基于车辆动态行为特征的交通状态识别研究

doi:10.16097/j.cnki.1009-6744.2025.01.005

交通运输系统工程与信息 ›› 2025, Vol. 25 ›› Issue (1): 44-55.DOI: 10.16097/j.cnki.1009-6744.2025.01.005

• 智能交通系统与信息技术 • 上一篇下一篇

基于车辆动态行为特征的交通状态识别研究

李熙莹^*1,2，卢美燕^1,2，何兆成^1,2，苏淑妍^1,2，庞淑敏^1,2

1. 中山大学，智能工程学院，广东深圳518107；2.广东省智能交通系统重点实验室，广东深圳518107

收稿日期:2024-10-16 修回日期:2024-11-25 接受日期:2024-12-27 出版日期:2025-02-25 发布日期:2025-02-21
作者简介:李熙莹(1972—)，女，陕西西安人，教授，博士。
基金资助:
国家自然科学基金(U21B2090)；广东省基础与应用基础研究基金(2022A1515010361)。

Traffic State Recognition Based on Vehicle Dynamic Behavior Characteristics

LI Xiying^*1,2, LU Meiyan^1,2, HE Zhaocheng^1,2, SU Shuyan^1,2, PANG Shumin^1,2

1. School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, Guangdong, China; 2. Guangdong Provincial Key Laboratory of Intelligent Transportation System, Shenzhen 518107, Guangdong, China

Received:2024-10-16 Revised:2024-11-25 Accepted:2024-12-27 Online:2025-02-25 Published:2025-02-21
Supported by:
National Natural Science Foundation of China (U21B2090)；Guangdong Basic andApplied Basic Research Foundation (2022A1515010361)。

摘要/Abstract

摘要： 交通状态识别研究对于预防和缓解交通拥堵具有重要的研究价值，不仅能够为交通管理提供决策支持，还能有效提升道路的运行效率。传统的交通状态识别方法仅考虑单一的宏观特征参数，忽视车辆变道行为的影响以及由此产生的车辆间相互干扰，导致状态划分空间粒度较粗，状态辨识不够精细化，难以深入分析交通拥堵的成因。对此，本文提出一种无人机视角下基于车辆动态行为特征的交通状态识别方法。首先，该方法结合基于旋转检测框的车辆检测算法(YOLOv8s-OBB)和车辆跟踪算法(BoTSORT)检测和跟踪车辆，解决水平框中背景像素冗余以及车辆框重叠的问题，提取车辆空间方向角和旋转4点坐标等更精准的车辆轨迹数据，并计算微观交通流参数；其次，利用获取的车辆空间方向角和旋转位置信息提出车辆动态行为特征参数，即变道干扰率和车辆方向波动指数；然后，结合宏观的平均速度和交通密度参数，构建多维状态特征空间，应用于实际道路场景的交通状态识别。最终实验结果表明：在旋转车辆目标检测中，该方法的mAP@0.5达到0.987，输出的车辆轨迹数据稳定且连续；在交通状态识别中，在平均速度和交通密度作为宏观特征参数的基础上引入变道干扰率后，状态识别精确度达到0.983；进一步，引入车辆方向波动指数后，状态识别精确度达到0.987。同时，根据状态特征空间表征，可以更加精准地将交通状态划分为4种状态，即畅通态、平稳态、拥挤态和堵塞态，从而可以为车辆动态行为定量化分析交通状态影响，为基于无人机视角的交通状态识别提供新的理论参考，为智能交通系统提供先进的状态精细感知。

关键词: 城市交通, 交通状态识别, 车辆动态行为特征参数, 旋转车辆检测与跟踪, 无人机航拍

Abstract: Traffic state recognition research is of great significance for the prevention and mitigation of traffic congestion. It provides decision support for traffic management and also effectively enhances the operational efficiency of roads. Traditional traffic state identification methods typically take into account one single macroscopic characteristic parameter, while overlooking the impact of vehicle lane-changing behaviors and the consequent mutual interference among vehicles. This leads to a relatively coarse granularity in the state division space and insufficient refinement in state identification, thereby hindering in-depth analysis of traffic congestion causes. In response to this, this study proposes a traffic state identification method based on vehicle dynamic behavior characteristics from an Unmanned Aerial Vehicle (UAV) perspective. Firstly, the method combines a vehicle detection algorithm (YOLOv8-OBB) based on rotated bounding boxes and a vehicle tracking algorithm (BoTSORT) to detect and track vehicles, addressing redundant background pixels and overlapping vehicle bounding boxes within horizontal bounding boxes, extract more accurate vehicle trajectory data such as vehicle spatial direction angle and four-point rotation coordinates, and calculate microscopic traffic flow parameters. Secondly, by utilizing the obtained vehicle driving direction angles and rotated position information, this study proposes vehicle dynamic behavior characteristics parameters: lane change interference rate and vehicle direction fluctuation index. Combined with macroscopic average speed and traffic density parameters, a multi-dimensional state feature space is constructed and applied to traffic state identification in actual road scenes. The ultimate experimental results demonstrate that the method achieved an mAP@0.5 of 0.987 in the rotated vehicle detection, with stable and continuous vehicle trajectory data output. In traffic state recognition, by introducing the lane change interference rate based on the average speed and traffic density as macroscopic feature parameters, the state recognition precision reached 0.983. Moreover, incorporating the direction fluctuation index, the state recognition precision reached 0.987. Additionally, according to the state characteristic space representation, the traffic state enables accurate classification into four states: smooth state, steady state, crowded state, and blocked state. This allows for quantitative analysis of the impact of vehicle dynamic behavior on traffic state, and provides novel theoretical insights for traffic state recognition from a UAV perspective, offering advanced fine-grained perception capabilities for intelligent transportation systems

Key words: urban traffic, traffic state recognition, vehicle dynamic behavior characteristics parameters, rotated vehicle detection and tracking, UAV aerial photography

中图分类号:

U491

李熙莹, 卢美燕, 何兆成, 苏淑妍, 庞淑敏. 基于车辆动态行为特征的交通状态识别研究[J]. 交通运输系统工程与信息, 2025, 25(1): 44-55.

LI Xiying, LU Meiyan, HE Zhaocheng, SU Shuyan, PANG Shumin. Traffic State Recognition Based on Vehicle Dynamic Behavior Characteristics[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 44-55.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2025.01.005

http://www.tseit.org.cn/CN/Y2025/V25/I1/44

参考文献

[1]邬群勇,胡振华,张红.基于多源轨迹数据的城市交通状态精细划分与识别[J].交通运输系统工程与信息, 2020, 20(1): 83-90. [WU Q Y, HU Z H, ZHANG H. Fine division and identification of urban traffic status based on multi-source trajectory data[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 83-90.]

[2]谢东繁,贾惠迪,李春艳,等.基于网格交通状态分类的行程时间规律挖掘与计算[J].交通运输系统工程与信息,2022, 22(3): 168-178. [XIE D F, JIA H D, LI C Y, et al. Mining and calculating travel time based on classification of grid traffic state[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 168-178.]

[3]黄玲,吴泽荣,洪佩鑫,等.基于地空信息融合的无人机交通状态感知方法研究[J].中国公路学报,2021,34 (12): 249-261. [HUANG L, WU Z R, HONG P X, et al. Research on UAV traffic state perception method based on ground and air information fusion[J]. China Journal of Highway and Transport, 2021, 34(12): 249-261.]

[4]谷远利,杜恒,陆文琦.多源数据融合驱动的城市快速路交通状态划分[J].交通运输系统工程与信息,2024, 24(3): 213-220, 231. [GU Y L, DU H, LU W Q. Traffic state division of urban expressway driven by multi-source data fusion[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3): 213-220, 231.]

[5]AFRIN T, YODO N. A probabilistic estimation of traffic congestion using Bayesian network[J]. Measurement, 2021, 174: 109051.

[6]CHENG Z, WANG W, LU J, et al. Classifying the traffic state of urban expressways: A machine-learning approach [J]. Transportation Research Part A: Policy and Practice, 2020, 137: 411-428.

[7]白骅,王建军,蒋意眉.基于点、线、面层次的公路网交通运行状态评价[J].中国公路学报,2018,31(11):197 204. [BAl H, WANG J J, JlANG Y M. Evaluation of highway network traffic operation state based on point， line，and area[J]. China Journal of Highway and Transport, 2018, 31(11): 197-204.]

[8]TU W, XIAO F, LI L, et al. Estimating traffic flow states with smart phone sensor data[J]. Transportation Research Part C: Emerging Technologies, 2021, 126: 103062.

[9]SUN D, AI Y, WANG L. Freeway traffic safety state classification method based on multi-parameter fusion clustering[J]. Modern Physics Letters B, 2022, 36(20): 2250088.

[10] WANG Y, FU Q, WANG X. A traffic status evaluation method of expressway merging area based on improved coupling theory[J]. Modern Physics Letters B, 2022, 36 (19): 2150616.

[11]张河山,谭鑫,范梦伟,等.无人机高空航拍视角下小尺度车辆精确检测方法[J].交通运输系统工程与信息, 2024, 24(3): 299-309. [ZHANG H S, TAN X, FAN MW, et al. Accurate detection method of small-scale vehicles from perspective of unmanned aerial vehicle high-altitude aerial photography[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3): 299-309.]

[12] BISIO I, GARIBOTTO C, HALEEM H, et al. Vehicular/ non-vehicular multi-class multi-object tracking in drone based aerial scenes[J]. IEEE Transactions on Vehicular Technology, 2023, 12(72): 4961-4977.

[13] QIU Z, BAI H, CHEN T. Special vehicle detection from UAV perspective via YOLO-GNS based deep learning network[J]. Drones, 2023, 7(2): 117.

[14]李熙莹, 梁靖茹,张伟斌,等.基于航拍视频构建风险指数的交织区拥堵识别方法[J].铁道科学与工程学报, 2023, 20(2): 494-505. [LI X Y, LIANG J R, ZHANG W B, et al. Congestion recognition method in weaving sections by constructing risk index based on aerial video [J]. Journal of Railway Science and Engineering, 2023, 20 (2): 494-505.]

[15] AHARON N, ORFAIG R, BOBROVSKY B Z. BoT SORT: Robust associations multi-pedestrian tracking[DB/ OL]. (2022-07-07) [2024-09-25]. https://arxiv.org/abs/ 2206.14651.

[16] CHEN T, GUESTRIN C. Xgboost: A scalable tree boosting system[C]// New York: Association for Computing Machinery, Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016.

[17] JOCHER G, CHAURASIA A, QIU J. Ultralytics YOLO [EB/OL]. (2023-11-12) [2024-09-25]. https://github. com/ultralytics/ultralytics.

[18] LLERENA J M, ZENI L F, KRISTEN L N, et al. Gaussian bounding boxes and probabilistic intersection- over-union for object detection[DB/OL]. (2021-06-10) [2024-09-25]. https://arxiv.org/abs/2106.06072.

[19] SUTHAHARAN S, SUTHAHARAN S. Support vector machine[J]. Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning, 2016, 36: 207-235.

[20] GENUER R, POGGI J M, GENUER R, et al. Random forests[M]. Springer, Cham: Springer International Publishing, 2020.

基于车辆动态行为特征的交通状态识别研究

Traffic State Recognition Based on Vehicle Dynamic Behavior Characteristics

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]	晋泽倩, 俞诚成, 叶昕. 混合效用和后悔规则下的洪涝交通疏散决策行为研究[J]. 交通运输系统工程与信息, 2025, 25(2): 16-25.
[2]	周雨阳, 赵聪颖, 李京昆, 陈艳艳, 柳堤, 王书灵. 多类城市职住及通勤状态对出行方式选择影响比较[J]. 交通运输系统工程与信息, 2025, 25(2): 26-35.
[3]	彭其渊, 刘思源, 江山, 冯涛, 陈垚, 张永祥. 贯通运营下市域铁路与地铁列车开行方案协同优化[J]. 交通运输系统工程与信息, 2025, 25(2): 36-47.
[4]	蒋阳升, 叶肖甫, 徐尉耀, 刘洪汛, 胡路. 考虑转运与拼车的共享自动驾驶电动汽车动态运营[J]. 交通运输系统工程与信息, 2025, 25(2): 58-68.
[5]	赵雪亭, 胡立伟, 周君. 城市交通拥塞风险场级联失效及韧性评估研究[J]. 交通运输系统工程与信息, 2025, 25(2): 146-156.
[6]	武慧荣, 王玉莹, 盛椿婷. 考虑动态需求的城市货运公交线路规划模型研究[J]. 交通运输系统工程与信息, 2025, 25(2): 214-226.
[7]	徐伟汉, 李欣, 王天奇. 基于生态驾驶的常规和需求响应公交混合调度方法[J]. 交通运输系统工程与信息, 2025, 25(2): 227-240.
[8]	李昊, 陈绍宽, 徐彬, 石梦彤, 肖迪, 陈梓琦. 考虑值乘能力差异的地铁跨线乘务轮班计划优化方法[J]. 交通运输系统工程与信息, 2025, 25(2): 253-260.
[9]	薛锋, 肖恩, 杨颖, 金成, 罗建. 基于多旅行商问题建模的地铁乘务排班计划优化[J]. 交通运输系统工程与信息, 2025, 25(2): 261-272.
[10]	张鹏, 吴照杰, 孙超, 李文权. 路口混合放行下的干线红波带宽最小优化模型[J]. 交通运输系统工程与信息, 2025, 25(2): 293-303.
[11]	许奇, 秦贝宁, 任澎, 陈越, 赖瑾璇. 建成环境对公交接驳地铁客流的异质性影响[J]. 交通运输系统工程与信息, 2025, 25(2): 352-363.
[12]	姚明, 王宇航, 曹淑超, 马露涵. 手机分心条件下行人运动特性研究[J]. 交通运输系统工程与信息, 2025, 25(2): 364-372.
[13]	翁剑成, 周慧缘, 张梦媛, 于江波. 考虑城市与群体异质的新能源车激励策略有效性研究[J]. 交通运输系统工程与信息, 2025, 25(1): 2-14.
[14]	王连震, 马志飞, 程国柱, 郑夫水. 城市道路智能网联汽车专用车道设置研究[J]. 交通运输系统工程与信息, 2025, 25(1): 56-66.
[15]	左忠义, 刘泽宇, 杨广川. 基于引力影响模型的轨道交通网络关键节点识别研究[J]. 交通运输系统工程与信息, 2025, 25(1): 102-112.