顾及路网与轨迹多模特征的道路等级分类研究

doi:10.12082/dqxxkx.2022.220218

地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (10): 1925-1940.doi: 10.12082/dqxxkx.2022.220218

顾及路网与轨迹多模特征的道路等级分类研究

张彩丽¹^,²(), 向隆刚¹^,^*(), 李雅丽¹, 林志勇³

1.武汉大学测绘遥感信息工程国家重点实验室,武汉 430079
2.邵阳学院城乡建设学院,邵阳 422000
3.武汉大学遥感信息工程学院,武汉 430079

收稿日期:2022-04-23 修回日期:2022-05-27 出版日期:2022-10-25 发布日期:2022-12-25
通讯作者: *向隆刚（1976— ）,男,湖南怀化人,博士,教授,主要从事轨迹数据分析、时空大数据管理。E-mail: geoxlg@whu.edu.cn
作者简介:张彩丽（1989—）,女,河南驻马店人,博士,主要从事轨迹数据分析与挖掘。E-mail: cailizhang@whu.edu.cn
基金资助:
国家自然科学基金项目(41771474);国家自然科学基金项目(42071432)

A Research on Road Type Classification Considering the Multi-mode Features of Road Network and Trajectories

ZHANG Caili¹^,²(), XIANG Longgang¹^,^*(), LI Yali¹, LIN Zhiyong³

1. State Key Lab of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
2. Urban and Rural Construction College, Shaoyang University, Shaoyang 422000, China
3. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Received:2022-04-23 Revised:2022-05-27 Online:2022-10-25 Published:2022-12-25
Contact: XIANG Longgang
Supported by:
National Natural Science Foundation of China(41771474);National Natural Science Foundation of China(42071432)

摘要/Abstract

摘要：

道路等级不仅反映在路网结构的静态骨架信息上,也蕴含在轨迹数据呈现的动态语义信息上。为解决(OpenStreetMap)OSM路网部分路段及路网生成产品等级缺失问题,本文提出一种顾及路网与轨迹多模特征的道路等级分类方法。首先通过轨迹数据的清洗、地图匹配和基于路名的路网合并实现轨迹点与命名道路的联结;然后以命名道路为分析单元,综合考虑路网及轨迹数据,在系统分析路网结构的道路几何特征、道路分布特征、道路拓扑特征及道路单双向信息基础上,进一步挖掘与融合轨迹数据蕴含的道路宽度、道路车流量、道路速度等静动态特征,形成关于道路等级的描述特征集,作为识别道路等级的基础与依据;最后以随机森林(RF)为基本分类器进行特征选择及模型训练实现道路等级识别。为验证本文方法,选取武汉市汉正街区域及二环区域,基于OSM路网数据及众源轨迹数据开展试验。该方法取得了较好的分类结果,小范围汉正街区域的验证集准确率为91.2%,大范围二环区域的验证集准确率达到80.8%。与单类特征相比,集成路网与轨迹特征极大提高了道路等级分类准确率;与原始路段形式进行道路等级分类相比,以路名重构道路形式进行道路等级分类效果更好。

关键词: 智能交通, 众源轨迹数据, 多模特征融合, 命名道路, 道路等级, OSM, 道路属性更新, 随机森林

Abstract:

Path planning and vehicle navigation not only rely on the basic road network structure, but also need information such as grades to assist, to achieve navigation services such as "road priority". Road type is not only reflected in the static skeleton information of the road network, but also in the dynamic semantic information presented by the trajectories. To identify the missing road type of the road sections in the existing road network such as OpenStreetMap (OSM) and road network generation products, a road type classification method considering multi-mode features of the road network and trajectories was proposed. First, the connection between trajectory points and named roads was realized through the cleaning of trajectory data, map matching, and the merging of OSM based on names. Then, a set of descriptive features of road type was formed as the basis for identifying road type by taking the named road as the analytical unit. Specifically, based on the systematic analysis of the road geometric features, road distribution features, road topological features, and one-way and two-way information of the road network structure, we further mined and integrated the static and dynamic features of trajectories, such as width, traffic volume, speed, and so on. Finally, a Random Forest (RF) model was used as the base classifier for feature selection and model training to identify road type. In order to verify our proposed method, we selected the OSM road network and crowd-sourced trajectories in the Hanzheng Street area and the second ring area of Wuhan to carry out the experiment. Our method achieved excellent classification results, the accuracy in verification set of the small area on Hanzheng Street reached 91.2%, and the accuracy in verification set of the larger area on the second ring reached 80.8%. Compared with single-class features, integrated road network and trajectory features greatly improved the accuracy of road type identification. Compared with the road type classification in the form of the original road section, the road type identification in the form of road name reconstruction was better. Compared with existing methods, e.g., commonly used K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), and other models, our proposed method achieved a higher accuracy. Feature rationality analysis also verified the effectiveness of the proposed method in this paper.

Key words: intelligent transportation, crowd-sourced trajectories, multi-modal feature fusion, named road, road type, OSM, road attribute update, random forest model

张彩丽, 向隆刚, 李雅丽, 林志勇. 顾及路网与轨迹多模特征的道路等级分类研究[J]. 地球信息科学学报, 2022, 24(10): 1925-1940.DOI:10.12082/dqxxkx.2022.220218

ZHANG Caili, XIANG Longgang, LI Yali, LIN Zhiyong. A Research on Road Type Classification Considering the Multi-mode Features of Road Network and Trajectories[J]. Journal of Geo-information Science, 2022, 24(10): 1925-1940.DOI:10.12082/dqxxkx.2022.220218

图/表 18

图1

图2

图3

图4

图5

表1

表2

图6

图7

表3

表4

图8

图9

图10

表5

表6

图11

表7

参考文献 29

[1]	Yu W H, Zhang Y F, Ai T H, et al. Road network generalization considering traffic flow patterns[J]. International Journal of Geographical Information Science, 2020, 34(1):119-149. DOI: 10.1080/13658816.2019.1650936 doi: 10.1080/13658816.2019.1650936
[2]	Goto A, Nakamura H. Functionally hierarchical road classification considering the area characteristics for the performance-oriented road planning[J]. Transportation Research Procedia, 2016, 15(1):732-748. DOI: 10.1016/j.trpr o.2016.06.061 doi: 10.1016/j.trpr o.2016.06.061
[3]	李辉, 朱苗苗, 韩志玲, 等. 面向功能的城市道路等级结构分析及资源配置[J]. 公路, 2020, 65(7):6.
	[ Li H, Zhu M M, Han Z L, et al. Research on hierarchy and resource allocation of urban road based on road function[J]. Highway, 2020, 65(7):6. ]
[4]	栾学晨, 杨必胜, 张云菲. 城市道路复杂网络结构化等级分析[J]. 武汉大学学报·信息科学版, 2012, 37(6):728-732.
	[ Luan X C, Yang B S, Zhang Y F. Structural hierarchy analysis of streets based on complex network theory[J]. Geomatics and Information Science of Wuhan University, 2012, 37(6):728-732. ] DOI: 10.13203/j.whugis201 2.06.024 doi: 10.13203/j.whugis201
[5]	Lyu H Y, Pfoser D, Sheng Y H. Movement-aware map construction[J], International Journal of Geographical Information Science, 2021, 35(6):1065-1093. DOI: 10.1080/13658816.2020.1863409 doi: 10.1080/13658816.2020.1863409
[6]	Arman M A, Tampère C M J. Lane-level routable digital map reconstruction for motorway networks using low-precision GPS data[J]. Transportation Research Part C: Emerging Technologies, 2021, 129(1):103234. DOI: 10.1 016/j.trc.2021.103234 doi: 10.1 016/j.trc.2021.103234
[7]	马超. 自发地理信息道路数据融合处理关键技术研究[D]. 郑州: 解放军信息工程大学, 2017.
	[ Ma C. Research on key technology of data fusion of volunteered information geographic road data[D]. Zhengzhou: Information Engineering University, 2017. ]
[8]	Li J, Qin Q M, Han J W, et al. Mining trajectory data and geotagged data in social media for road map inference[J]. Transactions in GIS, 2015, 19(1):1-18. DOI: 10.1111/tgis.1 2072 doi: 10.1111/tgis.1 2072
[9]	Van W K, Biljecki F, Stefan V D S. Automatic update of road attributes by mining GPS tracks[J]. Transactions in GIS, 2016, 20(5):664-683. DOI: 10.1111/tgis.12186 doi: 10.1111/tgis.12186
[10]	Ajmar A, Arco E, Boccardo P. Definition of a methodology to derive road network functional hierarchy classes using car tracking data[J]. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci, 2020, XLIII-B4-2020:307-312. DOI: 10.5194/isprs-archives-XLIII-B4-2020-307-2020 doi: 10.5194/isprs-archives-XLIII-B4-2020-307-2020
[11]	Jiang B. Street hierarchies: A minority of streets account for a majority of traffic flow[J]. International Journal of Geographical Information Science, 2009, 23(8):1033-1048. DOI: 10.1080/13658810802004648 doi: 10.1080/13658810802004648
[12]	Zhou C, Li W J, Jia H G. Road network generalization based on float car tracking[J]. Int. Arch. Photogram. Remote Sens. Spatial Inf. Sci, 2016, XLI-B4-2016:71-77. DOI: 10.5194/isprsarchives-XLI-B4-71-2016 doi: 10.5194/isprsarchives-XLI-B4-71-2016
[13]	邓敏, 陈雪莹, 唐建波, 等. 一种顾及道路交通流量语义信息的路网选取方法[J]. 武汉大学学报·信息科学版, 2020, 45(9):1438-1447.
	[ Deng M, Chen X Y, Tang J B, et al. A method for road network selection considering the traffic flow semantic information[J]. Geomatics and Information Science of Wuhan University, 2020, 45(9):1438-1447. ] DOI: 10.13203/j.whugis20180053 doi: 10.13203/j.whugis20180053
[14]	曹炜威, 张红, 何晶, 等. 顾及结构和几何特征的道路自动选取方法[J]. 武汉大学学报·信息科学版, 2017, 42(4):5.
	[ Cao W W, Zhang H, He J, et al. Road selection considering structural and geometric properties[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4):520-524. ] DOI: 10.13203/j.whugis20140862 doi: 10.13203/j.whugis20140862
[15]	韩远. 基于多属性决策层次分析法的道路选取方法[D]. 兰州: 兰州交通大学, 2020.
	[ Han Y. Road selection based on multi-attribute decision-making analytic hierarchy process[D]. Lanzhou: Lanzhou Jiao tong University, 2020. ]
[16]	胡云岗, 陈军, 李志林, 等. 基于网眼密度的道路选取方法[J]. 测绘学报, 2007, 36(3):111-117.
	[ Hu Y G, Chen J, Li Z L, et al. Selective omission of road features based on mesh density for digital map generalization[J]. Acta Geodaetica et CartographicaSinica, 2007, 36(3):111-117. ]
[17]	施树明, 于壮, 林楠, 等. 面向汽车运行工况数据采集的道路等级K核划分方法[J]. 中国公路学报, 2016, 29(11):171-178.
	[ Shi S M, Yu Z, Lin N, et al. Road hierarchy for vehicle driving cycle data collection based on k-core algorithm[J]. China Journal of Highway and Transport, 2016, 29(11):171-178. ] DOI: CNKI:SUN:ZGGL.0.2016-11-025 doi: CNKI:SUN:ZGGL.0.2016-11
[18]	Zhou Q, Li Z. Empirical determination of geometric parameters for selective omission in a road network[J]. International Journal of Geographical Information Science, 2016, 30(2),263-299. DOI: 10.1080/13658816.2015.1085 538 doi: 10.1080/13658816.2015.1085 538
[19]	袁林辉. 集成学习与多参数体系对OSM道路网自动选取的研究[D]. 南京: 南京大学, 2018.
	[ Yuan L H. Study on ensemble learning and multi-parameters system for OSM road network selection[D]. Nanjing: Nanjing University, 2018. ]
[20]	Zheng J, Gao Z, Ma J, et al. Deep graph convolutional networks for accurate automatic road network selection[J]. ISPRS International Journal of Geo-information. 2021, 10(11):768. DOI: 10.3390/ijgi10110768 doi: 10.3390/ijgi10110768
[21]	Zhou Q, Li Z. A comparative study of various supervised learning approaches to selective omission in a road network[J]. The Cartographic Journal, 2017, 54(3):254-264. DOI: 10.1179/1743277414Y.0000000083 doi: 10.1179/1743277414Y.0000000083
[22]	向隆刚, 邵晓天. 载体轨迹停留信息提取的核密度法及其可视化[J]. 测绘学报, 2016, 45(9):1122-1131.
	[ Xiang L G, Shao X T. Visualization and extraction of trajectory stops based on kernel-density[J]. Acta Geodaetica et CartographicaSinica, 2016, 45(9):1122-1131. ] DOI: 10.11947/j.AGCS.2016.20150347 doi: 10.11947/j.AGCS.2016.20150347
[23]	Newson P, Krumm J. Hidden markov map matching through noise and sparseness[C]. Proceedings of the 17th ACM SIG-SPATIAL International Conference on Advances in Geographic Information Systems, Washington, USA, 2009:336-343. DOI: 10.1145/1653771.1653818 doi: 10.1145/1653771.1653818
[24]	刘凯, 龚星星, 常四铁. 城市道路分级体系及相关因素研究[J]. 交通运输工程与信息学报, 2012, 10(4):7.
	[ Liu K, Gong X X, Chang S T. Study on urban road hierarchy and related factors[J]. Journal of Transportation Engineering and Information, 2012, 10(4):7. ] DOI: CNKI:SUN:JTGC.0.2012-04-015 doi: CNKI:SUN:JTGC.0.2012-04
[25]	唐炉亮, 杨雪, 靳晨, 等. 基于约束高斯混合模型的车道信息获取[J]. 武汉大学学报·信息科学版, 2017, 42(3):341-347.
	[ Tang L L, Yang X, Jin C, et al. Traffic lane number extraction based on the constrained gaussian mixture model[J]. Geomatics and Information Science of Wuhan University, 2017, 42(3):341-347. ] DOI: 10.13203/j.whugi s20140965 doi: 10.13203/j.whugi s20140965
[26]	Xu Y, Xie Z, Wu L, et al. Multilane roads extracted from the OpenStreetMap urban road network using random forests[J]. Transactions in GIS, 2019, 23(2):224-240. DOI: 1 0.1111/tgis.12514 doi: 1 0.1111/tgis.12514
[27]	OpenStreet Map. https://www.openstreetmap.org/.
[28]	城市综合交通体系规划标准(GB/T51328-2018)[S]. 2018.
	[ Standard for urban comprehensive transport system planning (GB/T51328-2018)[S]. 2018. ]
[29]	何云, 黄翀, 李贺, 等. 基于Sentinel-2A影像特征优选的随机森林土地覆盖分类[J]. 资源科学, 2019, 41(5):170-179.
	[ He Y, Huang C, Li H, et al. Land-cover classification of random forest based on Sentinel-2A image feature optimization[J]. Resources Science, 2019, 41(5):992-1001. ] DOI: 10.18402/resci.2019.05.15 doi: 10.18402/resci.2019.05.15

实验区域	OSM路网		轨迹数据
实验区域	原始路段数/条	重建样本数/条	轨迹点数/个	平均采样频率/s	面积/km²
汉正街数据集	1438	520	568 906	29.31	4.2×2.8
二环区数据集	14 340	5187	15 946 541	30.26	14.8×14.3

等级ID	新划分等级	释义	OSM 对应原始等级
0	fast	城市环线,无红绿灯,立体交叉	motorway, trunk
1	fast_link	高架与地面的连接路	motorway_link, trunk_link
2	primary	城市主要行车道路	primary
3	primary_link	一般为左转、右转、提前掉头专用道	primary_link
4	secondary	连接主干路,兼有服务功能	secondary
5	branch	连接小区路、次干路,以服务功能为主	tertiary, secondary_link, tertiary_link
6	service	园区内部能够驾车的道路	service, residential, living_street, unclassified

等级ID	等级类别	汉正街			二环区
等级ID	等级类别	精确率	召回率	F1值	精确率	召回率	F1值
0	fast	80.6	100.0	89.3	65.4	59.7	62.4
1	fast_link	100.0	100.0	100.0	77.7	87.2	82.2
2	primary	100.0	67.5	80.6	61.0	67.5	64.1
3	primary_link	100.0	75.0	85.7	64.8	74.7	69.4
4	secondary	50.2	80.0	61.7	49.3	42.6	45.7
5	branch	63.9	71.2	67.4	54.8	63.2	58.7
6	service	98.1	95.1	96.6	94.8	89.6	92.1
总体准确率		91.2			80.8

类别	原始路段		路名重构道路
类别	汉正街	二环区	汉正街/	二环区
OSMF	83.7	69.5	90.4	77.0
TRIF	64.7	58.0	79.1	64.3
OSMF+TRIF	84.8	75.1	91.2	80.8

模型	方法	原始路段		路名重构道路
模型	方法	汉正街/%	二环区/%	汉正街/%	二环区/%
RF	本文方法	84.8	75.1	91.2	80.8
SVM	文献[8]方法	68.4	56.4	76.9	60.1
KNN	OSMF	80.8	62.2	86.7	73.5
	TRIF	60.7	48.6	76.1	49.5
	OSMF+TRIF	81.7	68.6	89.9	75.4
SVM	OSMF	79.7	64.2	86.2	69.9
	TRIF	66.4	56.3	76.2	60.4
	OSMF+TRIF	83.4	70.4	88.0	74.4
GNB	OSMF	54.7	54.4	63.5	60.4
	TRIF	51.6	57.0	57.1	42.3
	OSMF+TRIF	58.5	61.7	74.4	66.9

顾及路网与轨迹多模特征的道路等级分类研究

A Research on Road Type Classification Considering the Multi-mode Features of Road Network and Trajectories

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 29

相关文章 15

Metrics

本文评价

推荐阅读 0

特征类别	汉正街/%	二环区/%
拓扑特征	79.1	70.4
拓扑特征+几何特征	81.7	78.0
拓扑特征+分布特征	86.0	79.6
拓扑特征+单双向	90.4	77.0
拓扑特征+宽度	92.6	78.3
拓扑特征+流量	91.5	80.0
拓扑特征+速度	91.2	80.8

特征来源	特征类别	指标	含义
路网数据	道路几何特征	Ldis	道路几何长度
	道路几何特征	RC	道路弯曲度
	道路分布特征	NArea	道路邻接网眼面积
		pdens	道路上n个节点密度平均值
		ldens	道路上n-1个路段线密度平均值
	道路拓扑特征	LLCE、LLCD、LLCC、LLCB、LLPG	从道路自身方面度量的节点群聚系数、度中心性、接近中心性、中介中心度、特征向量中心性
		PCE、PCD、PCC、PCB、PPG	从组成对象node方面度量的节点群聚系数、度中心性、接近中心性、中介中心度、特征向量中心性
		LCE、LCD、LCC、LCB、LPG	从组成对象link方面度量的节点群聚系数、度中心性、接近中心性、中介中心度、特征向量中心性
轨迹数据	道路流量特征	trinum	道路所匹配的轨迹条数
		triTnum	一条道路转向其他道路,或其他道路转向该道路的进出流量
		triSnum	道路组成的路段单元间通过流量
	道路单双向特征	oneway	道路的单双向信息
	道路宽度特征	W	道路匹配轨迹点到道路中心线距离的最大值与最小值之差
		meanw0、modew0、stdw0、medianw0	道路匹配轨迹点到道路中心线距离绝对值的平均值、众数、标准差、中位数
		w5-w95	道路匹配轨迹点到道路中心线距离绝对值的5~90百分位
	道路速度特征	means0、modes0、stds0、medians0	道路匹配轨迹点速度的平均值、众数、标准差、中位数
	道路速度特征	s5-s95	道路匹配轨迹点速度的5~90百分位

[1]	李玉洁, 江洪, 刘宣广. 基于CatBoost的植被总初级生产力遥感模拟方法及在福建省的应用[J]. 地球信息科学学报, 2023, 25(9): 1908-1922.
[2]	曹煜, 方秀琴, 杨露露, 蒋心远, 廖美玉, 任立良. 基于随机森林的西辽河流域CCI土壤湿度降尺度研究[J]. 地球信息科学学报, 2023, 25(8): 1669-1681.
[3]	林炫歆, 肖桂荣, 周侯伯. 顾及土地利用动态变化的滑坡易发性评估方法[J]. 地球信息科学学报, 2023, 25(5): 953-966.
[4]	秦肖伟, 程博, 杨志平, 李林, 董文, 张新, 杨树文, 靳宗义, 薛庆. 基于时序遥感影像的西南山区地块尺度作物类型识别[J]. 地球信息科学学报, 2023, 25(3): 654-668.
[5]	黄帅元, 董有福, 李海鹏. 黄土高原区SRTM1 DEM高程误差校正模型构建及对比分析[J]. 地球信息科学学报, 2023, 25(3): 669-681.
[6]	陈欣, 向隆刚, 焦凤伟. 基于众源轨迹的OSM路网转向信息增强[J]. 地球信息科学学报, 2023, 25(10): 1954-1967.
[7]	杜树坤, 张晶, 韩志军, 公茂玉. 基于随机森林模型的“网格-月”尺度武装冲突风险预测及影响因素分析——以中南半岛为例[J]. 地球信息科学学报, 2023, 25(10): 2026-2038.
[8]	潘雨飘, 赵翔, 王静, 张亦清, 刘耀林. 基于SMOTE-RF算法的村庄发展类型识别方法研究[J]. 地球信息科学学报, 2023, 25(1): 163-176.
[9]	杨洋, 邵哲平, 赵强, 潘家财, 胡雨, 梅强. 基于厦门港的海上交通事故地理空间分布及风险预测研究[J]. 地球信息科学学报, 2022, 24(9): 1676-1687.
[10]	吴亚楠, 郭长恩, 于东平, 段爱民, 刘玉, 董士伟, 单东方, 吴耐明, 李西灿. 基于不确定性分析的遥感分类空间分层及评估方法[J]. 地球信息科学学报, 2022, 24(9): 1803-1816.
[11]	聂祥琴, 陈瀚阅, 牛铮, 张黎明, 刘炜, 邢世和, 范协裕, 李家国. 基于时序影像的农业活动因子提取与闽西耕地SOC数字制图[J]. 地球信息科学学报, 2022, 24(9): 1835-1852.
[12]	高位, 涂伟, 李明晓, 方碧宸, 陈栋胜, 黄正东, 贺彪. 基于影响因子动态更新的都市圈国土-人口协同模拟[J]. 地球信息科学学报, 2022, 24(8): 1502-1511.
[13]	唐璐, 许捍卫, 丁彦文. 融合多源地理大数据的城市街区综合活力评价[J]. 地球信息科学学报, 2022, 24(8): 1575-1588.
[14]	裴泽华, 葛淼, 李浩, 何进伟, 王聪霞. 基于随机森林模型的中国中老年人群HDL-C环境影响因素研究[J]. 地球信息科学学报, 2022, 24(7): 1286-1300.
[15]	郭逸飞, 吴田军, 骆剑承, 石含宁, 郜丽静. 基于不确定性迭代优化的山地植被遥感制图[J]. 地球信息科学学报, 2022, 24(7): 1406-1419.