非机动车超越行为轨迹分段识别与分析方法

doi:10.16097/j.cnki.1009-6744.2024.03.031

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (3): 323-332.DOI: 10.16097/j.cnki.1009-6744.2024.03.031

• 工程应用与案例分析 • 上一篇

非机动车超越行为轨迹分段识别与分析方法

张蕊^{* 1}，段予¹，孔令争²，侯先磊¹

1. 北京建筑大学，土木与交通工程学院，北京 100044；2. 中冶京诚工程技术有限公司，北京 100176

收稿日期:2024-03-11 修回日期:2024-04-29 接受日期:2024-05-07 出版日期:2024-06-25 发布日期:2024-06-24
作者简介:张蕊(1971- )，女，黑龙江宁安人，教授
基金资助:
国家重点研发计划(2022YFB2601900)；住房和城乡建设部软科学研究项目 (2018-R2-046)；北京市属高等学校高水平科研创新团队建设支持计划项目(BPHR20220109)

A Trajectory Segmentation and Analysis Method for Non-motor Vehicle Overtaking Behavior Recognition

ZHANG Rui^*1 , DUAN Yu¹, KONG Lingzheng² , HOU Xianlei¹

1. School of Civil and Traffic Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China; 2. MCC Capital Engineering & Research Incorporation Limited, Beijing 100176, China

Received:2024-03-11 Revised:2024-04-29 Accepted:2024-05-07 Online:2024-06-25 Published:2024-06-24
Supported by:
National Key Research and Development Program of China (2022YFB2601900)；Soft Science Research Project of the Ministry of Housing and Urban-Rural Development (2018-R2-046)；The Project of Construction and Support for High-level Innovative Teams of Beijing Municipal Institutions (BPHR20220109)

摘要/Abstract

摘要： 非机动车超越次数是非机动车道服务水平评价的重要参数，随着路侧高位视频设备的应用普及，为非机动车超越行为识别提供了良好的视频数据来源。目前有关轨迹分段方法的研究难以适应非机动车行驶角度变化频繁且超越轨迹较长的特点。本文提出基于片段轨迹时长和分割间隔时间两个参数的轨迹分段方法，根据视频获取的640条超越轨迹数据，分析非机动车各类超越行为的特性，选取纵向平均速度、纵向速度标准差、横向平均速度、横向速度标准差作为特征参数，基于K最近邻(K-Nearest Neighbor, KNN)算法建立非机动车超越分类模型。根据超越行为持续时间平均值确定自行车片段轨迹时长取值为[4, 9] s，分割间隔时间取值为[1, 8] s；电动自行车的片段轨迹时长取值为[4, 8] s，分割间隔时间取值为[1, 7] s，利用分类模型对各参数组合分段获得的非机动车轨迹片段进行识别。研究结果表明：自行车片段轨迹时长为8 s，分割间隔时间为6s；电动自行车片段轨迹时长为6 s，分割间隔时间为4 s时，对应的识别误差百分比最低，分段效果最佳。

关键词: 城市交通, 超越行为识别, 轨迹分段, 非机动车, 片段轨迹时长, 分割间隔时间

Abstract: The number of overtaking by non-motor vehicles is crucial for evaluating the level of services. With the widespread availability of roadside video equipment, it provides valuable video data for recognizing non-motor vehicle overtaking behavior. However, existing research on trajectory segmentation is difficult to adapt to the frequent changes in driving angles and lengthy overtaking trajectories exhibited by non-motor vehicles. In this paper, non-motor vehicle trajectories are segmented into fixed-length segments (trajectory segment length) based on specific interval time (segmentation interval). Using data from 640 overtaking trajectories captured from videos, various overtaking behaviors of non-motor vehicles are analyzed. Key characteristic parameters such as average longitudinal velocity, longitudinal velocity standard deviation, average lateral velocity, and lateral velocity standard deviation are selected. A classification model is then established using the K-Nearest Neighbor(KNN) algorithm to classify non-motor vehicle overtaking behaviors. Based on the average duration of overtaking behaviors, trajectory segment lengths for bicycles range from 4 to 9 seconds with segmentation intervals from 1 to 8 seconds, while for electric bicycles, trajectory segment lengths range from 4 to 8 seconds with segmentation intervals from 1 to 7 seconds. The classification model is then employed to identify overtaking behavior in non- motor vehicle trajectory segments for each parameter combination. Results indicate that for bicycles, a trajectory segment length of 8 seconds and a segmentation interval of 6 seconds yield the lowest recognition error rate and the most effective segmentation. Similarly, for electric bicycles, a trajectory segment length of 6 seconds and a segmentation interval of 4 seconds achieve optimal performance.

Key words: urban traffic, overtaking behavior recognition, trajectory segmentation, non-motor vehicle, trajectory segment length, segmentation interval

中图分类号:

U484

张蕊, 段予, 孔令争, 侯先磊. 非机动车超越行为轨迹分段识别与分析方法[J]. 交通运输系统工程与信息, 2024, 24(3): 323-332.

ZHANG Rui , DUAN Yu, KONG Lingzheng, HOU Xianlei. A Trajectory Segmentation and Analysis Method for Non-motor Vehicle Overtaking Behavior Recognition[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3): 323-332.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.03.031

http://www.tseit.org.cn/CN/Y2024/V24/I3/323

参考文献

[1] Transportation Research Board. Highway capacity manual (5th edition) [R]. Washington DC: National Research Council, 2010.

[2] 边扬, 杨家夏, 赵晓华, 等. 基于轨迹数据的共享电动自行车逆行风险行为影响因素研究 [J]. 中国公路学报, 2021, 34(12): 262- 275. [BIAN Y, YANG J X, ZHAO X H, et al. Research on influencing factors of reverse riding risk behavior of shared e-bike based on trajectory data[J]. China Journal of Highway and Transport, 2021, 34(12): 262-275.]

[3] 陈佳琪. 数据驱动的道路骑行适宜性研究: 以上海市杨浦区路网为例[J]. 交通与港航, 2022, 9(5): 76-82. [CHEN J Q. Data-driven research on the urban road cycling suitability: Case study of road network in Yangpu District of Shanghai[J]. Communication & Shipping, 2022, 9(5): 76-82.]

[4] 张欢, 边扬, 梁鲲, 等. 基于手机内置传感器数据的路段自行车交通服务水平模型研究[J]. 交通工程, 2022, 22(5): 78-83, 90. [ZHANG H, BIAN Y, LIANG K, et al. Research on bicycle traffic service level model based on mobile phone built-in sensor data[J]. Journal of Transportation Engineering, 2022, 22(5): 78-83, 90.]

[5] 胡莹, 邵春福, 王书灵, 等. 基于共享单车骑行轨迹的骑行质量识别方法[J]. 吉林大学学报(工学版), 2023, 53(4): 1040-1046. [HU Y, SHAO C F, WANG S L, et al. Identification of road riding quality based on shared bike trajectory data[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1040-1046.]

[6] 姚迪, 张超, 黄建辉, 等. 时空数据语义理解: 技术与应用[J]. 软件学报, 2018, 29(7): 2018-2045. [YAO D, ZHANG C, HUANG J H, et al. Semantic understanding of spatio-temporal data: Techonology & Application[J]. Journal of Software, 2018, 29(7): 2018-2045.]

[7] 杨晨希, 乔栋, 牛怡, 等. 基于鼠标轨迹语义理解的医学影像阅片交互意图识别[J]. 西北大学学报(自然科学版), 2023, 53(3): 387-400. [YANG C X, QIAO D, NIU Y, et al. Interactive intention recognition of medical image reviewing based on semantic understanding of mouse trajectory[J]. Journal of Northwest University (Natural Science Edition), 2023, 53(3): 387-400.]

[8] KANG J, MA H, DUAN Z, et al. Vehicle trajectory clustering in urban road network environment based on DOC2VEC model[C]. 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen: IEEE, 2021.

[9] 徐文洁, 赵欣, 酆磊, 等. 基于高精度轨迹数据的车辆换道行为识别研究[J]. 武汉理工大学学报(交通科学与工程版), 2023, 47(2): 239-244, 250. [XU W J, ZHAO X, FENG L, et al. Research on vehicle lane-changing behavior recognition based on high-precision positioning trajectory data[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering), 2023, 47(2): 239-244, 250.]

[10] LEE J G, HAN J, WHANG K Y. Trajectory clustering: A partition-and-group framework[C]. ACM SIGMOD International Conference on Management of Data, Beijing, China, 2007.

[11] 陈刚, 王国新, 明振军, 等. 基于DBSCAN聚类和LSTM网络的装甲车辆集群轨迹预测方法 [J/OL]. 兵工学报, (2024-02-02) [2024-03-04]. http://kns.cnki.net/kcms/ detail/11.2176.tj.20240201.1104.002.html. [CHEN G, WANG G X, MING Z J, et al. Armored vehicle cluster trajectory predi-ction method based on DBSCAN clustering and LSTM network[J]. Acta Armamentarii, (2024-02-02) [2024-03-04]. http://kns.cnki.net/kcms/ detail/11.2176.tj.20240201.1104.002.html.]

[12] 张建波, 孙建平, 徐春玲, 等. 考虑交通运行条件影响的驾驶员特征聚类[J]. 交通运输系统工程与信息, 2022, 22(2): 330-336. [ZHANG J B, SUN J P, XU C L, et al. Driver characteristics clustering under impact of varying traffic operation conditions[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 330-336.]

[13] 李志斌, 王炜, 赵德, 等. 机非物理分隔道路上自行车超车事件模型[J]. 东南大学学报(自然科学版), 2012,42(1): 156-161. [LI Z B, WANG W, ZHAO D, et al. Modeling bicycle passing events on physically separated roadways[J]. Journal of Southeast University(Natural Science Edition), 2012, 42(1): 156-161.]

[14] 梁肖, 戎亚萍, 赵欣苗, 等. 自行车微观行为研究综述[J]. 交通运输系统工程与信息, 2016, 16(4): 46-53. [LIANG X, RONG Y P, ZHAO X M, et al. Review of bicyclist microscopic behavior studies[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16 (4): 46-53.]

[15] 赵彤彤, 张春雷, 张春雨, 等 . 基于模糊熵的 KNN分类模型在岩性识别中的应用[J]. 计算机工程与应用, 2018, 54(24): 260-265. [ZHAO T T, ZHANG C L, ZHANG C Y, et al. Application of KNN classification model based on fuzzy entropy in lithology recognition. [J]. Computer Engineering and Applications, 2018, 54 (24): 260-265.]

非机动车超越行为轨迹分段识别与分析方法

A Trajectory Segmentation and Analysis Method for Non-motor Vehicle Overtaking Behavior Recognition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	牛振宁, 安琨, 马万经. 车网互动场景下电动网约车运营与充放电动态调度策略[J]. 交通运输系统工程与信息, 2024, 24(4): 50-59.
[2]	邓明君, 李书行, 李响, 张兵, 薛运强. 基于主线密度预测的快速路入口匝道控制方法[J]. 交通运输系统工程与信息, 2024, 24(4): 94-104.
[3]	魏书樵, 倪颖, 孙剑, 邱红桐. 基于生成对抗模仿学习的路段非机动车行为仿真[J]. 交通运输系统工程与信息, 2024, 24(4): 105-115.
[4]	李铁柱, 谢炳言, 刘天昊, 陈海波, 王召. 基于规则的信号交叉口纯电动公交节能驾驶策略[J]. 交通运输系统工程与信息, 2024, 24(4): 139-150.
[5]	姚恩建, 王鑫, 刘莎莎, 杨扬, 李成. 考虑机会充电与行程时间可靠性的区域多车型电动公交调度优化[J]. 交通运输系统工程与信息, 2024, 24(4): 151-165.
[6]	熊杰, 梁晶晶, 李向楠, 窦雪萍, 李同飞. 考虑分时电价和多车型的电动公交行车计划优化[J]. 交通运输系统工程与信息, 2024, 24(4): 188-199.
[7]	李洪运, 江志彬, 谷金晶, 刘伟, 王炳勋. 轨道交通远郊区段计划性停运对常乘客的转移影响[J]. 交通运输系统工程与信息, 2024, 24(4): 212-222.
[8]	陈红, 李晨光, 王铎, 段超杰, 姚振兴. 空间异质下地铁建成环境与站点覆盖客流吸引度关系研究[J]. 交通运输系统工程与信息, 2024, 24(4): 253-262.
[9]	易洪波, 刘昱岗, 王童语. 考虑空间需求不均的模块化公交线路运行方案优化研究[J]. 交通运输系统工程与信息, 2024, 24(4): 166-175.
[10]	翁剑成, 乔润童, 王茂林, 林鹏飞, 刘冬梅, 张晓亮. 考虑场景差异性的混合车型公交调度优化方法[J]. 交通运输系统工程与信息, 2024, 24(4): 176-187.
[11]	关昊天, 戢晓峰, 李武, 陈方, 邓若凡. 建成环境对共享单车与地铁组合出行的影响关系[J]. 交通运输系统工程与信息, 2024, 24(4): 200-211.
[12]	胡晓伟, 卢泓博, 安实. 考虑暴雨灾害动态影响的城市应急车辆救援路径优化研究[J]. 交通运输系统工程与信息, 2024, 24(3): 75-82.
[13]	张伯男, 姚向明, 赵鹏, 杨中平, 杨建国. 考虑高平峰差异的城市轨道交通节能运行图优化研究[J]. 交通运输系统工程与信息, 2024, 24(3): 164-171.
[14]	温芳, 柏赟, 陈垚. 考虑快慢车的城轨跨线运营开行方案与时刻表优化[J]. 交通运输系统工程与信息, 2024, 24(3): 172-183.
[15]	冉昕晨, 陈坚, 陈绍宽, 刘葛辉, 邹庆茹. 城市轨道交通多编组列车时刻表和车底周转综合优化研究[J]. 交通运输系统工程与信息, 2024, 24(3): 184-193.