货车-两轮车碰撞事故典型场景提取及关联规则分析

doi:10.3969/j.issn.1674-8484.2024.04.006

摘要/Abstract

摘要：

基于视频信息提取了货车-两轮车碰撞典型事故场景，对事故场景中不同事故因素间的相关性进行了挖掘以补充代表事故遗漏的事故特征。应用210例带视频信息的货车-两轮车碰撞事故案例获取相关事故信息，采用 K-modes聚类方法对事故案例进行聚类得到典型事故场景，采用关联规则方法对每个事故场景中事故因素之间的关联度进行分析。结果表明：货车-两轮车事故可分为4种典型场景，即2种十字路口事故，1种直行道路事故以及1种丁字路口事故。十字路口事故场景中事故特征与存在视觉障碍关联度较高，且在十字路口事故中“货车左转”所带来的风险也比较高；直行道路事故中货车制动规避与道路上是否有信号灯存在关联性；丁字路口事故中型货车转向规避与骑车人遭到碾压之间存在关联性。该研究结果可以为两轮车骑车人安全对策和安全测试场景提供参考。

关键词: 汽车安全, 交通事故视频, 货车, 两轮车, K-modes聚类, 关联规则分析

Abstract:

Typical accident scenarios of truck-two-wheeler collisions were extracted based on video information. The correlation among accident factors within these scenarios was explored using association rules analysis to elucidate accident characteristics that were not typically described by typical accidents. Accident information was extracted from 210 cases of truck-two-wheeler accidents with accompanying video information sourced from the internet. These cases were then subjected to K-modes clustering to obtain typical accident scenarios. Subsequently, association rule mining was employed to analyze the degree of association among accident factors within each accident scenario. The results show that truck-two-wheeler accidents can be categorized into four typical scenarios, namely two types of intersection accidents, one straight road accident, and one T-junction accident. In intersection accidents, there is a high association between accident features and the presence of visual obstacle. The accident featuring a “truck turning left” will cause high accident risk. In straight road accidents, there is an association between truck braking for avoidance and the presence of traffic signals on the road. In T-junction accidents, there is an association between medium-sized truck steering for avoidance and two-wheeler riders being crushed. These research findings can provide reference to safety measures and safety testing scenarios for two-wheeler riders.

Key words: automotive safety, traffic accident video, truck, two-wheelers, K-modes cluster, association rules

中图分类号:

U461.91

聂进, 张翔, 张越, 王丙雨, 易向贤, 周伍. 货车-两轮车碰撞事故典型场景提取及关联规则分析[J]. 汽车安全与节能学报, 2024, 15(4): 503-510.

NIE Jin, ZHANG Xiang, ZHANG Yue, WANG Bingyu, YI Xiangxian, ZHOU Wu. Typical accident scene extraction and accident factor association rules analysis for truck-two-wheeler collisions[J]. Journal of Automotive Safety and Energy, 2024, 15(4): 503-510.

图/表 11

参考文献 21

[1]	康义. 中国统计年鉴(2023): 交通事故情况[EB/OL]. [2024-07-20]. https://www.stats.gov.cn/sj/ndsj/2023/indexch.htm.
	KANG Yi. China Statistical Yearbook-2023: Traffic Accident Situation[EB/OL]. [2024-07-20]. https://www.stats.gov.cn/sj/ndsj/2023/indexch.htm. (in Chinese)
[2]	Keall M D, Newstead S. Analysis of factors that increase motorcycle rider risk compared to car driver risk[J]. Accid Anal Prev, 2012, 49: 23-29. doi: 10.1016/j.aap.2011.07.001 pmid: 23036378
[3]	王卫杰, 沈轩霆, 王贵彬, 等. 电动自行车骑行者事故伤害程度影响因素分析[J]. 中国安全科学学报, 2019, 29(2): 20-25.
	WANG Weijie, SHEN Xuanting, WANG Guibin, et al. Analysis of factors affecting injury to electric bicycle rider in crash[J]. Chin Safe Sci J, 2019, 29(2): 20-25. (in Chinese)
[4]	张道文, 李敏, 庞劭荣, 等. 重型货车与二轮车事故致因及其拓扑层级分析[J]. 汽车安全与节能学报, 2023, 14(2): 157-164.
	ZHANG Daowen, LI Min, PANG Shaorong, et al. Accident causes and its topological hierarchy analysis for heavy-duty trucks and two-wheelers[J]. J Autom Safe Energ, 2023, 14(2): 157-164. (in Chinese)
[5]	ZHAO Yuqing, Ito D, Mizuno K. AEB effectiveness evaluation based on car-to-cyclist accident reconstructions using video of drive recorder[J]. Traf Inju Prev, 2019, 20(1): 100-106.
[6]	Euro NCAP. Commercial van test and assessment protocol[EB/OL]. [2024-7-20]. https://cdn.euroncap.com/media/67254/euro-ncap-assessment-protocol-sa-v91.pdf.
[7]	中国汽车技术研究中心有限公司. C-NCAP管理规则(2024年版)[S/OL]. 天津: 中国汽车技术研究中心. [2024-1-18]. https://cncap.obs.cn-north-4.myhuaweicloud.com/cms/files/769801002080616448.zip.
	China Automotive Engineering Research Institute Co., Ltd. C-NCAP manage rules (2024 Vers)[S/OL]. Tianjing: China Automotive Engineering Research Institute. [2024-1-18]. https://cncap.obs.cn-north-4.myhuaweicloud.com/cms/files/769801002080616448.zip. (in Chinese)
[8]	蒋骏, 王朝健, 李哓艳. 面向AEB测试的汽车与不同二轮车典型事故场景构建[J]. 公路与汽运, 2023 (2): 32-39.
	JIANG Jun, WANG Chaojian, LI Xiaoyan. Construction of typical accident scenarios for cars and different two-wheelers for AEB testing[J]. Highway Autom Appl, 2023 (2): 32-39. (in Chinese)
[9]	胡林, 李根, 王方, 等. 基于CIDAS事故数据的路口乘用车-两轮车测试场景研究[J]. 汽车工程, 2023, 45(8): 1417-1427.
	HU Lin, LI Gen, WANG Fang, et al. Research on test scenarios of passenger cars and two-wheelers at intersections based on CIDAS accident data[J]. Autom Engineering, 2023, 45(8): 1417-1427. (in Chinese)
[10]	邹铁方, 刘前程, 魏亮. 加装传统AEB后的未避免事故典型碰撞场景与事故特征[J]. 汽车工程, 2023, 45(6): 1062-1072.
	ZOU Tiefang, LIU Qiancheng, WEI Liang. Typical collision scenarios and accident characteristics of accidents not avoided after installing traditional AEB[J]. Autom Engineering, 2023, 45(6): 1062-1072. (in Chinese)
[11]	韩勇, 贺伟, 李泉, 等. 基于视频信息的汽车碰撞事故中骑车人运动学响应分析[J]. 汽车安全与节能学报, 2017, 8(4): 381-387.
	HAN Yong, HE Wei, LI Quan, et al. Analysis of two-wheelers kinematics before/during/after vehicle collisions based on video records[J]. Chin J Autom Engi, 2017, 8(4): 381-387. (in Chinese)
[12]	吴良伟, 邹铁方, 刘阳阳, 等. 基于视频的自行车事故特征及控制人致伤因素观察[J]. 汽车工程学报, 2021, 11(6): 393-403+412.
	WU Liangwei, ZOU Tiefang, LIU Yangyang, et al. Observation on characteristics of bicycle accidents and injury factors for bicycle riders based on video recordings[J]. Chin J Autom Engi, 2021, 11(6): 393-403+412. (in Chinese)
[13]	ZHAO Yuqing, Miyahara T, Mizuno K, et al. Analysis of car driver responses to avoid car-to-cyclist perpendicular collisions based on drive recorder data and driving simulator experiments[J]. Accid Anal Prev, 2021, 150: 105862.
[14]	PAN Di, HAN Yong, JIN Qianqian, et al. Study of typical electric two-wheelers pre-crash scenarios using k-medoids clustering methodology based on video recordings in China[J]. Accid Anal Prev, 2021, 160: 106320.
[15]	中华人民共和国公安部. GA 802-2019: 道路交通管理机动车类型[S/OL]. (2019-6-15). https://hbba.sacinfo.org.cn/attachment/onlineRead/f5b97e669ecd2c6e66110ac554abb6938fe1d92996727162f185eeff93ceaea7.
	Ministry of Public Security of the People's Republic of China. GA 802-2019: Road traffic management-types of motor vehicles[S/OL]. (2019-6-15). https://hbba.sacinfo.org.cn/attachment/onlineRead/f5b97e669ecd2c6e66110ac554abb6938fe1d92996727162f185eeff93ceaea7. (in Chinese)
[16]	聂进, 杨济匡. 基于汽车-自行车碰撞事故重建的骑车人动力学响应和损伤研究[J]. 汽车工程, 2015, 37(2): 160-167.
	NIE Jin, YANG Jikuang. A Study on the dynamic response and injury of cyclist based on car-bicycle accident reconstruction[J]. Autom Engineering, 2015, 37(2): 160-167. (in Chinese)
[17]	中国国家标准化管理委员会. GB/T 33195-2016: 道路交通事故车辆速度鉴定[S/OL]. (2016-12-13). http://c.gb688.cn/bzgk/gb/showGb?type=online&hcno=4477946C3B913E4307355223CB323A0B.
	Standardization Administration of the People's Republic of China. GB/T 33195-2016: Identification for the speed of vehicle involved in road traffic accident[S]. (2016-12-13). http://c.gb688.cn/bzgk/gb/showGb?type=online&hcno=4477946C3B913E4307355223CB323A0B. (in Chinese)
[18]	中华人民共和国公安部. GA/T 1133-2014: 基于视频图像的车辆行驶速度技术鉴定[S/OL]. (2014-2-10). .
	Ministry of Public Security of the People's Republic of China. GA/T 1133-2014: Vehicle speed identification based on video[S/OL]. (2014-2-10). https://www.nssi.org.cn/cssn/js/pdfjs/web/preview.jsp?a100=GA/T%201133-2014. (in Chinese).
[19]	韩学源, 金先龙, 张晓云, 等. 基于视频图像与直接线性变换理论的车辆运动信息重构[J]. 汽车工程, 2012, 34 (12): 1145-1149.
	HAN Xueyuan, JIN Xianlong, ZHANG Xiaoyun, et al. Vehicle movement information reconstruction based on video image and DLT theory[J]. Autom Engineering, 2012, 34(12): 1145-1149. (in Chinese)
[20]	Montella A. Identifying crash contributory factors at urban roundabouts and using association rules to explore their relationships to different crash types[J]. Accid Anal Prev, 2011, 43(4): 1451-1463. doi: 10.1016/j.aap.2011.02.023 pmid: 21545878
[21]	Liao Chia-wen, Perng Yeng-horng. Data mining for occupational injuries in the Taiwan construction industry[J]. Safe Sci, 2008, 46(7): 1091-1102.

场景	方法
机动车直线行驶且摄像机位置固定	逐帧法计算速度
机动车转向、摄像机位置固定且视频画面中有可知距离的固定参考点(如人行横道线、地面交通标识等)	通过DLT计算速度
碰撞场景有对应的经验公式且其他方法失效	《道路交通事故车辆速度鉴定》中对应场景经验公式计算速度

场景	方法
机动车直线行驶且摄像机位置固定	逐帧法计算速度
机动车转向、摄像机位置固定且视频画面中有可知距离的固定参考点(如人行横道线、地面交通标识等)	通过DLT计算速度
碰撞场景有对应的经验公式且其他方法失效	《道路交通事故车辆速度鉴定》中对应场景经验公式计算速度

分类	样本数	货车v (km·h^-1)	碰撞角度 (°)	应急措施
1簇	39	20	30~60	两轮车转向，骑车人遭到碾压
2簇	75	10	90~120	货车制动
3簇	64	30	90~120	无，骑车人被抛出
4簇	37	20	30~60	无，骑车人遭到碾压

分类	样本数	货车v (km·h^-1)	碰撞角度 (°)	应急措施
1簇	39	20	30~60	两轮车转向，骑车人遭到碾压
2簇	75	10	90~120	货车制动
3簇	64	30	90~120	无，骑车人被抛出
4簇	37	20	30~60	无，骑车人遭到碾压

规则序号	前项	后项	置信度	提升度	支持度
1	{两轮车直行，货车直行，无碾压，骑车人无转向}	{无视觉障碍}	0.97	1.24	0.78
2	{骑车人未采取应急措施，十字路口，有信号灯}	{垂向两轮车左至右}	0.61	1.39	0.44
3	{骑车人未采取应急措施，有信号灯，骑车人无转向}	{货车无转向规避，十字路口，无视觉障碍}	0.66	1.50	0.44
4	{不存在视觉障碍，无碾压，两轮车直行}	{货车直行}	0.97	1.29	0.75
5	{两轮车直行，货车无转向规避，不存在视觉障碍，骑车人无转向}	{货车直行，无碾压}	0.79	1.35	0.59
6	{厢式货车，骑车人无转向}	{骑车人未采取应急措施}	0.96	1.26	0.77