基于低频GNSS轨迹的转向级城市交通信息精细预测

doi:10.11947/j.AGCS.2021.20210252

测绘学报 ›› 2021, Vol. 50 ›› Issue (11): 1469-1477.doi: 10.11947/j.AGCS.2021.20210252

基于低频GNSS轨迹的转向级城市交通信息精细预测

方孟元¹, 唐炉亮¹, 杨雪², 胡淳¹

1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
2. 中国地质大学(武汉)地理与信息工程学院, 湖北武汉 430074

收稿日期:2021-05-09 修回日期:2021-07-17 发布日期:2021-12-07
通讯作者: 唐炉亮 E-mail:tll@whu.edu.cn
作者简介:方孟元(1995—),男,博士生,研究方向为地理信息科学、时空数据挖掘等。
基金资助:
国家重点研发计划（2017YFB0503604；2016YFE0200400）；国家自然科学基金（41971405；41671442；41901394）；武大-华为空间信息技术创新实验室资助项目

Fine-grained traffic information prediction at the turning-level based on low-frequency GNSS trajectory data

FANG Mengyuan¹, TANG Luliang¹, YANG Xue², HU Chun¹

1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2. School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China

Received:2021-05-09 Revised:2021-07-17 Published:2021-12-07
Supported by:
The National Key Research and Development Program of China (Nos. 2017YFB0503604;2016YFE0200400);The National Natural Science Foundation of China (Nos. 41971405;41671442;41901394);Wuhan University-Huawei Geoinformatics Innovation Laboratory

摘要/Abstract

摘要： 利用浮动车GNSS轨迹数据可以实时获取和预测城市交通状态，且覆盖范围广、部署成本低，对自动驾驶路线决策、交通拥堵治理具有重要的支撑作用。现阶段，利用浮动车GNSS轨迹数据预测的信息仅包含路段上的交通速度、状态，而忽略了交叉口内不同行驶方向上的交通流差异；且交通信息准确性受到GNSS采样频率的限制。本文提出一种基于图卷积网络和低频GNSS轨迹数据的转向级交通预测方法：首先，顾及轨迹点间车辆运动模式提出一种排队起始点估计模型；然后，基于对偶图理论构建转向连通关系的图结构；最后，基于图卷积网络提出一种顾及转向时空模式的交通预测模型。试验结果显示，本文方法能准确地获取和预测转向级交通速度、排队长度信息，交通预测准确性全面优于基准方法。

关键词: GNSS轨迹, 图卷积网络, 数据挖掘, 短时交通预测, 转向级

Abstract: The floating-car GNSS trajectory data have been widely used to obtain and predict the urban traffic status in real time, with wide coverage and low deployment cost, and the result has an important supporting role for route decision-making of automatic driving and traffic management. However, the traffic information predicted by the floating-car GNSS data only contains the traffic information on each road segment, ignoring the difference of the traffic flow in different driving directions at the intersection; besides, the accuracy of the traffic information is limited by the GNSS sampling frequency. This paper proposes a turning-level traffic prediction method based on graph convolutional network and low-frequency GNSS trajectory data: first, a queuing-starting-point estimation model is proposed considering vehicle movement pattern; second, a Graph-structure of the turning connection relationship is constructed based on the dual graph theory; finally, to consider spatio-temporal pattern, a traffic prediction model is constructed based on the graph convolutional network. The experimental results show that our method can accurately obtain and predict the traffic speed and queue length at turning-level, and effectively improve the accuracy of traffic prediction by learning the spatio-temporal pattern within the Graph.

Key words: GNSS trajectory, graph convolutional network, data mining, short-term traffic prediction, turning-leve

中图分类号:

P208

方孟元, 唐炉亮, 杨雪, 胡淳. 基于低频GNSS轨迹的转向级城市交通信息精细预测[J]. 测绘学报, 2021, 50(11): 1469-1477.

FANG Mengyuan, TANG Luliang, YANG Xue, HU Chun. Fine-grained traffic information prediction at the turning-level based on low-frequency GNSS trajectory data[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1469-1477.

参考文献

[1] 陆建. 城市交通系统可持续发展规划理论与方法[D]. 南京: 东南大学, 2003. LU Jian. Sustainable planning theory and method of urban transportation system[D]. Nanjing: Southeast University, 2003.
[2] 唐炉亮, 阚子涵, 段倩, 等. 一种时空路径支持下的车辆油耗与排放估计方法[J]. 测绘学报, 2017, 46(12): 2024-2031. DOI: 10.11947/j.AGCS.2017.20160439. TANG Luliang, KAN Zihan, DUAN Qian, et al. A space-time path supported estimation approach for vehicles’ fuel-consumption and emissions[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(12): 2024-2031. DOI: 10.11947/j.AGCS.2017.20160439.
[3] 唐炉亮, 牛乐, 杨雪, 等. 利用轨迹大数据进行城市道路交叉口识别及结构提取[J]. 测绘学报, 2017, 46(6): 770-779. DOI: 10.11947/j.AGCS.2017.20160614. TANG Luliang, NIU Le, YANG Xue, et al. Urban intersection recognition and construction based on big trace data[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(6): 770-779. DOI: 10.11947/j.AGCS.2017.20160614.
[4] TALMOR I, MAHALEL D. Signal design for an isolated intersection during congestion[J]. Journal of the Operational Research Society, 2007, 58(4): 454-466. DOI: 10.1057/palgrave.jors.2602146.
[5] 《中国公路学报》编辑部. 中国汽车工程学术研究综述·2017[J]. 中国公路学报, 2017, 30(6): 1-197. Editorial Department of China Journal of Highway and Transport. Review on China’s automotive engineering research progress: 2017[J]. China Journal of Highway and Transport, 2017, 30(6): 1-197.
[6] 徐正, 王怿超, 黄璇, 等. 基于交通摄像头视频的车牌识别与测速[J]. 江西科学, 2012, 30(4): 528-531. XU Zheng, WANG Yichao, HUANG Xuan, et al. License plate recognition and speed based on the traffic camera video[J]. Jiangxi Science, 2012, 30(4): 528-531.
[7] 高富荣, 方强. 机动车地感线圈测速监测系统性能和检测方法研究[J]. 上海计量测试, 2008, 35(2): 27-28. GAO Furong, FANG Qiang. The research on method of performance testing and verification for traffic loop-based speed meter[J]. Shanghai Measurement and Testing, 2008, 35(2): 27-28.
[8] PREMEBIDA C, MONTEIRO G, NUNES U, et al. A LiDAR and vision-based approach for pedestrian and vehicle detection and tracking[C]//Proceedings of 2007 IEEE Intelligent Transportation Systems Conference. Bellevue, WA, USA: IEEE, 2007: 1044-1049.
[9] CETIN M. Estimating queue dynamics at signalized intersections from probe vehicle data: methodology based on kinematic wave model[J]. Transportation Research Record: Journal of the Transportation Research Board, 2012, 2315(1): 164-172. DOI: 10.3141/2315-17.
[10] HIRIBARREN G, HERRERA J C. Real time traffic states estimation on arterials based on trajectory data[J]. Transportation Research Part B: Methodological, 2014(69): 19-30. DOI: 10.1016/j.trb.2014.07.003.
[11] 冯毅文. 基于大规模车辆轨迹数据的道路交叉口排队长度探测[D]. 深圳: 深圳大学, 2017. FENG Yiwen. Queue length detection of road intersection based on large scale vehicle trajectory data[D]. Shenzhen: Shenzhen University, 2017.
[12] TIŠLJARIĆ L, ERDELIĆ T, CARIĆ T. Analysis of intersection queue lengths and level of service using GPS data[C]//Proceedings of 2018 International Symposium ELMAR. Zadar, Croatia: IEEE, 2018: 43-46.
[13] 唐炉亮, 阚子涵, 任畅, 等. 利用GPS轨迹的转向级交通拥堵精细分析[J]. 测绘学报, 2019, 48(1): 75-85. DOI: 10.11947/j.AGCS.2019.20170448. TANG Luliang, KAN Zihan, REN Chang, et al. Fine-grained analysis of traffic congestions at the turning level using GPS traces[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(1): 75-85. DOI: 10.11947/j.AGCS.2019.20170448.
[14] 沈敬伟, 周廷刚, 朱晓波. 基于GPS浮动车数据的交通信息时空分布研究[J]. 西南大学学报(自然科学版), 2015, 37(8): 157-162. SHEN Jingwei, ZHOU Tinggang, ZHU Xiaobo. On the spatial and temporal distribution of traffic information based on GPS floating car data[J]. Journal of Southwest University (Natural Science Edition), 2015, 37(8): 157-162.
[15] 李勇. 基于出租车GPS数据的城市交通拥堵识别和关联性分析[D]. 哈尔滨: 哈尔滨工业大学, 2016. LI Yong. Congestion identification and correlation analysis on urban traffic based on taxi GPS data[D]. Harbin: Harbin Institute of Technology, 2016.
[16] 杨海强. 基于出租车GPS数据的城市常发性交通拥堵演变研究[D]. 哈尔滨: 哈尔滨工业大学, 2018. YANG Haiqiang. Research of urban recurrent congestion evolution based on taxi GPS data[D]. Harbin: Harbin Institute of Technology, 2018.
[17] 韩超, 宋苏, 王成红. 基于ARIMA模型的短时交通流实时自适应预测[J]. 系统仿真学报, 2004, 16(7): 1530-1532, 1535. HAN Chao, SONG Su, WANG Chenghong. A real-time short-term traffic flow adaptive forecasting method based on ARIMA model[J]. Journal of System Simulation, 2004, 16(7): 1530-1532, 1535.
[18] THOMAS T, WEIJERMARS W, VAN BERKUM E. Predictions of urban volumes in single time series[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(1): 71-80. DOI: 10.1109/TITS.2009.2028149.
[19] SUN Shiliang, ZHANG Changshui, YU Guoqiang. A Bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132. DOI: 10.1109/TITS.2006.869623.
[20] MA Xiaolei, DAI Zhuang, HE Zhengbing, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 818. DOI: 10.3390/s17040818.
[21] 罗文慧, 董宝田, 王泽胜. 基于CNN-SVR混合深度学习模型的短时交通流预测[J]. 交通运输系统工程与信息, 2017, 17(5): 68-74. LUO Wenhui, DONG Baotian, WANG Zesheng. Short-term traffic flow prediction based on CNN-SVR hybrid deep learning model[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(5): 68-74.
[22] 闫旭, 范晓亮, 郑传潘, 等. 基于图卷积神经网络的城市交通态势预测算法[J]. 浙江大学学报(工学版), 2020, 54(6): 1147-1155. YAN Xu, FAN Xiaoliang, ZHENG Chuanpan, et al. Urban traffic flow prediction algorithm based on graph convolutional neural networks[J]. Journal of Zhejiang University (Engineering Science), 2020, 54(6): 1147-1155.
[23] YU Bing, YIN Haoteng, ZHU Zhanxing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: IJCAI, 2018: 3634-3640.
[24] ZHANG Junbo, ZHENG Yu, QI Dekang, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018(259): 147-166.
[25] ZHAO Ling, SONG Yujiao, ZHANG Chao, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[26] EL-SHAWARBY I, RAKHA H, INMAN V W, et al. Evaluation of driver deceleration behavior at signalized intersections[J]. Transportation Research Record: Journal of the Transportation Research Board, 2007, 2018(1): 29-35.
[27] 郑年波, 陆锋, 段滢滢. 道路转向延迟的动态对偶图模型[J]. 中国图象图形学报, 2010, 15(6): 915-920. ZHENG Nianbo, LU Feng, DUAN Yingying. Dynamic dual-graph model for turn delays on road networks[J]. Journal of Image and Graphics, 2010, 15(6): 915-920.
[28] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.
[29] MA Xiaolei, YU Haiyang, WANG Yunpeng, et al. Large-scale transportation network congestion evolution prediction using deep learning theory[J]. PLoS One, 2015, 10(3): e0119044. DOI: 10.1371/journal.pone.0119044.

基于低频GNSS轨迹的转向级城市交通信息精细预测

Fine-grained traffic information prediction at the turning-level based on low-frequency GNSS trajectory data

RichHTML

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

本文评价

[1]	刘耀林, 刘启亮, 邓敏, 石岩. 地理大数据挖掘研究进展与挑战[J]. 测绘学报, 2022, 51(7): 1544-1560.
[2]	傅琛, 黄升钶, 汤焱, 吴杭彬, 刘春, 姚连璧, 黄炜. 结合行驶场景语义的轨迹-路网实时匹配方法[J]. 测绘学报, 2021, 50(11): 1617-1627.
[3]	左溪冰, 刘冰, 余旭初, 张鹏强, 高奎亮, 朱恩泽. 高光谱影像小样本分类的图卷积网络方法[J]. 测绘学报, 2021, 50(10): 1358-1369.
[4]	刘纪平, 张用川, 徐胜华, 钱新林, 仇阿根, 张福浩. 一种顾及道路复杂度的增量路网构建方法[J]. 测绘学报, 2019, 48(4): 480-488.
[5]	吴华意, 黄蕊, 游兰, 向隆刚. 出租车轨迹数据挖掘进展[J]. 测绘学报, 2019, 48(11): 1341-1356.
[6]	王培晓, 张恒才, 王海波, 吴升. ST-CFSFDP:快速搜索密度峰值的时空聚类算法[J]. 测绘学报, 2019, 48(11): 1380-1390.
[7]	唐炉亮, 阚子涵, 任畅, 张霞, 李清泉. 利用GPS轨迹的转向级交通拥堵精细分析[J]. 测绘学报, 2019, 48(1): 75-85.
[8]	杨学习, 邓敏, 石岩, 唐建波, 刘启亮. 一种空间交叉异常显著性判别的非参数检验方法[J]. 测绘学报, 2018, 47(9): 1250-1260.
[9]	李明晓, 张恒才, 仇培元, 程诗奋, 陈洁, 陆锋. 一种基于模糊长短期神经网络的移动对象轨迹预测算法[J]. 测绘学报, 2018, 47(12): 1660-1669.
[10]	兰泽英, 刘洋. 领域知识辅助下基于多尺度与主方向纹理的遥感影像土地利用分类[J]. 测绘学报, 2016, 45(8): 973-982.
[11]	何占军, 刘启亮, 邓敏, 蔡建南. 显著空间同位模式的多尺度挖掘方法[J]. 测绘学报, 2016, 45(11): 1335-1341.
[12]	李德仁, 李熙. 论夜光遥感数据挖掘[J]. 测绘学报, 2015, 44(6): 591-601.
[13]	胡庆武王明李清泉. 利用位置签到数据探索城市热点与商圈[J]. 测绘学报, 2014, 43(3): 314-321.
[14]	李德仁, 张良培, 夏桂松. 遥感大数据自动分析与数据挖掘[J]. 测绘学报, 2014, 43(12): 1211-1216.
[15]	刘启亮,邓敏,石岩,彭东亮. 一种基于多约束的空间聚类方法[J]. 测绘学报, 2011, 40(4): 0-441.