubei, China

Funds:

National Natural Science Foundation of China 51905224

National Natural Science Foundation of China 51605197

More Information

Author Bio:
GE Hui-min(1979-), female, associate professor, PhD, hmge@ujs.edu.cn

摘要

摘要: 构建了文献质量评价指标体系，筛选出288篇相关文献，综合分析了文献数据获取方式、指标选取、识别方法和研究结论；以驾驶行为为主要研究对象，结合统计学方法，系统阐述了驾驶分心试验数据的获取方式，总结了其多样性和两极化的原因；梳理了驾驶分心识别指标的研究成果，总结了其使用效能和优缺点；对比了不同驾驶分心识别模型的准确率，分析了其差异性的根源；提出了未来驾驶分心数据获取方式、指标选取、识别方法的研究趋势。分析结果表明：试验是驾驶分心数据获取的主要方式，自然驾驶数据集、视频录像是新的数据获取方式，路边观察和调查问卷的数据获取方式关注度较低；对照、跟车、超车、变道场景及添加其他危险事件的复杂度较高的场景是研究较多的驾驶分心场景；驾驶分心次任务的设置说明目前驾驶分心研究的类型和主题较集中；融合指标是使用频次最高的驾驶分心识别指标，且以驾驶绩效指标和眼动指标、驾驶绩效指标和反应指标这两类融合指标较多，驾驶绩效指标是使用最多的单类指标；支持向量机模型是使用最多的驾驶分心识别模型，但识别准确率标准差较大，性能不稳定，深度学习算法模型的识别准确率较高，且稳定性好；未来的驾驶分心研究需均衡研究主题，扩展人机共驾的分心场景，深化驾驶分心类型研究，构建标准化指标体系和选取原则，强化模型构建识别不同类型和严重程度的驾驶分心。
- 驾驶行为 /
- 驾驶分心 /
- 分心试验 /
- 识别指标 /
- 识别模型
Abstract: An indicator system for evaluating the quality of literatures was established. Based on this system and considering driving behavior as the main focus of this research, 288 relevant papers were selected, and their data acquisition methods, indicator selections, detection methods, and research conclusions were comprehensively analyzed. Taking driving behavior as the main research object, a method of obtaining test data on driving distractions was systematically derived combined with statistical methods, and the reasons for the diversity and polarization in the obtained data were summarized. The research results of different driving distraction indicators were categorized, and the efficiency, advantages, and disadvantages of these indicators were summarized. The accuracies of different driving distraction detection models were compared, and the root causes of their differences were analyzed. Future research trends of driving distraction data acquisition methods, indicator selections, and detection methods were proposed. Analysis results show that experimental tests are the primary methods for obtaining driving distraction data. Natural driving datasets and video recordings have been proposed as new methods of data acquisition, data acquisition methods of roadside observations and surveys have received less attention. Comparison scenario, vehicle following scenario, overtaking scenario, lane changing scenario, and relatively more complex scenarios involving other dangerous events are the most extensively studied driving distraction scenarios. The setting of driving distraction sub-tasks indicates that current research on driving distraction has focused on several types and topics. Fusion indicators, generally including driving performance and eye movement indicator, and driving performance and reaction indicator, are the most frequently used in driving distraction. Driving performance is the most commonly used single indicator. Support vector machine model is the most commonly used driving distraction detection model, while the standard deviation of detection accuracy is large, and this model is also unstable. In contrast, the detection accuracy of a deep learning algorithm-based model is high, and its stability is good. Future research on driving distraction should balance research topics, expand distraction scenarios to human-machine co-driving, further investigate the types of driving distractions, construct a standardized indicator system and selection principles, and strengthen model construction to detect different types and determine the severity of driving distractions. 11 tabs, 1 fig, 96 refs.
- driving behavior /
- driving distraction /
- distraction experiment /
- identification indicator /
- identification model

HTML全文

图 1 文献筛选流程

Figure 1. Literature screening process

下载: 全尺寸图片幻灯片

表 1 文献质量评估指标

Table 1. Literature quality assessment indicators

序号	评估指标
1	研究的动机、目标、意义是否明确
2	研究问题陈述是否清晰
3	研究设计是否适用于研究目的
4	研究对驾驶分心类型是否描述清楚
5	驾驶分心试验场景及次任务设置描述是否清晰
6	数据采集方案是否科学、合理
7	驾驶分心指标选取是否能对驾驶分心状态进行较好识别
8	数据分析及呈现方法是否清晰、合理、充分
9	构建的驾驶分心识别模型是否能够提高准确率
10	驾驶分心识别模型是否能够减少计算时间
11	研究结论是否清楚的说明和充分的讨论
12	是否具有研究不足与展望

下载: 导出CSV

表 2 驾驶分心数据获取方式

Table 2. Acquisition methods of driving distraction data

获取方式	驾驶分心试验	路边观察	调查问卷	自然驾驶数据集	视频图像
文献数量	133	5	5	22	10

下载: 导出CSV

表 3 驾驶分心试验场景

Table 3. Driving distraction test scenarios

场景	高速公路场景	乡村道路场景	城市道路场景	对照场景	其他驾驶行为/干扰场景	对照与干扰融合场景
文献绝对数量	25	10	12	25	51	10
文献相对数量	63	41	50	33	54	10
变异系数	1.52	3.10	3.17	0.28	0.06	0.00

下载: 导出CSV

表 4 驾驶分心试验次任务

Table 4. Sub-tasks in driving distraction test

次任务	PDT次任务	主题次任务	认知分心次任务	视觉分心次任务	操作分心次任务	听觉分心次任务	复合分心次任务
文献数量	20	48	69	25	8	2	4

下载: 导出CSV

表 5 PDT次任务

Table 5. PDT subtasks

PDT次任务	光刺激检测	行人检测	变化检测	图像检测	箭头信号检测	目标音调检测	听觉刺激反应
文献数量	5	4	3	2	1	1	1

下载: 导出CSV

表 6 主题次任务

Table 6. Subject subtask

主题次任务	手机通话	广告干扰	车载系统交互	交通标志识别	发短信	操作手机	操作音乐播放器
文献数量	12	8	8	4	4	2	2

下载: 导出CSV

表 7 自然驾驶数据集

Table 7. Natural driving data sets

数据集	自建数据集	IVBSS数据集	VTTI数据集	EuroFOT数据集	NGSIM数据集	SHRP2NDS数据集	SH-NDS数据集
文献数量	5	2	1	2	1	8	1

下载: 导出CSV

表 8 驾驶分心状态识别指标

Table 8. Identification indicators of driving distracted state

指标			文献绝对数量	文献相对数量	变异系数
基本指标	驾驶绩效指标		38	107	1.82
	眼动指标		12	65	4.42
	生理心理指标		11	22	1.00
	反应指标		9	54	5.00
	面部头部指标		2	10	4.00
融合指标	两类融合指标	驾驶绩效和眼动融合指标	23	42	0.83
		反应和驾驶绩效融合指标	22	36	0.64
		反应和眼动融合指标	6	19	2.17
		反应和生理心理融合指标	3	4	0.33
		驾驶绩效和生理心理融合指标	3	7	1.33
		驾驶绩效和面部头部融合指标	1	4	3.00
		眼动和面部头部融合指标	4	7	0.75
		眼动和生理心理融合指标	1	4	3.00
	三类融合指标	驾驶绩效、眼动与反应融合指标	13	13	0.00
		驾驶绩效、眼动与生理心理融合指标	3	3	0.00
		驾驶绩效、眼动与面部头部融合指标	3	3	0.00
		驾驶绩效、生理心理与反应融合指标	1	1	0.00

下载: 导出CSV

表 9 分项指标总结

Table 9. Summary of sub-indicators

驾驶绩效指标(次数)	眼动指标(次数)	生理心理指标(次数)	反应与面部头部指标(次数)
纵向速度(82)	注视持续时间(13)	心率(17)	制动反应时间(18)
纵向加速度(33)	眨眼频率(12)	脑电信号(15)	次任务反应时间(14)
车道位置(31)	扫视频率(11)	皮电信号(10)	PDT响应时间(12)
方向盘转角(30)	瞳孔直径(8)	心率变异性(9)	次任务正确率(11)
车头间距(20)	眼睛位置坐标(8)	心电信号(5)	PDT命中率(8)
车头时距(19)	注视位置(7)	β波(5)	危险事件反应时间(7)
横向加速度(18)	注视时间(6)	α波(4)	次任务错误率(5)
油门踏板开度(17)	扫视持续时间(6)	θ波(3)	碰撞反应时间(2)
转向熵(13)	平均注视时间(6)	血压(3)	变道时间(2)
方向盘反转率(11)	注视时间百分比(5)	事件相关电位(2)	反应距离(2)
车辆横向位移(11)	总扫视时间(5)	δ波(2)	障碍反应时间(2)
车道偏差(10)	眨眼时间(4)	呼吸量(2)	错误数(2)
方向盘转角角速度(10)	最长扫视时间(4)	额叶(2)	总反应时间(1)
制动踏板开度(9)	扫视次数(3)	呼吸次数(2)	任务转换反应时间(1)
横向速度(8)	偏航注视角(3)	顶叶(2)	总反应数(1)
制动踏板力(8)	眼跳幅度(3)	中央中线(2)	错误反应数(1)
碰撞时间(7)	总注视数(3)	呼吸速率(2)	反应时间变异性(1)
方向盘转速(6)	眼睑开度(3)	左/右枕叶(2)	感知反应时间(1)
横向偏移(6)	总注视时间(3)	单位时间吸空气量(1)	检出率(1)
偏航角(5)	路面注视时间比例(3)	心电变异率(1)	思考时间(1)
转向偏差(5)	平均扫视时间(3)	心电功率(1)	平均失误比例(1)
横向位置(5)	注视次数(3)	电眼图(1)	事件探测率(1)
偏航角速度(5)	最长注视时间(3)	心率间隔(1)	记忆商(1)
速度变异性(4)	注视频率(3)	P300振幅(1)	头部位置(5)
方向盘位置(4)	扫视时间百分比(2)	θ功率(1)	头部旋转角度(3)
纵向减速度(3)	视线离开路面时间(2)	脑前额叶外皮(1)	头偏航角(3)
油门踏板力(3)	扫视时间(2)	皮肤电反应量(1)	头俯仰角(3)
超车次数(3)	单次扫视时间(1)	心电图信号(1)	面部表情(3)
偏离车道次数(3)	视线水平方向角(1)	ERP波幅(1)	嘴唇变化(2)
方向盘最大转角(2)	视线垂直方向角(1)	鼻周电位活动(1)	头倾角(2)
车道偏离持续时间(2)	注视一步转移概率(1)	手掌电位活动(1)	头部最大偏航率(1)
车道变换频率(2)	转向角度(1)	脑电波幅值(1)	唇长与唇宽的比率(1)
方向盘反转数(2)	闭眼时间间隔(1)	脑电波功率对数(1)	眼睛的长宽比例(1)
碰撞次数(2)	注视距离(1)	脑电波功率谱密度(1)	头部姿势(1)

下载: 导出CSV

表 10 分心识别指标优缺点与适用场景

Table 10. Advantages and disadvantages of distraction identification indicators and their applicable scenarios

识别指标	典型指标	优点	缺点	适用场景
驾驶绩效指标	速度、加速度、车道位置、方向盘转角、车头间距、油门踏板开度	容易采集，不需要昂贵的设备费用，适用于对任何分心类型的分析，便于工程实践，容易落地	对驾驶人分心状态的评估和识别准确性不高，数据处理较为繁琐	适用于驾驶分心试验、自然驾驶数据集调用和任何分心类型
眼动指标	注视持续时间、眨眼频率和扫视频率	对视觉分心相关的分心类型检测准确率高	需要使用眼动仪等设备进行采集，对驾驶人的驾驶造成干扰，不易落地	适用于驾驶分心试验和视觉分心等相关分心类型
生理心理指标	心率和脑电信号	对认知分心相关的分心检测准确率高，数据处理简单	需要使用脑电仪、生理心理反馈仪等医学设备进行采集，对驾驶干扰较大，仪器费用昂贵且工程实践困难	适用于驾驶分心试验和认知分心等相关分心类型
反应指标	制动反应时间、次任务反应时间、PDT反应时间	容易采集，不会对驾驶状态造成干扰，可对驾驶人的任务工作量进行测量，并可用于评价指标	仍需要外部设备进行采集，数据采集过程中存在误差，也不容易落地	适用于驾驶分心试验和设计跟驰等复杂设计场景，适用于所有分心类型
面部头部指标	头部位置、头部角度和面部表情	数据类型多样、图像数据适合使用热门的深度学习算法，外部设备采集不易对驾驶人造成干扰，容易落地	操作分心类型检测准确率较高，但其他分心状态检测的准确性有待验证	适用于驾驶分心试验、自然驾驶数据集调用和任何分心类型
融合指标	包含以上指标	不同类型间的指标融合，可保证识别的高准确率，可根据研究内容选择合适的融合指标	不同类型数据的采样频率不同，需要对数据进行同步采集	适用于所有场景和分心类型

下载: 导出CSV

表 11 识别模型分析

Table 11. Identification model analysis

参数	识别模型
参数	SVM	ANN	RF	KNN	其他传统机器学习	混合传统机器学习	深度学习
比例/%	32.14	8.93	12.50	7.14	10.71	3.57	25.00
文献数量	18	5	7	4	6	2	14
平均准确率/%	91.26	92.05	90.60	92.21	86.20	93.85	93.55
准确率最大值/%	98.90	98.45	94.65	98.12	94.00	95.09	96.60
准确率最小值/%	80.00	88.70	85.38	83.50	80.80	92.60	89.00
准确率标准差/%	5.36	4.53	3.03	6.29	4.70	1.25	2.44

下载: 导出CSV

参考文献(96)

[1]	廖源. 基于多源信息融合的驾驶人分心监测研究[D]. 北京: 清华大学, 2015. LIAO Yuan. Driver distraction detection through driving performance and eye movement: from feature extraction to classifier design[D]. Beijing: Tsinghua University, 2015. (in Chinese)
[2]	MCEVOY S P, STEVENSON M R, WOODWARD M. The prevalence of, and factors associated with, serious crashes involving a distracting activity[J]. Accident Analysis and Prevention, 2007, 39(3): 475-482. doi: 10.1016/j.aap.2006.09.005
[3]	PETTITT M, BURNETT G E, STEVENS A. Defining driver distraction[C]//IEEE. 12th World Congress on Intelligent Transport Systems November. New York: IEEE, 2009: 1-12.
[4]	王颖. 基于人机交互仿真的驾驶次任务研究[D]. 北京: 清华大学, 2009. WANG Ying. In-vehicle secondary task study based on human-machine interactive simulation[D]. Beijing: Tsinghua University, 2009. (in Chinese)
[5]	PARKER D, REASON J T, MANSTEAD A S R, et al. Driving errors, driving violations and accident involvement[J]. Ergonomics, 1995, 38(5): 1036-1048. doi: 10.1080/00140139508925170
[6]	WICKENS C D, GORDON S E, LIU Y D. An introduction to human factors engineering[R]. Victoria: University of Victoria, 1998.
[7]	马勇, 石涌泉, 付锐, 等. 驾驶人分心时长对车道偏离影响的实车试验[J]. 吉林大学学报(工学版), 2015, 45(4): 1095-1101. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201504011.htm MA Yong, SHI Yong-quan, FU Rui, et al. Impact of driver's distraction driving time on vehicle lane departure[J]. Journal of Jilin University (Engineering and Technology Edition), 2015, 45(4): 1095-1101. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201504011.htm
[8]	LANSDOWN T C, BROOK-CARTER N, KERSLOOT T. Distraction from multiple in-vehicle secondary tasks: vehicle performance and mental workload implications[J]. Ergonomics, 2004, 47(1): 91-104. doi: 10.1080/00140130310001629775
[9]	DUKIC T, AHLSTROM C, PATTEN C, et al. Effects of electronic billboards on driver distraction[J]. Traffic Injury Prevention, 2013, 14(5): 469-476. doi: 10.1080/15389588.2012.731546
[10]	EBNALI M, AHMADNEZHAD P, SHATERI A, et al. The effects of cognitively demanding dual-task driving condition on elderly people's driving performance; Real driving monitoring[J]. Accident Analysis and Prevention, 2016, 94: 198-206. doi: 10.1016/j.aap.2016.05.016
[11]	彭丹丹, 田伟, 石京. 机导航方式对驾驶行为的影响研究[J]. 中国安全科学学报, 2017, 27(9): 39-44. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201709007.htm PENG Dan-dan, TIAN Wei, SHI Jing. Research on the influences of mobile navigation on driving behavior[J]. China Safety Science Journal, 2017, 27(9): 39-44. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201709007.htm
[12]	王加, 陈慧. 基于驾驶人操纵及车辆运动轨迹信息的驾驶分心辨识方法[J]. 汽车技术, 2013(10): 14-18. doi: 10.3969/j.issn.1000-3703.2013.10.004 WANG Jia, CHEN Hui. Recognition of distraction driving based on driver operation signals and vehicle trajectory[J]. Automobile Technology, 2013(10): 14-18. (in Chinese) doi: 10.3969/j.issn.1000-3703.2013.10.004
[13]	LIN C T, KO L W, SHEN T K. Computational intelligent brain computer interaction and its applications on driving cognition[J]. IEEE Computational Intelligence Magazine, 2009, 4(4): 32-46. doi: 10.1109/MCI.2009.934559
[14]	LIN C T, CHEN S A, CHIU T T, et al. Spatial and temporal EEG dynamics of dual-task driving performance[J]. Journal of NeuroEngineering and Rehabilitation, 2011, 8(1): 11. doi: 10.1186/1743-0003-8-11
[15]	周昱廷. 基于驾驶人在环试验台的注意力分散研究[D]. 长沙: 湖南大学, 2017. ZHOU Yu-ting. The research about distraction based on driver-in-loop simulation experiment[D]. Changsha: Hunan University, 2017. (in Chinese)
[16]	SON J, PARK M. Detection of cognitive and visual distraction using radial basis probabilistic neural networks[J]. International Journal of Automotive Technology, 2018, 19(5): 935-940. doi: 10.1007/s12239-018-0090-4
[17]	KIM S L, YANG J H. Evaluation of the effects of driver distraction part 1: based on simulator experiments[C]//IEEE. 2018 IEEE International Conference on Systems, Man, and Cybernetics. New York: IEEE, 2018: 1081-1086.
[18]	崔健, 赵建有. 驾驶分心对隧道段行车安全影响分析[J]. 安全与环境学报, 2016, 16(6): 174-178. https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201606036.htm CUI Jian, ZHAO Jian-you. Experiment study of the impact of the distracted driving manners on the tunnel traffic safety[J]. Journal of Safety and Environment, 2016, 16(6): 174-178. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201606036.htm
[19]	LIANG Y L, LEE J D. Combining cognitive and visual distraction: less than the sum of its parts[J]. Accident Analysis and Prevention, 2010, 42(3): 881-890. doi: 10.1016/j.aap.2009.05.001
[20]	BOWDEN V K, LOFT S, WILSON M D, et al. The long road home from distraction: investigating the time-course of distraction recovery in driving[J]. Accident Analysis and Prevention, 2019, 124: 23-32. doi: 10.1016/j.aap.2018.12.012
[21]	WÖLLMER M, BLASCHKE C, SCHINDL T, et al. Online driver distraction detection using long short-term memory[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2): 574-582. doi: 10.1109/TITS.2011.2119483
[22]	YANG Y, MCDONALD M, ZHENG P. Can drivers' eye movements be used to monitor their performance? A case study[J]. IET Intelligent Transport Systems, 2012, 6(4): 444-452. doi: 10.1049/iet-its.2012.0008
[23]	LIANG Y, HORREY W J, HOFFMAN J D. Reading text while driving understanding drivers' strategic and tactical adaptation to distraction[J]. Human Factors, 2015, 57(2): 347-359. doi: 10.1177/0018720814542974
[24]	李力. 基于CNNs和LSTM的驾驶人疲劳和分心状态识别研究[D]. 长沙: 湖南大学, 2018. LI Li. A study on recognizing driver fatigue and distraction state by means of CNNs and LSTM[D]. Changsha: Hunan University, 2018. (in Chinese)
[25]	曾淼. 车载信息系统分神对驾驶安全的影响[D]. 广州: 广东工业大学, 2018. ZENG Miao. Research on the influence of vehicle information system distraction on driving safety[D]. Guangzhou: Guangdong University of Technology, 2018. (in Chinese)
[26]	BENDAK S, AL-SALEH K. The role of roadside advertising signs in distracting drivers[J]. International Journal of Industrial Ergonomics, 2010, 40(3): 233-236. doi: 10.1016/j.ergon.2009.12.001
[27]	REIMER B, MEHLER B, COUGHLIN J F, et al. The impact of a naturalistic hands-free cellular phone task on heart rate and simulated driving performance in two age groups[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2011, 14(1): 13-25. doi: 10.1016/j.trf.2010.09.002
[28]	BEEDE K E, KASS S J. Engrossed in conversation: the impact of cell phones on simulated driving performance[J]. Accident Analysis and Prevention, 2006, 38(2): 415-421. doi: 10.1016/j.aap.2005.10.015
[29]	LI Nan-xiang, BUSSO C. Predicting perceived visual and cognitive distractions of drivers with multimodal features[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 51-65. doi: 10.1109/TITS.2014.2324414
[30]	马艳丽, 高月娥, 史惠敏. 车内音频娱乐系统操作对驾驶绩效的影响研究[J]. 武汉理工大学学报(交通科学与工程版), 2017, 41(3): 454-457. doi: 10.3963/j.issn.2095-3844.2017.03.019 MA Yan-li, GAO Yue-e, SHI Hui-min. Effects of in-vehicle audio system operation on driving performance[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering Edition), 2017, 41(3): 454-457. (in Chinese) doi: 10.3963/j.issn.2095-3844.2017.03.019
[31]	BIRRELL S A, YOUNG M S. The impact of smart driving aids on driving performance and driver distraction[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2011, 14(6): 484-493. doi: 10.1016/j.trf.2011.08.004
[32]	LEE J D, MCGEHEE D V, BROWN T L, et al. Collision warning timing, driver distraction, and driver response to imminent rear-end collisions in a high-fidelity driving simulator[J]. Human Factors, 2002, 44(2): 314-334. doi: 10.1518/0018720024497844
[33]	CANTIN V, LAVALLIÈRE M, SIMONEAU M, et al. Mental workload when driving in a simulator: effects of age and driving complexity[J]. Accident Analysis and Prevention, 2009, 41(4): 763-771. doi: 10.1016/j.aap.2009.03.019
[34]	KUTILA M H, JOKELA M, MÄKINEN T, et al. Driver cognitive distraction detection: feature estimation and implementation[J]. Proceedings of The Institution of Mechanical Engineers Part D: Journal of Automobile Engineering, 2007, 221(9): 1027-1040. doi: 10.1243/09544070JAUTO332
[35]	JAHN G, OEHME A, KREMS J F, et al. Peripheral detection as a workload measure in driving: effects of traffic complexity and route guidance system use in a driving study[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2005, 8(3): 255-275. doi: 10.1016/j.trf.2005.04.009
[36]	党珊. 基于手机打车软件使用的驾驶分心行为研究[D]. 成都: 西南交通大学, 2017. DANG Shan. The study of driving distraction behavior based on using the mobile taxi app[D]. Chengdu: Southwest Jiaotong University, 2017. (in Chinese)
[37]	OVIEDO-TRESPALACIOS O, HAQUE M M, KING M, et al. Effects of road infrastructure and traffic complexity in speed adaptation behaviour of distracted drivers[J]. Accident Analysis and Prevention, 2017, 101: 67-77. doi: 10.1016/j.aap.2017.01.018
[38]	CHIANG D P, BROOKS A M, WEIR D H. On the highway measures of driver glance behavior with an example automobile navigation system[J]. Applied Ergonomics, 2004, 35(3): 215-223. doi: 10.1016/j.apergo.2004.01.005
[39]	COOPER J M, VLADISAVLJEVIC I, MEDEIROS-WARD N, et al. An investigation of driver distraction near the tipping point of traffic flow stability[J]. Human Factors, 2009, 51(2): 261-268. doi: 10.1177/0018720809337503
[40]	JONGEN E M M, BRIJS K, MOLLU K, et al. 70 km/h speed limits on former 90 km/h roads: effects of sign repetition and distraction on speed[J]. Human Factors, 2011, 53(6): 771-785. doi: 10.1177/0018720811419848
[41]	TARABAY R, ABOU-ZEID M. Assessing the effects of auditory-vocal distraction on driving performance and physiological measures using a driving simulator[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2018, 58: 351-364. doi: 10.1016/j.trf.2018.06.026
[42]	KIRCHER K, AHLSTORM C. Evaluation of methods for the assessment of attention while driving[J]. Accident Analysis and Prevention, 2017, 114: 40-47.
[43]	ALONSO M, VEGA M H, MARTÍN O. Driving simulation study for the analysis of distraction effects in longitudinal driving behaviour[J]. Cognition, Technology and Work, 2012, 14(4): 283-297. doi: 10.1007/s10111-011-0180-9
[44]	LEE Y C, LEE J D, BOYLE L N. The interaction of cognitive load and attention-directing cues in driving[J]. Human Factors, 2009, 51(3): 271-280. doi: 10.1177/0018720809337814
[45]	顾高峰. 车载信息系统分神对驾驶绩效的影响研究[D]. 黑龙江: 哈尔滨工业大学, 2014. GU Gao-feng. Research on the impact of in-vehicle information system distraction on driving Performance[D]. Heilongjiang: Harbin Institute of Technology, 2014. (in Chinese)
[46]	YAN Wei, WONG S C, LI Y C, et al. Young driver distraction by text messaging: a comparison of the effects of reading and typing text messages in Chinese versus English[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2015, 31: 87-98. doi: 10.1016/j.trf.2015.03.010
[47]	张辉, 钱大琳, 邵春福, 等. 模拟驾驶环境下驾驶人分心状态判别[J]. 中国公路学报, 2018, 31(4): 43-51. doi: 10.3969/j.issn.1001-7372.2018.04.006 ZHANG Hui, QIAN Da-lin, SHAO Chun-fu, et al. Driver's distraction states identification in simulating driving environment[J]. China Journal of Highway and Transport. 2018, 31(4): 43-51. (in Chinese) doi: 10.3969/j.issn.1001-7372.2018.04.006
[48]	李鹏辉, 廖呈玮, 郑志晓, 等. 认知分心对车辆跟驰过程操控安全性的影响[J]. 中国公路学报, 2018, 31(5): 167-173. doi: 10.3969/j.issn.1001-7372.2018.05.020 LI Peng-hui, LIAO Cheng-wei, ZHENG Zhi-xiao, et al. Impact of cognitive distraction on vehicle control safety in car-following situation[J]. China Journal of Highway and Transport, 2018, 31(5): 167-173. (in Chinese) doi: 10.3969/j.issn.1001-7372.2018.05.020
[49]	马欣. 虚拟现实驾驶仿真环境下的驾驶分心研究[D]. 北京: 北方工业大学, 2017. MA Xin. Research on driving distraction in virtual reality driving simulation environment[D]. Beijing: North China University of Technology, 2017. (in Chinese)
[50]	KOUNTOURIOTIS G K, SPYRIDAKOS P, CARSTEN O M J, et al. Identifying cognitive distraction using steering wheel reversal rates[J]. Accident Analysis and Prevention, 2016, 96: 39-45. doi: 10.1016/j.aap.2016.07.032
[51]	高岩, 罗毅, 尤志栋, 等. 手机操作类型对驾驶人跟车行为的影响[J]. 中国公路学报, 2018, 31(4): 1-9, 58. doi: 10.3969/j.issn.1001-7372.2018.04.001 GAO Yan, LUO Yi, YOU Zhi-dong, et al. Influence operating types on smartphone on drivers' car-following behavior[J]. China Journal of Highway and Transport, 2018, 31(4): 1-9, 58. (in Chinese) doi: 10.3969/j.issn.1001-7372.2018.04.001
[52]	LEE J D, CAVEN B, HAAKE S, et al. Speech-based interaction with in-vehicle computers: the effect of speech-based e-mail on drivers' attention to the roadway[J]. Human Factors, 2001, 43(4): 631-640. doi: 10.1518/001872001775870340
[53]	MUHRER E, VOLLRATH M. The effect of visual and cognitive distraction on driver's anticipation in a simulated car following scenario[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2011, 14(6): 555-566. doi: 10.1016/j.trf.2011.06.003
[54]	DOSHI A, TRIVEDI M M. Head and eye gaze dynamics during visual attention shifts in complex environments[J]. Journal of Vision, 2012, 12(2): 1-16. doi: 10.1167/12.2.1
[55]	ROSS V, JONGEN E M, WANG W, et al. Investigating the influence of working memory capacity when driving behavior is combined with cognitive load: an LCT study of young novice drivers[J]. Accident Analysis and Prevention, 2014, 62: 377-387. doi: 10.1016/j.aap.2013.06.032
[56]	KABER D B, LIANG Yu-lan, ZHANG Yu, et al. Driver performance effects of simultaneous visual and cognitive distraction and adaptation behavior[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2012, 15(5): 491-501. doi: 10.1016/j.trf.2012.05.004
[57]	ZHANG Y, KABER D B, ROGERS M, et al. The effects of visual and cognitive distractions on operational and tactical driving behaviors[J]. Human Factors, 2014, 56(3): 592-604. doi: 10.1177/0018720813495279
[58]	CHAN M, SINGHAL A. The emotional side of cognitive distraction: implications for road safety[J]. Accident Analysis and Prevention, 2013, 50: 147-154. doi: 10.1016/j.aap.2012.04.004
[59]	HASHASH M, ZEID M A, MOACDIEH N M, et al. Social media browsing while driving: effects on driver performance and attention allocation[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2019, 63: 67-82. doi: 10.1016/j.trf.2019.03.021
[60]	GARRISON T M, WILLIAMS C C. Impact of relevance and distraction on driving performance and visual attention in a simulated driving environment[J]. Applied Cognitive Psychology, 2013, 27(3): 396-405. doi: 10.1002/acp.2917
[61]	郑志晓. 视觉分神对驾驶人行为的影响研究[D]. 北京: 清华大学, 2017. ZHENG Zhi-xiao. Research on the impact of visual distraction on driving behaviors[D]. Beijing: Tsinghua University, 2017. (in Chinese)
[62]	CHISHOLM S L, CAIRD J K, LOCKHART J. The effects of practice with MP3 players on driving performance[J]. Accident Analysis and Prevention, 2008, 40(2): 704-713. doi: 10.1016/j.aap.2007.09.014
[63]	NOWOSIELSKI R J, TRICK L M, TOXOPEUS R. Good distractions: testing the effects of listening to an audiobook on driving performance in simple and complex road environments[J]. Accident Analysis and Prevention, 2018, 111: 202-209. doi: 10.1016/j.aap.2017.11.033
[64]	ZHANG H, SMITH M R H, WITT G J. Identification of real-time diagnostic measures of visual distraction with an automatic eye-tracking system[J]. Human Factors, 2006, 48(4): 805-821. doi: 10.1518/001872006779166307
[65]	TOPOLŠEK D, AREH I, CVAHTE T. Examination of driver detection of roadside traffic signs and advertisements using eye tracking[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2016, 43: 212-224. doi: 10.1016/j.trf.2016.10.002
[66]	STAVRINOS D, JONES J L, GAMER A A, et al. Impact of distracted driving on safety and traffic flow[J]. Accident Analysis and Prevention, 2013, 61: 63-70. doi: 10.1016/j.aap.2013.02.003
[67]	WESTER A E, BÖCKER K B E, VOLKERTS E R, et al. Event-related potentials and secondary task performance during simulated driving[J]. Accident Analysis and Prevention, 2008, 40(1): 1-7. doi: 10.1016/j.aap.2007.02.014
[68]	HORREY W J, LESCH M F, GARABET A, et al. Dissociation between driving performance and drivers' subjective estimates of performance and workload in dual-task conditions[J]. Journal of Safety Research, 2009, 40(1): 7-12. doi: 10.1016/j.jsr.2008.10.011
[69]	WAARD D, BROOKHUIS K A, HERNÁNDEZ-GRESS N. The feasibility of detecting phone-use related driver distraction[J]. International Journal of Vehicle Design, 2001, 26(1): 85-95. doi: 10.1504/IJVD.2001.001931
[70]	ENGSTRÖM J, JOHANSSON E, ÖSTLUND J. Effects of visual and cognitive load in real and simulated motorway driving[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2005, 8(2): 97-120. doi: 10.1016/j.trf.2005.04.012
[71]	LIANG Y L, LEE J D. A hybrid Bayesian network approach to detect driver cognitive distraction[J]. Transportation Research Part C: Emerging Technologies, 2014, 38: 146-155. doi: 10.1016/j.trc.2013.10.004
[72]	DESHMUKH S, DEHZANGI O. Identification of real-time driver distraction using optimal subband detection powered by wavelet packet transform[C]//IEEE. 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks. New York: IEEE, 2017: 9-12.
[73]	LIU Tian-chi, YANG Yan, HUANG Guang-bin, et al. Cluster regularized extreme learning machine for detecting mixed-type distraction in driving[C]//IEEE. 2015 IEEE 18th International Conference on Intelligent Transportation Systems. New York: IEEE, 2015: 1323-1326.
[74]	姚莹. 基于视觉特征的驾驶人分心驾驶行为甄别方法研究[D]. 北京: 北京工业大学, 2017. YAO Ying. Detection method of distracted driving based on visual features and behavior data[D]. Beijing: Beijing University of Technology, 2017. (in Chinese)
[75]	PRAT F, PLANES M, GRAS M E, et al. An observational study of driving distractions on urban roads in Spain[J]. Accident Analysis and Prevention, 2014, 74: 8-16. http://europepmc.org/abstract/med/25463939
[76]	YOUNG K L, LENNÉ M G. Driver engagement in distracting activities and the strategies used to minimise risk[J]. Safety Science, 2010, 48(3): 326-332. doi: 10.1016/j.ssci.2009.10.008
[77]	HOANG NGAN LE T, ZHENG Yu-tong, ZHU Chen-chen, et al. Multiple scale Faster-RCNN approach to driver's cell-phone usage and hands on steering wheel detection[C]//IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. New York: IEEE, 2016: 46-53.
[78]	WONG J T, HUANG S H. Attention allocation patterns in naturalistic driving[J]. Accident Analysis and Prevention, 2013, 58: 140-147. doi: 10.1016/j.aap.2013.04.033
[79]	TIVESTEN E, DOZZA M. Driving context and visual-manual phone tasks influence glance behavior in naturalistic driving[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2014, 26: 258-272. doi: 10.1016/j.trf.2014.08.004
[80]	PRZYBYLA J, TAYLOR J, JUPE J, et al. Estimating risk effects of driving distraction: a dynamic errorable car-following model[J]. Transportation Research Part C: Emerging Technologies, 2014, 50: 117-129. http://www.sciencedirect.com/science/article/pii/S0968090X14002150
[81]	WANG Yuan, BAO Shan, DU Wen-jun, et al. A spectral power analysis of driving behavior changes during the transition from non-distraction to distraction[J]. Traffic Injury Prevention, 2017, 18(8): 826-831. doi: 10.1080/15389588.2017.1320549
[82]	OSMAN O A, HAJIJ M, KARBALAIEALI S, et al. A hierarchical machine learning classification approach for secondary task identification from observed driving behavior data[J]. Accident Analysis and Prevention, 2019, 123: 274-281. doi: 10.1016/j.aap.2018.12.005
[83]	孙剑, 张一豪, 王俊骅. 基于自然驾驶数据的分心驾驶行为识别方法[J]. 中国公路学报, 2020, 33(9): 225-235. doi: 10.3969/j.issn.1001-7372.2020.09.022 SUN Jian, ZHANG Yi-hao, WANG Jun-hua. Detecting driver distraction behavior with naturalistic driving data[J]. China Journal of Highway and Transport, 2020, 33(9): 225-235. (in Chinese) doi: 10.3969/j.issn.1001-7372.2020.09.022
[84]	张兰芳, 崔博宇, 王俊骅, 等. 自然驾驶状态下使用手机对驾驶控制行为的影响[J]. 同济大学学报(自然科学版), 2019, 47(12): 1756-1763. doi: 10.11908/j.issn.0253-374x.2019.12.010 ZHANG Lan-fang, CUI Bo-yu, WANG Jun-hua, et al. Effects of naturalistic mobile phone operations on driving control behavior[J]. Journal of Tongji University (Natural Science), 2019, 47(12): 1756-1763. (in Chinese) doi: 10.11908/j.issn.0253-374x.2019.12.010
[85]	BACKER-GRØNDAHL A, SAGBERG F. Driving and telephoning: relative accident risk when using hand-held and hands-free mobile phones[J]. Safety Science, 2011, 49(2): 324-330. doi: 10.1016/j.ssci.2010.09.009
[86]	MASALA G L, GROSSO E. Real time detection of driver attention: emerging solutions based on robust iconic classifiers and dictionary of poses[J]. Transportation Research Part C: Emerging Technologies, 2014, 49: 32-42. doi: 10.1016/j.trc.2014.10.005
[87]	HU Jun, LIU Wei, KANG Jia-wen, et al. Semi-cascade network for driver's distraction recognition[J]. Automobile Engineering, 2019, 233(9): 2323-2332. doi: 10.1177/0954407019857408
[88]	ERAQI H M, ABOUELNAGA Y, SAAD M H, et al. Driver distraction identification with an ensemble of convolutional neural networks[J]. Journal of Advanced Transportation, 2019, 2019: 4125865. http://arxiv.org/abs/1901.09097v1
[89]	TRAN D, DO H M, SHENG Wei-hua, et al. Real-time detection of distracted driving based on deep learning[J]. IET Intelligent Transport Systems, 2018, 12(10): 1210-1219. doi: 10.1049/iet-its.2018.5172
[90]	BAHETI B, GAJRE S, TALBAR S. Detection of distracted driver using convolutional neural network[C]//IEEE. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New York: IEEE, 2018: 1032-1038.
[91]	JONES M P, CHAPMAN P, BAILEY K. The influence of image valence on visual attention and perception of risk in drivers[J]. Accident Analysis and Prevention, 2014, 73: 296-304. doi: 10.1016/j.aap.2014.09.019
[92]	KOUNTOURIOTIS G K, WILKIE R M, GARDNER P H, et al. Looking and thinking when driving: the impact of gaze and cognitive load on steering[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2015, 34: 108-121. doi: 10.1016/j.trf.2015.07.012
[93]	HARADA T, MORI K, YOSHIZAWA A, et al. SS3: a design of the cognitive process model for a car driver considering quantitatively expressed distraction[C]//IEEE 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing. New York: IEEE, 2014: 273-280.
[94]	BILLAH T, MAHBUBUR RAHMAN S M. Tracking-based detection of driving distraction from vehicular interior video[C]//IEEE. 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance. New York: IEEE, 2016: 423-428.
[95]	DEHZANGI O, TAHERISADR M. Driver distraction detection using MEL cepstrum representation of galvanic skin responses and convolutional neural networks[C]//IEEE. 2018 24th International Conference on Pattern Recognition. New York: IEEE, 2018: 1481-1486.
[96]	TORRES R, OHASHI O, PESSIN G. A machine-learning approach to distinguish passengers and drivers reading while driving[J]. Sensors, 2019, 19(14): 3174. doi: 10.3390/s19143174