无信号交叉口人车冲突严重程度影响因素分析

doi:10.16265/j.cnki.issn1003-3033.2023.08.1084

摘要/Abstract

摘要：

为提高无信号交叉口通行效率并改善行人过街安全性,利用K-means++算法聚类冲突指标以判定人车冲突严重程度,通过多重共线性检验和皮尔逊相关性分析剔除严重共线性和影响不显著的因素,并进行影响因素强弱程度排序,采用多元有序Logistic回归算法,对比分析各显著独立因素对人车冲突严重程度的具体影响。结果表明:以碰撞时间、间隙时间、安全减速度为冲突指标,可将人车冲突严重程度分为严重、一般和轻微冲突;行人特征中,性别、分心行为、等候时间、平均穿越速度以及是否有人陪同对冲突严重程度的影响强弱程度依次减小;车辆特征中,车头时距、行驶意图和车辆类型对冲突严重程度有显著影响。

关键词: 无信号交叉口, 人车冲突严重程度, 影响因素, K-means++算法, 多元有序Logistic回归

Abstract:

In order to improve the crossing efficiency at unsignalized intersections and the safety of pedestrian crossings, K-means++ algorithm was used to cluster the conflict indicators to determine the severity of vehicle-pedestrian conflict. Severe multicollinearity and insignificant influencing factors were eliminated by multi-collinearity test and Pearson correlation analysis, and then the influencing factors were ranked. Multiple ordered Logistic regression algorithm was used to compare and analyze the specific influence of each significant independent factor on the severity of vehicle-pedestrian conflicts. The results show that the severity of vehicle-pedestrian conflicts can be divided into severe, general and minor conflicts by taking time to collision, gap time and deceleration to safety time as conflict indicators. The influence of gender, distracted behavior, waiting time, average crossing speed and whether accompanied by others on the severity of conflict decreased successively among the pedestrian characteristics. Headway, driving intention and vehicle type have significant effects on the severity of conflict among the vehicle characteristics.

Key words: unsignalized intersections, severity of vehicle-pedestrian conflict, influencing factors, K-means++ algorithm, multi-variate ordered Logistic regression

张名芳, 马艳华, 马勇. 无信号交叉口人车冲突严重程度影响因素分析[J]. 中国安全科学学报, 2023, 33(8): 190-197.

ZHANG Mingfang, MA Yanhua, MA Yong. Influencing factors on severity of vehicle-pedestrian conflict at unsignalized intersections[J]. China Safety Science Journal, 2023, 33(8): 190-197.

图/表 8

图1

图2

表1

冲突指标最终聚类中心

冲突指标	分类
冲突指标	严重冲突	一般冲突	轻微冲突
$t T m i n$	1.13	2.03	3.26
$t G m i n$	0.59	0.88	2.59
$a p m a x$	2.01	1.16	0.48
$a v m a x$	1.44	0.61	0.32

表1

表2

单因素方差分析结果

冲突指标	F	显著性
$t T m i n$	8.736	0.000
$t G m i n$	3.001	0.004
$a p m a x$	69.096	0.000
$a v m a x$	61.931	0.000

表2

表3

图3

表4

表5

参考文献 21

[1]	许伦辉, 骈宇庄, 林永杰, 等. 基于累积前景理论的无信控路段人车通行冲突博弈分析[J]. 中国公路学报, 2022, 35(1):119-136. doi: 10.19721/j.cnki.1001-7372.2022.01.011
	XU Lunhui, PIAN Yuzhuang, LIN Yongjie, et al. Game analysis of conflict between pedestrians and vehicular traffic on unsignalized sections based on cumulative prospect theory[J]. China Journal of Highway and Transport, 2022, 35(1):119-136. doi: 10.19721/j.cnki.1001-7372.2022.01.011
[2]	王俊骅, 方守恩. 路段行人-机动车冲突观测方法及冲突特性[J]. 同济大学学报:自然科学版, 2008, 36(4):503-507.
	WANG Junhua, FANG Shouen. Pedestrian-Vehicle conflict observation and characteristics of road section[J]. Journal of Tongji University :Natural Science, 2008, 36(4):503-507.
[3]	吴佩洁, 孟祥海, 曹梦迪. 城市交通事故多发点鉴别与时空模式挖掘[J]. 中国安全科学学报, 2020, 30(11):127-133. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.019
	WU Peijie, MENG Xianghai, CAO Mengdi. Identification of black spots in urban roads and spatiotemporal patterns mining[J]. China Safety Science Journal, 2020, 30(11):127-133. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.019
[4]	孙璐, 李颜平, 钱军, 等. 基于交通冲突技术的交织区交通安全评价[J]. 中国安全科学学报, 2013, 23(1):55-60.
	SUN Lu, LI Yanping, QIAN Jun, et al. Evaluation of weaving sections with respect to traffic safety based on traffic conflict technique[J]. China Safety Science Journal, 2013, 23(1):55-60.
[5]	兰柳亭, 徐磊, 龚毅, 等. 行人与右转车辆冲突严重度评估[J]. 重庆理工大学学报:自然科学, 2022, 36(7):70-77.
	LAN Liuting, XU Lei, GONG Yi, et al. Evaluation of the conflict severity between pedestrians and right-turning vehicles[J]. Journal of Chongqing University of Technology:Natural Science, 2022, 36(7):70-77.
[6]	韩勇, 袁小宾, 卢明, 等. 汽车与电动两轮车碰撞典型场景下的AEB纵横向触发策略研究[J]. 汽车工程, 2023, 45(3): 501-509.
	HAN Yong, YUAN Xiaobin, LU Ming, et al. Research on AEB longitudinal and transverse triggering strategy in typical scenarios of vehicle to electric two-wheelers collisions[J]. Automotive Engineering, 2023, 45(3):501-509.
[7]	沈志远, 胡莹莹. 考虑尾流影响的侧向双跑道机场的跑道容量研究[J]. 南京航空航天大学学报, 2020, 52(1):161-170.
	SHEN Zhiyuan, HU Yingying. Runway capacity of lateral double-runway airport considering wake effect[J]. Journal of Nanjing University of Aeronautics and Astronsutics, 2020, 52(1):161-170.
[8]	李兴佳, 李建芬, 朱敏, 等. 基于无迹卡尔曼滤波的定位融合与校验算法研究[J]. 汽车工程, 2021, 43(6):825-832.
	LI Xingjia, LI Jianfen, ZHU Min, et al. Research on positioning fusion and verification algorithm based on UKF[J]. Automotive Engineering, 2021, 43(6):825-832.
[9]	TAGELDIN A, SAYED T. Developing evasive action-based indicators for identifying pedestrian conflicts in less organized traffic environments[J]. Journal of Advanced Transportation, 2016, 50(6):1193-1208. doi: 10.1002/atr.v50.6
[10]	MUPPAK R, TALLAM T. Vehicle pedestrian interaction analysis at unsignalized intersection using trajectory data[J]. IOP Conference Series: Earth and Environmental Science, 2022, 982(1):1257-1266.
[11]	周竹萍, 王炜, 任刚, 等. 信号交叉口行人交通冲突特性及影响因素分析[J]. 东南大学学报:自然科学版, 2014, 44(6):1294-1298.
	ZHOU Zhuping, WANG Wei, REN Gang, et al. Analysis on characteristics and influential factors of pedestrian conflicts with vehicles at signalized intersections[J]. Journal of Southeast University:Natural Science Edition, 2014, 44(6):1294-1298.
[12]	KUMAR A, PAUL M, GHOSH I. Analysis of pedestrian conflict with right-turning vehicles at signalized intersections in India[J]. Journal of Transportation Engineering Part A: Systems, 2019, 145(6):451-463.
[13]	SHEYKHFARD, ABBAS. Analysis of the occurrence and severity of vehicle-pedestrian conflicts in marked and unmarked crosswalks through naturalistic driving study[J]. Transportation Research Part F: Traffic Psychology and Behavior, 2021, 76 (3):178-192. doi: 10.1016/j.trf.2020.11.008
[14]	陈永恒, 刘芳宏, 曹宁博. 信控交叉口行人与提前右转机动车冲突影响因素[J]. 吉林大学学报:工学版, 2018, 48(6):1669-1676.
	CHEN Yongheng, LIU Fanghong, CAO Ningbo. Analysis of conflict factors between pedestrians and channelized right turn vehicles at signalized intersections[J]. Journal of Jilin University:Engineering and Technology Edition, 2018, 48(6):1669-1676.
[15]	TRUONG L T, THAI H, LE T V, et al. Pedestrian distraction: mobile phone use and its associations with other risky crossing behaviours and conflict situations[J]. Safety Science, 2022, 153(1):105816-105 825.
[16]	汪钰涵, 马国杰, 庄想灵. 手机分心对行人过街中信息加工及行为的影响[J]. 心理科学进展, 2021, 29(5): 806-816. doi: 10.3724/SP.J.1042.2021.00806
	WANG Yuhan, MA Guojie, ZHUANG Xiangling. The effect of cell phone distraction on pedestrians' information processing and behavior during road crossing[J]. Advances in Psychological Science, 2021, 29(5):806-816. doi: 10.3724/SP.J.1042.2021.00806
[17]	金辉, 吕明. 基于得分系数的跟车工况驾驶风格识别研究[J]. 北京理工大学学报, 2021, 41(3): 245-250.
	JIN Hui, LYU Ming. Driving style recognition based on the score coefficient under the following condition[J]. Transactions of Beijing Institute of Technology, 2021, 41(3): 245-250.
[18]	REN Quan, ZHANG Hongbing, ZHANG Dailu, et al. A novel hybrid method of lithology identification based on K-means++ algorithm and fuzzy decision tree[J]. Journal of Petroleum Science and Engineering, 2022, 208(1): 109 681-109 693.
[19]	王建仁, 马鑫, 段刚龙. 改进的K-means聚类k值选择算法[J]. 计算机工程与应用, 2019, 55(8): 27-33. doi: 10.3778/j.issn.1002-8331.1810-0075
	WANG Jianren, MA Xin, DUAN Ganglong. Improved K-means clustering k-value selection algorithm[J]. Computer Engineering and Applications, 2019, 55(8): 27-33. doi: 10.3778/j.issn.1002-8331.1810-0075
[20]	包银鑫, 曹阳, 施佺. 基于改进时空残差卷积神经网络的城市路网短时交通流预测[J]. 计算机应用, 2022, 42(1): 258-264. doi: 10.11772/j.issn.1001-9081.2021010080
	BAO Yinxin, CAO Yang, SHI Quan. Improved spatio-temporal residual convolutional neural network for urban road network short-term traffic flow prediction[J]. Journal of Computer Applications, 2002, 42(1): 258-264.
[21]	王辛岩, 李天娇. 基于PCA和有序logistics回归的驾驶工作负荷影响因素分析[J]. 数学的实践与认识, 2020, 50(22): 78-84.
	WANG Xinyan, LI Tianjiao. Analysis of factors affecting driving activity workload based on PCA and ordered logistic regression[J]. Mathematics in Practice and Theory, 2020, 50(22): 78-84.

序号	影响因素	共线性统计
序号	影响因素	容忍度	VIF
1	行人年龄	0.028	35.371
2	行人性别	0. 141	7.093
3	行人是否带东西	0.334	2.990
4	行人是否有人陪同	0.276	3.617
5	行人平均穿越速度	0.170	5.872
6	行人等候时间	0.428	2.335
7	行人延误	0.036	28.063
8	行人分心行为	0.243	4.117
9	车辆旅行时间	0.332	3.008
10	车头时距	0.313	3.197
11	车辆类型	0.399	2.506
12	车辆行驶意图	0.717	1.394

排序	影响因素	相关系数
1	行人性别	-0.67
2	行人分心行为	0.65
3	车头时距	0.58
4	行人等候时间	-0.55
5	车辆行驶意图	0.49
6	行人平均穿越速度	-0.46
7	车辆类型	-0.34
8	行人是否有人陪同	0.27

影响因素	分类	严重冲突		一般冲突
影响因素	分类	B	Sig.	B	Sig.
行人性别	1:女	-3.015	0.000	-3.297	0.001
行人性别	2:男	0^b	—	—	—
行人分心行为	1:使用手机	3.397	0.009	2.915	0.004
	2:与同伴聊天	3.225	0.013	2.641	0.017
	3:否	0^b	—	—	—
车头时距	1:[0.5,10.2]	3.197	0.000	3.117	0.012
	2:(10.2,29.6]	3.338	0.001	3.004	0.001
	3:(29.6,68.4]	0^b	—	—	—
行人等候时间	1:[0,4.2]	-2.792	0.009	-2.663	0.026
	2:(4.2,12.6]	-2.994	0.017	-2.875	0.031
	3:[27.3,29.4]	0^b	—	—	—
车辆行驶意图	1:左转	2.577	0.004	2.441	0.000
	2:右转	2.349	0.009	2.096	0.037
	3:直行	0b	—	—	—
行人平均穿越速度	1:[0,0.56]	-1.709	0.000	-1.611	0.006
	2:(0.56,1.09]	-1.883	0.000	-1.598	0.000
	3:(1.09,1.49]	-2.164	0.003	-1.930	0.015
	4:(1.49,2.01]	0^b	—	—	—
车辆类型	1:大客(货)车	-1.779	0.006	-1.699	0.001
	2:小轿车	-1.895	0.000	-1.758	0. 000
	3:三轮车	0^b	—	—	—
行人是否有人陪同	1:没有	1.507	0.015	1.425	0.011
	2:一个	1.491	0.008	1.147	0.039
	3: 大于一个	0^b	—	—	—