基于DBI和稀疏轨迹数据的交通状态精细划分与识别

doi:10.12082/dqxxkx.2022.210408

地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (3): 458-468.doi: 10.12082/dqxxkx.2022.210408

• 地球信息科学理论与方法 • 上一篇下一篇

基于DBI和稀疏轨迹数据的交通状态精细划分与识别

朱秋圳¹^,²^,³(), 邬群勇¹^,²^,³^,^*(), 姚铖鑫¹^,²^,³, 孙豪宇¹^,²^,³

1.福州大学空间数据挖掘与信息共享教育部重点实验室,福州 350108
2.卫星空间信息技术综合应用国家地方联合工程研究中心,福州 350108
3.福州大学数字中国研究院（福建）,福州 350108

收稿日期:2021-07-18 修回日期:2021-08-30 出版日期:2022-03-25 发布日期:2022-05-25
通讯作者: *邬群勇（1973— ）,男,山东诸城人,研究员,主要从事时空数据挖掘和地理信息服务研究。 E-mail: qywu@fzu.edu.cn
作者简介:朱秋圳（1996— ）,男,福建平和人,硕士生,主要从事时空数据挖掘研究。E-mail: zqiiuz@163.com
基金资助:
国家自然科学基金项目(41471333);中央引导地方科技发展专项(2017L3012)

Fine Classification and Identification of Traffic States based on DBI and Sparse Trajectory Data

ZHU Qiuzhen¹^,²^,³(), WU Qunyong¹^,²^,³^,^*(), YAO Chengxin¹^,²^,³, SUN Haoyu¹^,²^,³

1. Key Lab of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350108, China
2. National & Local Joint Engineering Research Center of Satellite Geospatial Information Technology, Fuzhou 350108, China
3. The Academy of Digital China (Fujian), Fuzhou 350108, China

Received:2021-07-18 Revised:2021-08-30 Online:2022-03-25 Published:2022-05-25
Contact: WU Qunyong
Supported by:
National Natural Science Foundation of China(41471333);The Central Guided Local Development of Science and Technol- ogy Project(2017L3012)

摘要/Abstract

摘要：

浮动车轨迹数据已逐渐成为城市交通状态识别的主要数据源之一,但是现有基于浮动车轨迹数据的交通状态识别中多数是应用高精度或是多源轨迹数据。针对稀疏轨迹数据在城市交通状态识别中存在识别精度不高的问题,本文提出一种结合戴维森堡丁指数（DBI）和轨迹相似性度量的动态交通状态划分方法。首先,对轨迹数据和路网数据进行预处理并且建立不同时间片的路段轨迹集合;接着,依据轨迹速度-空间相似性,利用戴维森堡丁指数动态地扩展轨迹的空间维度,并根据轨迹相似性度量方法构建最佳车辆队列;然后,将前后不同的车辆队列进行二次处理,连接组成交通流簇;最后,基于模糊C均值聚类方法将交通流进行划分,实现路段交通状态的识别。采用厦门市厦禾路、湖滨西路和湖滨南路交叉路段上的真实出租车轨迹数据进行测试,结果表明,本文所提方法保证了车辆队列速度分布与原始轨迹速度分布基本一致,相比对比方法Kmeans++和ST-DBSCAN,本文方法均方根误差平均下降了18.77%和21.22%,并且在不同的实验路段表现更加稳定,可有效、可靠地运用稀疏轨迹数据识别城市交通状态,进而实现城市交通状态的精细分析。

关键词: 城市交通, 动态划分, 轨迹相似性度量, 稀疏轨迹数据, 戴维森堡丁指数, 车辆队列, 状态识别, 模糊聚类

Abstract:

Compared with traditional traffic detection data, floating vehicle trajectory data have the characteristics of wide coverage, low cost, and high mobility, which have been widely used in urban traffic status recognition and have gradually become one of the main data sources for urban traffic state recognition. However, most of the existing traffic state recognition based on floating vehicle trajectory data is based on high-precision or multi-source trajectory data. To address the problem of low accuracy of sparse trajectory data in urban traffic state recognition, this paper proposes a dynamic traffic state classification method combining Davies-Bouldin Index (DBI) and trajectory similarity metric to finely classify urban road traffic state, and then realizes the spatial and temporal characteristics of urban traffic state. Firstly, we pre-process the trajectory data and road network data, including data cleaning, map matching, and format conversion, record the relative spatial distances between trajectory points and matching road sections, and build a set of trajectories of road sections in different time slices. Secondly, we dynamically extend the spatial dimension of trajectories by using Davies-Bouldin Index (DBI) according to the trajectory speed-spatial similarity, and construct the best vehicle queue according to the trajectory similarity measure. After that, the different vehicle queues before and after are processed twice, and the vehicle queues are merged according to the rules and connected to form traffic flow clusters, so as to achieve the purpose of dividing local road sections and laying the foundation for subsequent recognition of local traffic states. Finally, the global trajectory points are clustered based on the fuzzy C-means clustering method to divide traffic states, and the speed bounds of different traffic states are obtained and compared with the previous traffic flow cluster speed The comparison is carried out to realize the local road traffic state identification, and then realize the fine analysis of traffic state. The real cab trajectory data at the intersection sections of Xiamen Xiahe Road, Hubin West Road, and Hubin South Road are used for testing. The results show that the traffic speed map calculated by the trajectory similarity metric method can reflect the changes of traffic speed on the road section more clearly, and the method ensures that the vehicle queuing speed distribution is basically consistent with the original trajectory speed distribution. Compared with the comparison methods, i.e., Kmeans++ and ST-DBSCAN, the root-mean-square error of the proposed method decreases by 18.77% and 21.22% on average, and it performs more stable and robust in different experimental road sections. It can effectively and reliably use sparse trajectory data to identify urban traffic states, and then realize the fine analysis of urban traffic states, which provides auxiliary decisions for the management of urban road traffic problems.

Key words: urban traffic, dynamic segmentation, similarity metrics, sparse trajectory data, Davies-Bouldin index, vehicle queues, status recognition, fuzzy cluster

朱秋圳, 邬群勇, 姚铖鑫, 孙豪宇. 基于DBI和稀疏轨迹数据的交通状态精细划分与识别[J]. 地球信息科学学报, 2022, 24(3): 458-468.DOI:10.12082/dqxxkx.2022.210408

ZHU Qiuzhen, WU Qunyong, YAO Chengxin, SUN Haoyu. Fine Classification and Identification of Traffic States based on DBI and Sparse Trajectory Data[J]. Journal of Geo-information Science, 2022, 24(3): 458-468.DOI:10.12082/dqxxkx.2022.210408

图/表 11

表1

图1

图2

图3

图4

图5

图6

图7

表2

图8

图9

参考文献 24

[1]	闫学东, 刘晓冰, 刘炀, 等. 基于浮动车大数据与网格模型的城市交通拥堵识别和评价研究[J]. 北京交通大学学报, 2019, 43(1):104-113.
	[ Yan X D, Liu X B, Liu Y, et al. Identification and evaluation of urban traffic congestion based on the big data of floating vehicles and grid modeling[J]. Journal of Beijing Jiaotong University, 2019, 43(1):104-113. ] DOI: 10.11860/j.issn.1673-0291.2019.01.012
[2]	Zheng Y. Trajectory data mining: an overview[J]. ACM Transactions on Intelligent Systems and Technology, 2015, 6(3):1-41. DOI: 10.1145/2743025
[3]	吴华意, 黄蕊, 游兰, 等. 出租车轨迹数据挖掘进展[J]. 测绘学报, 2019, 48(11):1341-1356.
	[ Wu H Y, Huang R, You L, et al. Recent progress in taxi trajectory data mining[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(11):1341-1356. ] DOI: 10.11947/j.AGCS.2019.20190210
[4]	黄子赫, 高尚兵, 蔡创新, 等. 多重处理的道路拥堵识别可视化融合分析[J]. 中国图象图形学报, 2020, 25(2):409-418.
	[ Huang Z H, Gao S B, Cai C X, et al. Visual fusion analysis of multiple-processing traffic congestion detection[J]. Journal of Image and Graphics, 2020, 25(2):409-418. ] DOI: 10.11834/jig.190272
[5]	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. ] DOI: 10.16097/j.cnki.1009-6744.2020.01.013
[6]	An S, Yang H Q, Wang J A, et al. Mining urban recurrent congestion evolution patterns from GPS-equipped vehicle mobility data[J]. Information Sciences, 2016, 373:515-526. DOI: 10.1016/j.ins.2016.06.033 doi: 10.1016/j.ins.2016.06.033
[7]	Chaurasia B K, Manjoro W S, Dhakar M. Traffic congestion identification and reduction[J]. Wireless Personal Communications, 2020, 114(2):1267-1286. DOI: 10.1007/s11277-020-07420-0 doi: 10.1007/s11277-020-07420-0
[8]	Kalinic M, Krisp J M. Fuzzy inference approach in traffic congestion detection[J]. Annals of GIS, 2019, 25(4):329-336. DOI: 10.1080/19475683.2019.1675760 doi: 10.1080/19475683.2019.1675760
[9]	Wang S L, Huang W, Lo H K. Traffic parameters estimation for signalized intersections based on combined shockwave analysis and Bayesian Network[J]. Transportation Research Part C: Emerging Technologies, 2019, 104:22-37. DOI: 10.1016/j.trc.2019.04.023 doi: 10.1016/j.trc.2019.04.023
[10]	He Z B, Qi G Q, Lu L L, et al. Network-wide identification of turn-level intersection congestion using only low-frequency probe vehicle data[J]. Transportation Research Part C: Emerging Technologies, 2019, 108:320-339. DOI: 10.1016/j.trc.2019.10.001 doi: 10.1016/j.trc.2019.10.001
[11]	Zhao Y, Shen S Y, Liu H X. A hidden Markov model for the estimation of correlated queues in probe vehicle environments[J]. Transportation Research Part C: Emerging Technologies, 2021, 128:103-128. DOI: 10.1016/j.trc.2021.103128
[12]	Zhang H, Liu H X, Chen P, et al. Cycle-based end of queue estimation at signalized intersections using low-penetration-rate vehicle trajectories[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(8):3257-3272. DOI: 10.1109/TITS.2019.2925111 doi: 10.1109/TITS.6979
[13]	Zhao Y, Zheng J F, Wong W, et al. Various methods for queue length and traffic volume estimation using probe vehicle trajectories[J]. Transportation Research Part C: Emerging Technologies, 2019, 107:70-91. DOI: 10.1016/j.trc.2019.07.008 doi: 10.1016/j.trc.2019.07.008
[14]	Ramezani M, Geroliminis N. Queue profile estimation in congested urban networks with probe data[J]. Computer-Aided Civil and Infrastructure Engineering, 2015, 30(6):414-432. DOI: 10.1111/mice.12095 doi: 10.1111/mice.2015.30.issue-6
[15]	Han K, Piccoli B, Szeto W Y. Continuous-time link-based kinematic wave model: Formulation, solution existence, and well-posedness[J]. Transportmetrica B: Transport Dynamics, 2016, 4(3):187-222. DOI: 10.1080/21680566.2015.1064793 doi: 10.1080/21680566.2015.1064793
[16]	周艳, 李妍羲, 江荣贵, 等. 交通拥堵与预警信息交互传播动力学分析[J]. 地球信息科学学报, 2017, 19(10):1279-1286. doi: 10.3724/SP.J.1047.2017.01279
	[ Zhou Y, Li Y X, Jiang R G, et al. Dynamic analysis of interactive transmission of warning information and traffic congestion[J]. Journal of Geo-information Science, 2017, 19(10):1279-1286. ] DOI: 10.3724/SP.J.1047.2017.01279
[17]	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.
	[ Tang L L, Niu L, Yang X E, 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
[18]	李思宇, 向隆刚, 张彩丽, 等. 基于低频出租车轨迹的城市路网交叉口提取研究[J]. 地球信息科学学报, 2019, 21(12):1845-1854. doi: 10.12082/dqxxkx.2019.190187
	[ Li S Y, Xiang L G, Zhang C L, et al. Extraction of urban road network intersections based on low-frequency taxi trajectory data[J]. Journal of Geo-information Science, 2019, 21(12):1845-1854. ] DOI: 10.12082/dqxxkx.2019.190187
[19]	Hsueh Y L, Chen H C, Huang W J. A hidden Markov model-based map-matching approach for low-sampling-rate GPS trajectories[C]// 2017 IEEE 7th International Symposium on Cloud and Service Computing (SC2). IEEE, 2017:271-274. DOI: 10.1109/SC2.2017.52
[20]	付子圣, 李秋萍, 柳林, 等. 利用GPS轨迹二次聚类方法进行道路拥堵精细化识别[J]. 武汉大学学报·信息科学版, 2017, 42(9):1264-1270.
	[ Fu Z S, Li Q P, Liu L, et al. Identification of urban network congested segments using GPS trajectories double-clustering method[J]. Geomatics and Information Science of Wuhan University, 2017, 42(9):1264-1270. ] DOI: 10.13203/j.whugis20150036
[21]	张彭, 张晓松, 雷方舒, 等. 道路拥堵概率估计方法及其在城市交通运行评价中的应用[J]. 交通运输系统工程与信息, 2015, 15(6):161-169.
	[ Zhang P, Zhang X S, Lei F S, et al. A method for estimating road congestion probability and its application in urban traffic operation evaluation[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(6):161-169. ] DOI: 10.1 6097/j.cnki.1009-6744.2015.06.025
[22]	雷宁, 张光德, 陈玲娟. 基于改进模糊聚类算法的快速路交通状态分类评价[J]. 公路, 2017, 62(11):134-139.
	[ Lei N, Zhang G D, Chen L J. Evaluation of traffic status classification for urban expressway based on improved fuzzy clustering[J]. Highway, 2017, 62(11):134-139. ]
[23]	Yu J R, Stettler M E J, Angeloudis P, et al. Urban network-wide traffic speed estimation with massive ride-sourcing GPS traces[J]. Transportation Research Part C: Emerging Technologies, 2020, 112:136-152. DOI: 10.1016/j.trc.2020.01.023 doi: 10.1016/j.trc.2020.01.023
[24]	王美红. 基于实测数据的天津市交通拥堵时空关联性分析[D]. 北京:北京交通大学, 2019.
	[ Wang M H. Analyzing spatiotemporal association of traffic congestion based on empirical data in Tianjin[D]. Beijing: Beijing Jiaotong University, 2019. ]

字段	样例	注释
cid	75677bf5af02481b760fa11eae94031c	车辆id
status	1	载客状态
speed	29.6	速度/(km/h)
direction	9	车头朝向
time	2020-06-22 08:45:11	采样时间
lon	118.12°E	经度
lat	24°N	纬度

路段编号	使用方法	评价指标
路段编号	使用方法	RMSE	MAE
A	本文方法	7.53	10.18
	Kmeans++	9.87	14.43
	ST-DBSCAN	12.88	15.44
B	本文方法	8.54	10.5
	Kmeans++	10.31	12.63
	ST-DBSCAN	11.02	11.62
I	本文方法	9.02	11.4
	Kmeans++	10.85	13.02
	ST-DBSCAN	9.53	12.53
J	本文方法	8.46	8.87
	Kmeans++	8.77	10.63
	ST-DBSCAN	10.23	13.11

基于DBI和稀疏轨迹数据的交通状态精细划分与识别

Fine Classification and Identification of Traffic States based on DBI and Sparse Trajectory Data

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 24

相关文章 11

Metrics

本文评价

推荐阅读 0

[1]	邝嘉恒, 邬群勇. 接驳地铁站的共享单车时空均衡性分析与吸引区域优化[J]. 地球信息科学学报, 2022, 24(7): 1337-1348.
[2]	黄洁, 石雯茜, 陈娱. 居民出行视角下的北京市双枢纽机场可达性研究[J]. 地球信息科学学报, 2022, 24(5): 914-924.
[3]	邵攀, 范红梅, 高梓昂. 基于自适应半监督模糊C均值的遥感变化检测[J]. 地球信息科学学报, 2022, 24(3): 508-521.
[4]	肖中圣, 许奇, 毛保华, 魏润斌, 冯佳. 不同测算方法下行程时间不确定性对可达性的影响分析[J]. 地球信息科学学报, 2022, 24(11): 2102-2114.
[5]	陈文静, 李锐, 董广胜, 李江. 网络地理信息服务中用户空间访问聚集行为研究[J]. 地球信息科学学报, 2021, 23(1): 93-103.
[6]	赵鹏军, 万婕. 城市交通与土地利用一体化模型的核心算法进展及技术创新[J]. 地球信息科学学报, 2020, 22(4): 792-804.
[7]	邬群勇, 张良盼, 吴祖飞. 顾及空间异质性的出租载客与公交客流回归分析[J]. 地球信息科学学报, 2019, 21(3): 337-345.
[8]	刘希亮, 陆锋. 适于城市交通时序空间数据预测的层叠泛化模型[J]. 地球信息科学学报, 2015, 17(12): 1474-1482.
[9]	刘康, 段滢滢, 陆锋. 基于拓扑与形态特征的城市道路交通状态空间自相关分析[J]. 地球信息科学学报, 2014, 16(3): 390-395.
[10]	陆锋, 段滢滢, 臧志刚. 短时交通预测的动态出行信息服务协同工作平台[J]. 地球信息科学学报, 2009, 11(5): 617-622.
[11]	吴锋, 战金艳, 邓祥征, 史娜娜. 生态系统服务功能动态区划方法与应用[J]. 地球信息科学学报, 2009, 11(4): 498-504.