Spatiotemporal Characteristics of Longitudinal Risky Driving Behaviors in Highway Tunnel Sections
-
摘要: 为了精准定位纵向风险驾驶行为在隧道路段的形态、位置及时间，增强交通管理部门主动预防交通事故的能力，针对传统时空分析维度分离的局限性，研究建立了时空维度结合的时空核密度估计模型（spatio-temporal kernel density estimation，STKDE），采用最小交叉二乘验证（least squares cross-validation，LSCV）确定模型最佳带宽。构建了基于轨迹数据的纵向风险驾驶行为识别方法，提取超速、超低速、急加速、急减速共4种纵向风险驾驶行为的时空位置；将隧道时空域分割为时空单元后，应用STKDE计算各时空单元内纵向风险驾驶行为时空核密度估计值ψ；结合时空立方体（space-time cube，ST-Cube）对STKDE结果可视化。基于下细腰隧道全域高精度轨迹数据进行实例分析，研究发现：高速驾驶行为在隧道出口100 m区域内高发，超速高发于16：00与09：00；低速驾驶行为在隧道入口前200 m高发，超低速高发于02：00与14：00；在进入隧道前100 m和隧道0~1 500 m区域，急加速与急减速行为的ψ始终大于0.5，处于高发状态，且在隧道区间内每隔150~200 m，2种急变速驾驶行为会同步出现波动，在驶离隧道后2种行为均迅速减少，且不再高发。通过与传统时空分析方法对比，结果表明：结合ST-Cube的STKDE分析方法，能实现耦合时空的特征分析，并量化估计全时空域内风险驾驶行为发生的可能性，其在对急加减速驾驶行为的特征分析中存在一定优势。Abstract: To pinpoint the patterns, locations, and timings of longitudinal risky driving behaviors in tunnel sections, enhancing the ability of traffic management departments to proactively prevent accidents, this study addresses the limitations of conventional separate spatio-temporal analysis dimensions by developing a spatio-temporal kernel density estimation model (STKDE). The model's optimal bandwidth is determined using least squares cross-validation (LSCV).A method for identifying longitudinal risky driving behaviors based on trajectory data is constructed, extracting spatio-temporal locations for four risky driving behaviors: speeding, extreme low speed, rapid acceleration, and rapid deceleration. By partitioning the spatio-temporal domain of the study area into units, STKDE is applied to compute the spatio-temporal kernel density estimation value, ψ, within each unit. The results of STKDE are visualized using a space-time cube model (ST-Cube). An empirical analysis based on high-precision trajectory data from the Xiaxiyao Tunnel reveals that high-speed driving behavior frequently occurs within 100 meters of the tunnel exit, with speeding peaking at 16:00 and 09:00. Low-speed driving behavior is frequent within 200 meters before the tunnel entrance, with extreme low speed peaking at 02:00 and 14:00. Within 100 meters before entry and throughout the first 1500 meters of the tunnel, the ψ values for rapid acceleration and deceleration remain above 0.5, indicating high-frequency occurrences.. Additionally, every 150~200 meters within the tunnel, these two types of sudden speed changes show simultaneous fluctuations, but significantly decrease and are no longer frequent once exiting the tunnel. A comparison with conventional spatio-temporal analysis methods shows that the STKDE method, combined with ST-Cube, achieves integrated spatio-temporal feature analysis and provides a quantifiable estimation of the likelihood of risky driving behaviors across the entire spatio-temporal domain, demonstrating a particular advantage in characterizing rapid acceleration and deceleration behaviors.
-
表 1 轨迹数据信息
Table 1. Track data information
字段 字段说明 单位 GlobalID 车辆全局编号 Timestamp 时间戳 ms PositionX 车辆纵向位置（平行道路方向距离道路起点的长度） m PositionY 车辆实际横向偏移（车辆距离道路内侧路缘线的偏移量） m VelocityX 纵向车速 m/s VelocityY 横向车速 m/s GlobalID 车辆全局编号 
下载: 导出CSV
表 2 隧道路段分车道速度特征统计
Table 2. Statistics of lane splitting speed characteristics of tunnel sections
车道 V/（km/h） V85/（km/h） V15/（km/h） Vmax/（km/h） Vmin/（km/h） N/veh 1 60.93 72.00 50.40 111.60 19.80 1 021 2 66.53 75.60 55.80 136.80 18.90 2 040 注：N为在指定车道上行驶过的车辆数。
下载: 导出CSV
表 3 超速与超低速高发时空（前10）
Table 3. Time and space of high speed and ultra-low speed(top 10)
排名 超速 超低速 X/m 车道Y 时间T X/m 车道Y 时间T 1 1 600 2 16：00 -200 1 02：00 2 1 600 2 09：00 -170 1 02：00 3 1 590 2 16：00 -190 1 02：00 4 1 590 2 09：00 -140 1 02：00 5 1 600 1 16：00 -180 1 02：00 6 1 580 2 09：00 -150 1 02：00 7 1 580 2 16：00 -160 1 02：00 8 1 590 1 16：00 -130 1 02：00 9 1 600 2 17：00 -120 1 02：00 10 1 570 2 09：00 -110 1 02：00
下载: 导出CSV
表 4 单车高速与单车低速高发时空（前10）
Table 4. Single-vehicle high-speed and single-vehicle low-speed high incidence times(top 10)
排名 单车高速 单车低速 X/m 车道Y 时间T X/m 车道Y 时间T 1 1 600 2 \ -180 2 \ 2 1 600 2 \ -190 2 \ 3 1 590 2 \ -200 2 \ 4 1 590 2 \ -170 2 \ 5 1 600 1 \ -160 2 \ 6 1 590 1 \ -150 2 \ 7 1 580 2 \ -180 1 \ 8 1 580 1 \ -170 1 \ 9 1 600 1 \ -140 2 \ 10 1 580 2 \ -190 1 \
下载: 导出CSV
表 5 急加速与急减速高发时空（前10）
Table 5. Time of high incidence of rapid acceleration and deceleration(top 10)
排名 急加速 急减速 X/m 车道Y 时间T X/m 车道Y 时间T 1 50 2 17：00 500 2 18：00 2 1 430 2 18：00 490 2 18：00 3 40 2 17：00 510 2 18：00 4 1 390 2 18：00 1 360 2 18：00 5 1 400 2 18：00 1 370 2 18：00 6 1 440 2 18：00 1 380 2 18：00 7 1 380 2 18：00 520 2 18：00 8 1 410 2 18：00 -90 2 17：00 9 1 420 2 18：00 1 340 2 18：00 10 40 2 18：00 1 390 2 18：00
下载: 导出CSV
-
[1] 马潇驰, 陆建. 风险驾驶行为对高速公路事故影响因素研究[C]. 2022世界交通运输大会, 武汉: 中国公路学会, 2022.MAX C, LU J. Study on the factors influencing risky driving behavior on highway accidents[C]. 2022 World Transport Congress, Wuhan, China: China Highway Society, 2022. (in Chinese) [2] 邱锋. 基于智能算法的高速公路隧道交通事故预测研究[D]. 西安: 长安大学, 2018.QIU F. Highway tunnel Traffic accident prediction research based on intelligent algorithm[D]. Xi'an: Chang'an University, 2018. (in Chinese) [3] 张璇, 唐进君, 黄合来, 等. 山区高速公路隧道路段与开放路段的事故影响因素分析[J]. 交通信息与安全, 2022, 40(3): 10-18. doi: 10.3963/j.jssn.1674-4861.2022.03.002ZHANG X, TANG J J, HUANG H L, et al. An analysis of influential factors of crashes at tunnels and open sections of mountainous freeways[J]. Journal of Transport Information and Safety, 2022, 40(3): 10-18. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2022.03.002 [4] 徐进, 曾粤. 高速条件下隧道出入口行驶速度特性[J]. 交通运输工程学报, 2021, 21(4): 197-209.XU J, ZENG Y. Characteristics of driving speed at tunnel entrance and Exit at high speed[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 197-209. (in Chinese) [5] 王建伟, 付佳杨, 付鑫. 基于网络时空核密度的不良驾驶行为多发点识别研究[C]. 2022世界交通运输大会, 武汉: 中国公路学会, 2022.WANG JW, FU JY, FU X. Research on the identification of multiple points of risk driving behavior based on network spatio-temporal kernel density[C]. 2022 World Transport Congress, Wuhan, China: China Highway Society, 2022. (in Chinese) [6] YAN G, WANG M, QIN P, et al. Comparative study on drivers' eye movement characteristics and psycho-physiological reactions at tunnel entrances in plain and high-altitude areas: a pilot study[J]. Tunnelling and Underground Space Technology, 2022, 122: 104370. doi: 10.1016/j.tust.2022.104370 [7] 白婧荣, 唐伯明, 孙宗元, 等. 毗邻互通立交特长隧道驾驶负荷研究[J]. 交通运输系统工程与信息, 2022, 22(1): 301-310.BAI J R, TANG B M, SUN Z Y, et al. On Driving Load of Super-long Tunnel Adjacent to Interchanges[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1): 301-310. (in Chinese) [8] 万利, 王虹婷, 张长安, 等. 高速公路隧道侧向宽度对大型车驾驶负荷的影响[J]. 公路交通科技, 2022, 39(9): 169-176.WAN L, WANG H T, ZHANG C A, et al. Influence of lateral width of expressway tunnel on driving load of large vehicle[J]. Journal of Highway and Transportation Research and Development, 2022, 39(9): 169-176. (in Chinese) [9] 阎莹, 王虹婷, 万利, 等. 基于因子分析与熵值法的不同隧道侧向宽度下驾驶负荷模型[J]. 中国公路学报, 2023, 36 (2): 190-202. doi: 10.3969/j.issn.1001-7372.2023.02.016YAN Y, WANG H T, WAN L, et al. Driver load model under different tunnel lateral widths based on factor analysis and entropy method[J]. China Journal of Highway and Transport, 2023, 36(2): 190-202. (in Chinese) doi: 10.3969/j.issn.1001-7372.2023.02.016 [10] 唐皓, 唐忠泽, 张驰, 等. 隧道与主线出口间小净距路段车辆行驶特征分析[J]. 交通信息与安全, 2023, 41(4): 33-43. doi: 10.3963/j.jssn.1674-4861.2023.04.004TANG H, TANG Z Z, ZHANG C, et al. An analysis of driving behavior on short distance section between tunnel and the exit of main roadway[J]. Journal of Transport Information and Safety, 2023, 41(4): 33-43. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.04.004 [11] 李永庆. 基于行为谱的隧道路段不良驾驶行为特性及识别研究[D]. 西安: 长安大学, 2022.LI Y Q. Research on characteristics and identification of risky driving behavior in tunnel section based on behavior spectrum[D]. Xi'an: Chang'an University, 2022. (in Chinese) [12] 王可, 陆键, 蒋愚明. 基于车辆行驶轨迹的道路不良驾驶行为谱构建与特征值计算方法[J]. 交通运输工程学报, 2020, 20(6): 236-249.WANG K, LU J, JANG Y M. Abnormal road driving behavior spectrum establishment and characteristic value calculation method based on vehicle driving trajectory[J]. Journal of Traffic and Transportation Engineering, 2020, 20(6): 236-249. (in Chinese) [13] 刘唐志, 毕辉云, 杨卓思, 等. 基于操纵量指标的合流区危险驾驶行为谱研究[J]. 交通运输系统工程与信息, 2023, 23 (2): 242-251.LIU T Z, BI H Y, YANG Z S, et al. Dangerous Driving Behavior Spectrum in Merging Area Based on Maneuver Indicators[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(2): 242-251. (in Chinese) [14] WANG J H, FU T, SHANGGUAN Q Q. Wide-area vehicle trajectory data based on advanced tracking and trajectory splicing technologies: potentials in transportation research[J]. Accident Analysis & Prevention, 2023, 186: 107044. [15] WANG J H, FU T, XUE J, et al. Realtime wide-area vehicle trajectory tracking using millimeter-wave radar sensors and the open TJRD TS dataset[J]. International Journal of Transportation Science and Technology, 2023, 12(1): 273-290. doi: 10.1016/j.ijtst.2022.02.006 [16] 中华人民共和国交通部. 公路项目安全性评价指南: JTG/T B05-2015[S]. 北京: 人民交通出版社, 2015.Ministry of Transport of the People's Republic of China. Specifications for highway safety audit: JTG/T B05-2015[S]. Beijing: China Communications Press, 2015. (in Chinese) [17] 中华人民共和国交通部. 道路交通标志和标线第5部分: 限制速度: GB 5768. 5-2017[S]. 北京: 中国标准出版社, 2017.Ministry of Transport, People's Republic of China. Road traffic signs and markings-part 5: speed limit: GB 5768. 5-2017[S]. Beijing: Standards Press of China, 2017. (in Chinese) [18] 徐进, 杨奎, 罗骁, 等. 山区双车道公路运行速度预测模型的加速度标定[J]. 哈尔滨工业大学学报, 2017, 49(3): 181-188.XU J, YANG K, LUO X, et al. Calibrating of acceleration and deceleration rate for the operating speed prediction models of two-lane roads in a mountainous area[J]. Journal of Harbin Institute of Technology, 2017, 49(3): 181-188. [19] BRUNSDON C, CORCORAN J, HIGGS G. Visualising space and time in crime patterns: a comparison of methods[J]. Computers, Environment and Urban Systems, 2007, 31(1): 52-75. doi: 10.1016/j.compenvurbsys.2005.07.009 [20] KRISTAN M, LEONARDIS A, SKOČAJ D. Multivariate online kernel density estimation with Gaussian kernels[J]. Pattern Recognition, 2011, 44(10-11): 2630-2642. doi: 10.1016/j.patcog.2011.03.019 [21] HOHL A, DELMELLE E, TANG W, et al. Accelerating the discovery of space-time patterns of infectious diseases using parallel computing[J]. Spatial and Spatio-temporal Epidemiology, 2016, 19: 10-20. doi: 10.1016/j.sste.2016.05.002 -
点击查看大图
图(9) / 表(5)
计量
- 文章访问数: 67
- HTML全文浏览量: 25
- PDF下载量: 8
- 被引次数: 0