车牌识别设备稀疏布局下的路段行程时间估计方法

doi:10.16097/j.cnki.1009-6744.2025.05.007

交通运输系统工程与信息 ›› 2025, Vol. 25 ›› Issue (5): 83-90.DOI: 10.16097/j.cnki.1009-6744.2025.05.007

车牌识别设备稀疏布局下的路段行程时间估计方法

王殿海¹，王奕飞¹，黄宇浪¹，刘泳¹，曾佳棋^*1,2

1. 浙江大学，建筑工程学院，智能交通研究所，杭州310058；2.浙江大学中原研究院，郑州450001

收稿日期:2025-06-23 修回日期:2025-07-21 接受日期:2025-08-05 出版日期:2025-10-25 发布日期:2025-10-25
作者简介:王殿海(1962—)，男，吉林大安人，教授，博士。
基金资助:
国家自然科学基金(52402391, 52131202)。

Estimating Link Travel Time Under Sparse License Plate Recognition Device Coverage

WANG Dianhai¹, WANG Yifei¹, HUANG Yulang¹, LIU Yong¹, ZENG Jiaqi^*1,2

1. Institute of Intelligent Transportation System, College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China; 2. Zhejiang University Zhongyuan Institute, Zhengzhou 450001, China

Received:2025-06-23 Revised:2025-07-21 Accepted:2025-08-05 Online:2025-10-25 Published:2025-10-25
Supported by:
National Natural Science Foundation of China (52402391, 52131202)。

摘要/Abstract

摘要： 车牌识别设备是城市路网中重要的交通状态检测器，但高昂的成本限制了其安装规模和密度。本文提出设备稀疏布局条件下的城市道路路段行程时间估计方法，考虑驻留轨迹的行程时间异常值干扰，将路段行程时间测量问题转化为混合整数优化模型，并设计基于不动点的交替求解方法。根据路段行程时间分布计算路径行程时间分布，识别异常行程时间；设计行程时间分配方法，将正常轨迹行程时间分配至各个路段；为确保计算稳定性，对高流量路段的行程时间分布参数进行贝叶斯更新，并将参数比例关系推广至流量不足的路段；通过迭代实现路段行程时间和异常轨迹的联合估计。杭州市真实车牌识别数据集的实验表明：70%设备覆盖率下，本文方法的平均百分比误差(MAPE)为13.29%；与梯度下降法相比，MAPE降低了7.69%，迭代次数减少了99.4%；针对车牌识别设备更加稀疏的城市场景，当设备覆盖率降至30%时，本文方法的MAPE仅为18.51%。

关键词: 智能交通, 交通状态, 组合优化, 路段行程时间, 车牌识别数据, 稀疏检测器

Abstract: License Plate Recognition (LPR) devices are crucial traffic state detectors in urban road networks, but the high cost limits their deployment scale and density. This paper proposes a method for urban road network link travel time estimation under sparse devices deployment. Considering the interference of dwell trajectory travel time outliers, this study develops a mixed-integer optimization model for the link travel time measurement, and proposes an alternating solution method based on fixed-point iteration. First, path travel time distributions are calculated based on link travel time distributions to identify abnormal travel times. A travel time assignment method is then designed to allocate normal trajectory travel times to individual links. To ensure computational stability, Bayesian updating is applied to the travel time distribution parameters of high-traffic links, and the parameter proportionality is extended to links with insufficient traffic flow. Link travel times and abnormal trajectories are jointly estimated through iteration procession. Experiments on a real LPR dataset from Hangzhou demonstrate that the proposed method achieves a mean percentage error (MAPE) of 13.29% under a 70% device penetration rate. Compared to the gradient descent method, the MAPE is reduced by 7.69%, and the number of iterations is reduced by 99.4%. Furthermore, for urban scenarios with even sparser LPR device coverage, when the device coverage rate drops to 30%, the proposed method results in the MAPE of 18.51%.

Key words: intelligent transportation, traffic state, combinatorial optimization, link travel time, license plate recognition data; sparse detectors

中图分类号:

U495

王殿海, 王奕飞, 黄宇浪, 刘泳, 曾佳棋. 车牌识别设备稀疏布局下的路段行程时间估计方法[J]. 交通运输系统工程与信息, 2025, 25(5): 83-90.

WANG Dianhai, WANG Yifei, HUANG Yulang, LIU Yong, ZENG Jiaqi. Estimating Link Travel Time Under Sparse License Plate Recognition Device Coverage[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(5): 83-90.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2025.05.007

http://www.tseit.org.cn/CN/Y2025/V25/I5/83

参考文献

[1] ÇOLAK S, LIMA A, GONZÁLEZ M C. Understanding congested travel in urban areas[J]. Nature Communications, 2016, 7(1): 10793–10801.

[2] DU S, IBRAHIM M, SHEHATA M, et al. Automatic license plate recognition (ALPIR): A state-of-the-art review[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(2): 311–325.

[3] DION F, RAKHA H. Estimating dynamic roadway travel times using automatic vehicle identification data for low sampling rates[J]. Transportation Research Part B: Methodological, 2006, 40(9): 745–766.

[4] PROKHORCHUK A, DAUWEIS J, JAILLET P. Estimating travel time distributions by bayesian network inference[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(5): 1867–1876.

[5] RAHMANI M, JENELIUS E, KOUTSOPOULOS H N. Non-parametric estimation of route travel time distributions from low-frequency floating car data[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 343–362.

[6] XU C, WANG Q, SUN L. Link representation learning for probabilistic travel time estimation[A]. arXiv, 2024.

[7] YU T, MA J. A review of the link traffic time estimation of urban traffic[C]. Singapore: Nanyang Executive Center of NTU, 2016.

[8] ZHAN X, HASAN S, UKKUSURI S V, et al. Urban link travel time estimation using large-scale taxi data with partial information[J]. Transportation Research Part C: Emerging Technologies, 2013, 33: 37–49.

[9] BERTSUMS D, DELARUE A, JAILLET P, et al. Travel time estimation in the age of big data[J]. Operations Research, 2019, 67(2): 498–515.

[10] PARK H, KIM Y. Model for filtering the outliers in DSRC travel time data on interrupted traffic flow sections [J]. KSCE Journal of Civil Engineering, 2018, 22(9): 3607–3619.

[11] LI A, LAM W H K, MA W, et al. Filtering limited automatic vehicle identification data for real-time path travel time estimation without ground truth[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(6): 4849–4861.

[12] 杨玲敏, 佘日辉,王红,等.随机时变特征下基于行程时间的路径选择算法[J]. 交通运输系统工程与信息, 2017, 17(5): 122–128, 143. [YANG L M, SHE R H, WANG H. Path choosing algorithm based on travel time under stochastic time-varying characteristics[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(5): 122–128, 143.]

[13] ZHENG F, VAN ZUYLEN H. Urban link travel time estimation based on sparse probe vehicle data[J]. Transportation Research Part C: Emerging Technologies, 2013, 31: 145–157.

[14] 王璞, 熊雨沙,王骋程,等.基于路径旅行时间分析的交通异常检测方法[J]. 电子科技大学学报, 2018, 47 (6): 869–875. [WANG P, XIONG Y S, WANG C C. Traffic anomaly detection method based on travel time of path[J]. Journal of University of Electronic Science and Technology of China, 2018, 47(6): 869–875.]

[15] HELLINGA B, IZADPANAH P, TAKADA H, et al. Decomposing travel times measured by probe-based traffic monitoring systems to individual road segments[J]. Transportation Research Part C: Emerging Technologies, 2008, 16: 768–782.

[16] HUANG L, YANG Y, CHEN H, et al. Context-aware road travel time estimation by coupled tensor decomposition based on trajectory data[J]. Knowledge-Based Systems, 2022, 245: 108596.

车牌识别设备稀疏布局下的路段行程时间估计方法

Estimating Link Travel Time Under Sparse License Plate Recognition Device Coverage

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]	田大新, 肖啸, 周建山. AI驱动的自动驾驶汽车轨迹预测方法综述[J]. 交通运输系统工程与信息, 2025, 25(5): 1-24.
[2]	程国柱, 王文志, 杨子涵, 汪国鹏, 陈永胜, 顾爽. 网联自动驾驶车辆专用车道设置研究综述[J]. 交通运输系统工程与信息, 2025, 25(5): 25-39.
[3]	吴付威, 杨慧, 马勇, 崔同川, 闫晟煜, 张智. L3级自动驾驶车辆两阶段预警对接管绩效影响研究[J]. 交通运输系统工程与信息, 2025, 25(5): 40-49.
[4]	窦雪萍, 杨明慧, 熊杰. 考虑自适应控制点的自动驾驶公交运行优化方法[J]. 交通运输系统工程与信息, 2025, 25(5): 50-58.
[5]	宋浪, 胡晓伟, 俞山川, 安实. 网联自动驾驶环境下交叉口车道分配与车辆轨迹协同优化[J]. 交通运输系统工程与信息, 2025, 25(5): 59-71.
[6]	林培群, 黄超铄, 周楚昊, 庞崇浩, 邓锴宇. 数据驱动的高速公路自学习元胞传输模型[J]. 交通运输系统工程与信息, 2025, 25(5): 103-113.
[7]	李传耀, 章孟丹, 唐铁桥. 考虑模块化公交供应限制的双模式早通勤均衡分析[J]. 交通运输系统工程与信息, 2025, 25(5): 205-214.
[8]	沈鹏举, 宋丽英, 林川倩. 高铁列车晚点数据的异常检测与增量聚类方法[J]. 交通运输系统工程与信息, 2025, 25(5): 236-247.
[9]	杨静, 侯宇晴, 谢余晨, 杨安安. 城市轨道交通网络短时OD客流多任务协同预测[J]. 交通运输系统工程与信息, 2025, 25(5): 261-270.
[10]	姚振兴, 刘贤, 赵一飞, 王亮, 王彦琛. 手机信令不均匀定位下出行端点自适应识别方法[J]. 交通运输系统工程与信息, 2025, 25(4): 44-52.
[11]	张鹏, 李兴旺, 姬炳豪, 孙超, 李文权. 路口重复放行的公交与社会车辆协同绿波优化模型[J]. 交通运输系统工程与信息, 2025, 25(4): 53-62.
[12]	代亮, 杜鹏飞, 黄自彬, 杨朋博. 基于深度强化学习的城市交通信号分层协同控制方法[J]. 交通运输系统工程与信息, 2025, 25(4): 63-72.
[13]	王庞伟, 王思淼, 雷方舒, 徐京辉, 王子鹏, 王力. 混合动作表示强化学习下的城市交叉口智慧信控方法[J]. 交通运输系统工程与信息, 2025, 25(4): 73-83.
[14]	王连震, 沈超文, 王宇萍, 薛淑祺. 网联高速公路合流区基于间隙优化的车辆协同控制方法[J]. 交通运输系统工程与信息, 2025, 25(4): 84-95.
[15]	王维锋, 黄建鑫, 王晓全, 吴昕韩, 卞子馨. 基于无锚旋转框的航拍图像车辆全向检测方法[J]. 交通运输系统工程与信息, 2025, 25(4): 104-115.