An Analysis of Driving Behavior on Short Distance Section between Tunnel and the Exit of Main Roadway
-
摘要: 当受地理与投资因素限制，山区高速公路隧道与主线出口间距离低于规范值，则该区域称为小净距路段。为描述该区域车辆行驶特征，充实山区公路设计与交通管控的理论基础，在我国秦岭服务区等7处山区高速公路小净距路段，通过无人机定点俯拍采集高清行车视频，基于视频提取全域车辆高精度速度与轨迹数据，实现车辆行驶特征分析。本研究基于SIFT算法进行视频配准；基于YOLOv5与DeepSORT算法实现车辆检测与连续跟踪；采用Savitzky-Golay滤波器对数据进行光滑滤波。基于以上方法，可获得高精度车辆行驶数据。经验证，车速精度可达到95%以上，轨迹误差小于20 cm。而后，考虑了净距长度、车辆类型、车道分布等指标，从多角度多因素对行车特征进行了分析。结果显示：①小净距路段车辆行驶特征与普通路段有明显的差异，车速分布不满足正态分布规律；②整体上驶出车辆在渐变段起点前10~20 m左右会稳定车辆运行状态；③由于视角更高，货车相对小车能更快识别出口路况，所以车速相对平稳；④内侧驶出小车在渐变段起点20 m后以1.1~1.4 m/s的横向速度驶入减速车道，当主线为左偏曲线最有利于驶出；⑤净距长度对驾驶行为产生的影响最为明显，交通流方面交通量是最大的影响因素，道路线形因素中曲线偏转方向及偏转角是最大的影响因素。Abstract: A short distance section is a section between the tunnel and the mainline exit of a mountainous highway whose length is lower than the normative value because of the limitation of geographical and investment factors. In order to analyze the driving characteristics of this area thus to enhance the theoretical base for mountain road design and traffic control, high-definition driving videos are collected by drones in 7 mountain roads (e.g., Qinling service area) with short distance sections in China. The high-precision speed and trajectory data of vehicles across the entire region have been extracted. The SIFT algorithm is used for video stabilization. The YOLOv5 and DeepSORT algorithms are adopted for vehicle detection and tracking. The Savitzky-Golay filter is utilized to filter the data. Finally, high precision driving data can be obtained based on the above methods. It is verified that the accuracy of speed can reach more than 95% and the error of trajectory is less than 20 cm. Next, the driving characteristics are analyzed from a variety of perspectives, such as clearance distance, vehicle type, lane distribution, and others. The results show that: ①the driving characteristics on short distance section are very different from those on usual road section that the speed distribution does not follow a normal distribution; ②generally the outgoing vehicles would be steady 10 to 20 m ahead of the commencement of the fading phase; ③the speed of trucks is smoother as truck drivers can identify the exit road conditions more quickly than the car drivers because of the larger angle of view; ④approximately 20 meters after the starting point of the transition section, the cars in the inner lane enter the deceleration lane with a lateral speed of 1.1 to 1.4 m/s, and when the mainline has a leftward curve it is most favorable to drive out; ⑤the clearance distance has the highest influence on driving behaviors, the traffic volume affects the most among traffic flow factors while the direction of curve deflection and deflection angle affect the most among the road geometry factors.
-
图 8 隧道出口小净距路段变道车辆速度图
Figure 8. Changes in the speed of vehicles changing lanes in the short distance section at the exit of the tunnel
图 10 部分小净距路段运行速度数据频率分布直方图
Figure 10. Histogram of frequency distribution of running speed data on some short distance sections
表 1 调研路段
Table 1. Investigation section
单位: m 公路名称 构造物 隧道长度 净距长度 西汉高速 朱雀停车区 6 300 15 秦岭服务区1 6 160 23 秦岭服务区2 11 200 25 皇冠互通1 330 23 皇冠互通2 370 150 福银高速 辋川互通 1 500 630 沪陕高速 竹林关互通 1 080 30 
下载: 导出CSV
表 2 数据准确性检验
Table 2. Data accuracy test
车型分类 车速分类 真实车速（km/h） 检测车速（km/h） 小车 79 77 79 79 64.8 67 86 80 86 82 74 79 86.4 91 69 66 64.8 68 大车 47 45 45 41 45 40.5 64.2 65 39.8 36 43.2 39 39 39 57.6 59 61.5 60
下载: 导出CSV
表 3 误差分析
Table 3. Error analysis
车辆类型 误差极大值/（km/h） 极值误差率/% 均值误差/（km/h） 均值误差率/% 均值准确率/% 均方根误差/（km/h） 大车 5 10 2.98 6.06 93.7 2.94 小车 6 6.98 3.89 5.08 95.5 3.74
下载: 导出CSV
表 4 路段数据信息
Table 4. Data information
路段 拍摄时长/min 小车总量/驶出车辆 大车总量/驶出车辆 朱雀停车区 30 97/21 210/165 秦岭服务区1 30 148/54 124/300 秦岭服务区2 30 160/60 130/210 皇冠互通1 30 191/35 106/230 皇冠互通2 25 166/26 87/180 辋川互通 30 195/50 124/200 竹林关互通 25 93/45 88/45
下载: 导出CSV
表 5 各小净距路段车速数据描述信息
Table 5. Speed data description information of each short distance sections
单位: km/h 小净距采集点 均值 中位数 标准差 方差 偏度 峰度 极大值 极小值 V85 秦岭1号小净距 90.91 87.45 14.80 217.66 -0.12 0.27 123.91 42.22 97.85 秦岭2~3号小净距 87.78 86.51 15.61 248.55 -0.26 -0.72 117.54 49.45 104.78 木瓜园隧道小净距 85.26 86.4 12.56 157.73 0.21 -0.45 121.6 60.63 97.92 无名隧道小净距 87.38 87.73 12.64 159.68 0.18 -0.42 120.36 57.6 101.65 辋川隧道小净距 86.11 86.4 10.77 115.95 0.52 -0.16 120 62.27 97.92 州河北隧道小净距 89.78 88.31 11.63 135.27 0.60 -0.25 119.13 61.29 103.59
下载: 导出CSV
表 6 正态性验证
Table 6. Normality verification
小净距采集点 Z值 渐近显著性 秦岭1号小净距 0.128 0 秦岭2~3号小净距 0.072 0.007 木瓜园隧道小净距 0.077 0 无名隧道小净距 0.084 0 辋川隧道小净距 0.093 0 州河北隧道小净距 0.109 0
下载: 导出CSV
表 7 影响因素信息统计
Table 7. Statistics of influencing factors
路段名称 净距长度/m 交通流因素 道路几何因素 交通量/（veh/h） 大型车比例/% 转向比例/% 半径/m 转角/（°） 偏向 纵坡/% 秦岭1号小净距 30 710 24.98 15 直线 2 秦岭2~3号小净距 33 430 37.48 9.7 直线 2 木瓜园隧道小净距 25 720 21.58 3.7 直线 1.5 无名隧道小净距 152 488 32.08 2.5 1 800 25 右偏 1.5 辋川隧道小净距 605 804 19.68 6.1 1 500 16 左偏 / 州河北隧道小净距 33 626 31.38 8 700 78 左偏 -0.65
下载: 导出CSV
表 8 各小净距变道速度和断面速度离散性数据表
Table 8. Discrete data table of lane change speed and section speed for each short distance
路段 变道速度/（km/h） 断面速度/（km/h） 平均值 速度变异系数 平均值 速度变异系数 秦岭1号小净距 45.9 0.33 84.91 0.18 秦岭2~3号小净距 53.9 0.26 87.24 0.15 木瓜园隧道小净距 60.1 0.30 85.22 0.16 无名隧道小净距 76.32 0.20 88.64 0.13 辋川隧道小净距 61.68 0.21 86.55 0.17 州河北隧道小净距 68.83 0.31 89.75 0.13
下载: 导出CSV
表 9 出口间最小净距
Table 9. The minimum distance between exits
主线设计速度/（km/h） 最小净距/m 单向2车道 单向3车道 单向4车道 120 500 700 1 000 100 400 600 800 80 300 450 600
下载: 导出CSV
表 10 最小净距组成
Table 10. The composition of minimum value
主线设计速度/（km/h） 最小净距/m 明适应距离 识别距离 120 100 350 100 84 290 80 67 230
下载: 导出CSV
-
[1] VOS J, FARAH H, HAGENZIEKER M. Speed behaviour upon approaching freeway curves[J]. Accident Analysis & Prevention, 2021, 159: 106276. [2] MCCARTT A, NORTHRUP V, RETTING R. Types and characteristics of ramp-related motor vehicle crashes on urban interstate roadways in Northern Virginia[J]. Journal of Safety Research, 2004, 35(1): 107-114. doi: 10.1016/j.jsr.2003.09.019 [3] 赵一飞, 陈敏, 潘兵宏. 隧道与互通式立交出口最小间距需求分析[J]. 长安大学学报(自然科学版), 2011, 31(3): 68-71. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL201103015.htmZHAO Y F, CHEN M, PAN B H. Minimumspacing demand analysis between tunnel and exit of interchange[J]. Journal of Chang'an University(Natural Science Edition), 2011, 31 (3): 68-71. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL201103015.htm [4] 丁瑞, 刘俊, 蒋艳, 等. 基于车辆加速度数据的互通立交匝道驾驶风险分析[J]. 交通信息与安全, 2021, 39(1): 17-25. doi: 10.3963/j.jssn.1674-4861.2021.01.0003DING R, LIU J, JIANG Y, et al. Driving risks of interchange ramps based on vehicle acceleration data[J]. Journal of Transport Information and Safety, 2021, 39(1): 17-25. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2021.01.0003 [5] PINNOW J, MASOUD M, ELHENAWY M, et al. A review of naturalistic driving study surrogates and surrogate indicator viability within the context of different road geometries[J]. Accident Analysis & Prevention, 2021, 157: 106185. [6] 陈云, 杜志刚, 焦方通, 等. 小半径公路短隧道入口段不同车型视觉负荷研究[J]. 武汉理工大学学报(交通科学与工程版), 2019, 43(4): 708-711, 717. https://www.cnki.com.cn/Article/CJFDTOTAL-JTKJ201904026.htmCHEN Y, DU Z G, JIAO F T, et al. Research on visual loads of different vehicle types in short tunnel entrance section of small radius highway[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering), 2019, 43 (4): 708-711, 717. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTKJ201904026.htm [7] QAID H, WIDYANTI A, SALMA S A, et al. Speed choice and speeding behavior on Indonesian highways: Extending the theory of planned behavior[J]. IATSS research, 2022, 46 (2): 193-199. doi: 10.1016/j.iatssr.2021.11.013 [8] 陈志贵, 王雪松, 张晓春, 等. 山区高速公路驾驶人加减速行为建模[J]. 中国公路学报, 2020, 33(7): 167-175. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202007017.htmCHEN Z G, WANG X S, ZHANG X C, et al. Modeling of driver acceleration and deceleration behavior in mountain freeways[J]. China Journal of Highway and Transport. 2020, 33(7): 167-175. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202007017.htm [9] ZHOU J, LUO Y, ZHZNG H, et al. Safety design strategy for highway interchange exit ramp[J]. Journal of Architectural Research and Development, 2021, 5(2): 1954. [10] 张驰, 闫晓敏, 李小伟, 等. 互通式立交单车道出口小客车运行速度模型[J]. 中国公路学报, 2017, 30(6): 279-286. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201706011.htmZHANG C, YAN X M, LI X W, et al. Operating speed model of passenger car at single-lane exit of interchange[J]. China Journal of Highway and Transport. 2017, 30(6): 279-286. (inChinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201706011.htm [11] 姚晶, 王海君, 潘兵宏. 基于换道模型的高速公路隧道出口与主线分流点最小净距研究[J]. 中外公路, 2017, 37(4): 298-302. https://www.cnki.com.cn/Article/CJFDTOTAL-GWGL201704068.htmYAO J, WANG H J, PAN B H. Research on the minimum clear distance between the expressway tunnel exit and the main line diversion point based on the lane changing model[J]. Journal of China & Foreign Highway, 2017, 37(4): 298-302. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GWGL201704068.htm [12] 廖军洪, 王芳, 邬洪波, 等. 高速公路互通立交与隧道最小间距研究[J]. 公路, 2012(1): 1-7. https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL201201002.htmLIAO J H, WANG F, WU H B. Research on minimum distance between interchange and tunnel in expressway[J]. Highway, 2012, 1: 1-7. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL201201002.htm [13] 盛启锦. 隧道群出口毗邻互通路段分离式指路标志设置研究[D]. 重庆: 重庆交通大学, 2020.SHENG Q J. Research on Setting of SeparateDirectional Signs for Tunnel Group Exit Adjacent to Mutual Intersection[D]. Chongqing: Chongqing Jiaotong University, 2020. (in Chinese) [14] PORTERA A, Bassani M. Experimental investigation into driver behavior along curved and parallel diverging terminals of exit interchange ramps[J]. Transportation research record, 2021, 2675(8): 254-267. [15] SINGH H, KATHURIA A. Analyzing driver behavior under naturalistic driving conditions: a review[J]. Accident Analysis & Prevention, 2021, 150: 105908. [16] PUNZO V, BORZACCHIELLO M T, CIUFFO B. On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation(NGSIM)program data[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(6): 1243-1262. [17] KRAJEWSKI R, BOCK J, KLOEKER L, et al. The highd dataset: A drone dataset of naturalistic vehicle trajectories on german highways for validation of highly automated driving systems[C]. 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA: IEEE, 2018. [18] 孔烜, 张杰, 邓露, 等. 基于机器视觉的车辆检测与参数识别研究进展[J]. 中国公路学报, 2021, 34(4): 13-30. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202104003.htmKONG H, ZHANG J, DENG L, et al. Research advances on vehicle parameter ldentification based on machine vision[J], China Journal of Highway and Transport, 2021, 34(4): 13-30. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202104003.htm [19] ZHANG C, TANG Z. ZHANG M., et al. Developing a more reliable aerial photography-based method for acquiring freeway traffic data[J]. Remote Sensing, 2022, 14(9): 2202. [20] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. [21] LIY L, DING Y Q, LI T. Nonlinear difusio fitering for peak-preseving smoothing of a spectrum signal[J]. Chemometrics and Intelient Laboratory Systems, 2016, 156: 157-165. [22] REINARTZ P, LACHAISE M, SCHMEER E, et al. Traffic monitoring with serial images from airborne cameras[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 61(3/4): 149-158. [23] 邓国忠, 曹帆, 吴勇. 互通式立交与隧道出口小间距路段事故影响因素分析[J]. 中外公路, 2019, 39(4): 283-287. https://www.cnki.com.cn/Article/CJFDTOTAL-GWGL201904058.htmDENG G Z, CAO F, WU Y. Analysis on accidents influence factors of the small spacing section between intersection andtunnel exit[J]. Journal of China & Foreign Highway, 2019, 39(4): 283-287. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GWGL201904058.htm [24] 戢晓峰, 谢世坤, 覃文文, 等. 基于轨迹数据的山区危险性弯道路段交通事故风险动态预测[J]. 中国公路学报, 2022, 35(4): 277-285. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202204023.htmJI X F, XIE S K, QIN W W, et al. Dynamic prediction of traffic accident risk in risky curve sections based on vehicle trajectory data[J], China Journal of Highway and Transport, 2022, 35(4): 277-285. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202204023.htm [25] 阎莹, 王晓飞, 张宇辉, 等. 高速公路断面运行车速分布特征研究[J]. 中国安全科学学报, 2008, 18(7): 171-176. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK200807030.htmYAN Y, WANG X F, ZHANG Y H. Research on section operating speed distribution characteristics of expressway[J]. China Safety Science Journal, 2008, 18(7): 171-176. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK200807030.htm [26] 蔡晓禹, 雷财林, 彭博, 等. 基于驾驶行为和信息熵的道路交通安全风险预估[J]. 中国公路学报, 2020, 33(6): 190-201. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202006019.htmCAI X Y, LEI C L, PENG B, et al. Road traffic safety risk estimation based on driving behavior and information entropy[J]. China Journal of Highway and Transport, 2020, 33 (6): 190-201. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202006019.htm [27] 阎莹, 张迎, 李庚凭, 等. 基于速度特征指标的高速公路线形一致性综合评价[J]. 安全与环境学报, 2017, 17(3): 835-839. https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201703007.htmYAN Y, ZHANG Y, LI G P, et al. Comprehensive evaluation of the highway alignment consistency based on the driving speed index characteristic features[J]. Journal of Safety and Environment, 2017, 17(3): 835-839. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-AQHJ201703007.htm -
点击查看大图
图(10) / 表(10)
计量
- 文章访问数: 546
- HTML全文浏览量: 374
- PDF下载量: 34
- 被引次数: 0