基于轨迹数据的道路客运班车停留站点位置提取方法

李军; 解超; 王林; 高中灵

doi:10.3963/j.jssn.1674-4861.2021.04.008

基于轨迹数据的道路客运班车停留站点位置提取方法

doi: 10.3963/j.jssn.1674-4861.2021.04.008

李军^{1, 2,},
解超¹,
王林^1, ,,
高中灵¹

1.
中国交通通信信息中心北京 100011
2.
北京交通大学交通运输学院北京 100044

基金项目:

国家自然科学基金项目 41971355

详细信息

作者简介:
李军(1979—), 博士, 高级工程师.研究方向: 综合交通运输理论与技术.E-mail: leejun@cttic.cn

通讯作者:
王林(1980—), 博士, 正高级工程师.研究方向: 交通时空大数据获取、分析与应用.E-mail: wanglin@cttic.cn

中图分类号: U495
计量
- 文章访问数: 484
- HTML全文浏览量: 298
- PDF下载量: 16
- 被引次数: 0
出版历程
- 收稿日期: 2020-07-30

A Method for Extracting Regular Bus Parking Stops of Road Passenger Transport Based on Trajectory Data

LI Jun^{1, 2
,},
JIE Chao¹,
WANG Lin^{1
, ,},
GAO Zhongling¹

1.
China Transport Telecommunications & Information Center, Beijing 100011, China
2.
School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China

摘要

摘要: 识别并提取道路客运班车停留站点的位置, 可为道路客运的客运站站址优化、定制出行乘降站点设置、出行信息服务等提供依据和支持, 然而当前获取班车停留站点位置的方法存在成本高、周期长的问题。通过分析道路客运班车停留轨迹数据的典型特征, 以班车轨迹数据为数据源, 基于DBSCAN算法检测位于停留站点的点簇进而提取停留站点位置。同时, 针对DBSCAN算法具有高时间复杂度的问题, 通过建立格网索引对算法进行了改进。基于京津冀区域的136条道路客运班线的班车轨迹数据进行了实证分析, 结果表明: 改进DBSCAN算法提高了算法执行效率, 平均执行时间减少了59.72%, 且所生成的班车停留站点数量与传统算法基本一致; 在提取得到的282个班车停留站点中, 256个为真实的班车停留站点, 班车停留站点提取的正确率为90.78%。
- 道路客运 /
- 停留站点提取 /
- 轨迹数据 /
- DBSCAN算法 /
- 班车
Abstract: It is of great significance to identify and extract the locations of the parking stops of regular buses of road passenger transport, providing support for optimizing the station location, setting the stops for customized travel, and the travel information service in road passenger transport. However, the current methods to obtain the location of parking stops of regular buses have problems of high cost and long cycle. The DBSCAN algorithm is used to detect point clusters located within parking stops and extract the parking stop location of regular buses by analyzing the typical characteristics of the track data of parking stops and taking those as the data source. Meanwhile, the DBSCAN algorithm is improved by establishing a special spatial grid index to decrease time complexity. Based on the track data of 136 regular routes of passenger service in the Beijing-Tianjin-Hebei region, this paper makes an empirical analysis.The results show that the improved DBSCAN algorithm can improve the execution efficiency, with the average execution time reduced by 59.72%. The number of parking stops is consistent with those generated by the traditional algorithm. Among the 282 regular bus parking stops extracted, 256 are real regular bus-parking stops with an accuracy rate of parking stops extraction of 90.78%.
- road passenger transportation /
- extraction of parking stops /
- trajectory data /
- DBSCAN algorithm /
- regular buses

HTML全文

图 1 班车轨迹点的空间分布

Figure 1. Spatial distribution of regular bus trajectories

下载: 全尺寸图片幻灯片

图 2 车辆定位误差

注：根据《汽车、挂车及汽车列车外廓尺寸、轴荷及质量限值》的规定，车辆高度限制为4 m，宽度限制为2.55 m，故取2.55 m为车辆宽度

Figure 2. Position error of vehicles

下载: 全尺寸图片幻灯片

图 3 轨迹数据漂移特征

Figure 3. Drift characteristic of trajectory data

下载: 全尺寸图片幻灯片

图 4 漂移数据处理方法

Figure 4. Processing method of drift data

下载: 全尺寸图片幻灯片

图 5 空间格网索引

Figure 5. Spatial grid index

下载: 全尺寸图片幻灯片

图 6 京津冀区域在线班车1 h的轨迹数据分布

Figure 6. Distribution of one-hour online regular bus trajectories in the Beijing-Tianjin-Hebei region

下载: 全尺寸图片幻灯片

图 7 班车停留站点提取过程

Figure 7. Extraction process of regular bus-parking stops

下载: 全尺寸图片幻灯片

图 8 改进算法的效率分析

Figure 8. Efficiency analysis of the improved algorithm

下载: 全尺寸图片幻灯片

图 9 班车停留站点与卫星影像图的匹配效果

Figure 9. Superimposed effect of regular bus parking stops in satellite images

下载: 全尺寸图片幻灯片

表 1 班车轨迹数据示例

Table 1. Samples of regular bus trajectories

车牌号码	定位时间	经度/(°)	纬度/(°)	速度/(km/h)	方向/(°)
京AD6***	2018-05-02 T09:30:09	112.280 17	29.221 87	60	156
津A67***	2018-05-10 T12:01:15	102.181 93	38.117 19	70	80
冀A59***	2018-05-09 T17:30:11	101.171 83	39.119 23	65	197

下载: 导出CSV

参考文献(19)

[1]	LI Jun, LI Qingqi, ZHU Yan, et al. An automatic extraction method of coach operation information from historical trajectory data[J]. Journalof Advanced Transportation, 2019(1): 1-15. http://downloads.hindawi.com/journals/jat/2019/3634942.pdf
[2]	YIN Ping, MU Lan. Modular capacitated maximal covering location problem for the optimal siting of emergency vehicles[J]. Applied Geography, 2012(34): 247-254. http://www.onacademic.com/detail/journal_1000035350179110_4cf5.html
[3]	刘旭, 陈云波, 施昆, 等. 结合Canopy-k-means算法和出租车轨迹数据的公交车站预测方法[J]. 测绘通报, 2018(11): 63-68. https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201811013.htm LIU Xu, CHEN Yunbo, SHI Kun, et al. Bus stations prediction based on Canopy-k-means from taxi GPS data[J]. Bulletin of Surveying and Mapping, 2018(11): 63-68. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB201811013.htm
[4]	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. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201911002.htm WU Huayi, HUANG Rui, YOU Lan, et al. Recent progress in taxi trajectory data mining[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(11): 1341-1356. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201911002.htm
[5]	林鹏飞, 翁剑成, 尹宝才, 等. 基于网约车轨迹数据的城市路网宏观运行质量评价方法[J]. 交通信息与安全, 2019, 37(6): 70-78. https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201906010.htm LIN Pengfei, WENG Jiancheng, YIN Baocai, et al. An evaluation method of macroscopic operation quality of urban road network based on data of online car-hailing trajectory[J]. Journal of Transport Information and Safety, 2019, 37(6): 70-78. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201906010.htm
[6]	TANG Kun, CHEN Shuyan, LIU Zhiyuan. Citywide spatial-temporal travel time estimation using big and sparse trajectories[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(12): 4023-4034. doi: 10.1109/TITS.2018.2803085
[7]	RONG Huigui, WANG Zepeng, ZHENG Hui, et al. Mining efficient taxi operation strategies from large scale geo-location data[J]. IEEE Acess, 2017(5): 25623-25634. http://www.onacademic.com/detail/journal_1000039994589110_746b.html
[8]	付鑫, 孙茂棚, 孙皓. 基于GPS数据的出租车通勤识别及时空特征分析[J]. 中国公路学报, 2017, 30(7): 134-143. doi: 10.3969/j.issn.1001-7372.2017.07.017 FU Xin, SUN Maopeng, SUN Hao. Taxi commute recognition and temporal-spatial characteristics analysis based on GPS data[J]. China Journal of Highway and Transport, 2017, 30(7): 134-143. (in Chinese) doi: 10.3969/j.issn.1001-7372.2017.07.017
[9]	唐炉亮, 郑文斌, 王志强, 等. 城市出租车上下客的GPS轨迹时空分布探测方法[J]. 地球信息科学学报, 2015, 17(10): 1179-1186. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201510007.htm TANG Luliang, ZHENG Wenbing, WANG Zhiqiang, et al. Space time analysis on the pick-up and drop-off of taxi passengers based on GPS big data[J]. Journal of Geo-information Science, 2015, 17(10): 1179-1186. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX201510007.htm
[10]	GUI Z, YU H. Mining traffic hot spots from massive taxi trace[J]. Journal of Computational Information Systems, 2014, 10(7): 2751-2760.
[11]	QU Zhaowei, WANG Xin, SONG Xianmin, et al. Location optimization for urban taxi stands based on taxi GPS trajectory big data[J]. IEEE Access, 2019(7): 62273-62283. http://ieeexplore.ieee.org/document/8713568/
[12]	ZHANG Desheng, HE Tian, LIN Shan, et al. Taxi-passengerdemand modeling based on big data from a roving sensor network[J]. IEEE Transactions on Big Data, 2017(3): 362-374. http://ieeexplore.ieee.org/document/7740911/
[13]	孙超, 张红军, 陈小鸿. 基于多源浮动车数据融合的道路交通运行评估[J]. 同济大学学报(自然科学版), 2018, 46(1): 46-52. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201801008.htm SUN Chao, ZHANG Hongjun, CHEN Xiaohong. Road traffic operation assessment based on multi-source floating car data fusion[J]. Journal of Tongji University(Natural Science Edition), 2018, 46(1): 46-52. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201801008.htm
[14]	CORTÉS CE, CIBSOM J CSCHWENDER A, et al. Commercial bus speed diagnosis based on GPS-monitored data[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(4): 695-707. doi: 10.1016/j.trc.2010.12.008
[15]	李军, 秦其明, 游林, 等. 利用浮动车数据提取停车场位置[J]. 武汉大学学报(信息科学版), 2013, 38(5): 599-603. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201305021.htm LI Jun, QIN Qiming, YOU Lin, et al. Parking lot extraction method based on floating car data[J]. Geomatics and Information Science of Wuhan University, 2013, 38(5): 599-603. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201305021.htm
[16]	JIANG Zhoutong, CHEN Xiqun, OUYANG Yanfeng. Traffic state and emission estimation for urban expressways based on heterogeneous data[J]. Transportation Research Part D: Transport and Environment, 2017(53): 440-453. http://oldmypage.zju.edu.cn/fck_filebrowser.php?cmd=download&id=704300
[17]	DRAIJER G, KALFS N, RERDOK J. Global positioning system as data collection method for travel research[J]. Transportation Research Record Journal of the Transportation Research Board, 2000(1): 147-153.
[18]	TANG Jinjun, LIU Fang, WANG Yinhai, et al. Uncovering urban human mobility from large scale taxi GPS data[J]. Physica A: Statistical Mechanics and its Applications, 2015, 438(11): 140-153. http://www.onacademic.com/detail/journal_1000038125306910_25e3.html
[19]	LI Jun, QIN Qiming, XIE Chao, et al. Integrated use of spatial and semantic relationships for extracting road networks from floating car data[J]. International Journal of Applied Earth Observation and Geoinformation, 2012(19): 238-247. http://www.onacademic.com/detail/journal_1000035625390410_e097.html