基于出租车GPS大数据的城市热点出行路段识别方法

交通运输系统工程与信息 ›› 2019, Vol. 19 ›› Issue (2): 238-246.

基于出租车GPS大数据的城市热点出行路段识别方法

曲昭伟，王鑫，宋现敏^*，夏英集，袁咪莉

吉林大学交通学院，长春 130022

收稿日期:2018-09-10 修回日期:2018-12-13 出版日期:2019-04-25 发布日期:2019-04-25
作者简介:曲昭伟(1962-)，男，吉林长春人，教授，博士.
基金资助:
国家自然科学基金/National Natural Science Foundation of China(51278220)；吉林省教育厅“十三五”科学技术项目/ Jilin Provincial Department of Education“13th Five-year”Science and Technology Project (JJKH20190153KJ).

Urban Hotspot Travel Section Identification Method Based on Taxi GPS Large Data

QU Zhao-wei, WANG Xin, SONG Xian-min, XIA Ying-ji, YUAN Mi-li

School of Transportation, Jilin University, Changchun 130022, China

Received:2018-09-10 Revised:2018-12-13 Online:2019-04-25 Published:2019-04-25

摘要/Abstract

摘要：

连续两个出租车 GPS定位点之间的时空间隔使得乘客上下车的位置必然介于一个线性区间内，据此提出轨迹线密度方法，用于在位置界限模糊的热点出行区域进一步搜索热点路段.利用成都市出租车 GPS数据，借助核密度估计分析出租车上下客位置的时空特性；基于轨迹线密度方法，计算了成都市春熙路商圈的路网密度值，划分路段热点强度，识别出了热点路段的位置，结合实际的出行需求分布完成方法有效性的验证.结果表明，本文所采用的方法能够有效识别出行需求旺盛的城市热点路段，不仅可以为出租车司机寻找客源提供重要的参考，还能够在交通相关部门选择出租车停靠站的位置时提供数据支持.

关键词: 城市交通, 轨迹线密度, 核密度分析, 城市热点路段, GPS大数据, 出租车停靠站

Abstract:

Due to the spatio- temporal interval between two consecutive taxi GPS points, the location where passengers get on or off the taxi is in a linear range. A method of trajectory density was proposed for further searching hotspots sections in the hotspots area where the hotspots location is fuzzy. Utilizing taxi GPS data of Chengdu, the spatio- temporal characteristics of the pick- up and drop- off location were analyzed by means of kernel density method; Based on the trajectory density method, the density of road network in Chunxi commercial district of Chengdu was calculated, the hotspots intensity of the section was divided, and the location of hotspots section was identified. The validity of the proposed method is verified by the actual travel demand distribution. The result shows that our method can effectively identify the hotspots sections where travel demand is strong. It can not only provide important reference for taxi drivers to find customers, but also give data support for traffic related departments to locate reasonable taxi stops.

Key words: urban traffic, trajectory density, kernel density estimation, urban hotspot section, GPS big data, taxi stands

中图分类号:

U491.1

曲昭伟，王鑫，宋现敏，夏英集，袁咪莉. 基于出租车GPS大数据的城市热点出行路段识别方法[J]. 交通运输系统工程与信息, 2019, 19(2): 238-246.

QU Zhao-wei, WANG Xin, SONG Xian-min, XIA Ying-ji, YUAN Mi-li. Urban Hotspot Travel Section Identification Method Based on Taxi GPS Large Data[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(2): 238-246.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19825.shtml

http://www.tseit.org.cn/CN/Y2019/V19/I2/238

参考文献

[1] ZHAO P X, QIN K, ZHOU Q, et al. Detecting hotspots from taxi trajectory data using spatial cluster analysis[J]. Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015(II-4/W2): 131-135.

[2] YU Z, ZHANG L Z, XIE X, et al. Mining interesting locations and travel sequences from GPS trajectories [C]// Quemada J，León G，Maarek Y，Nejdl W. Proceedings of the 18th international conference on World wide web. New York: ACM, 2009: 791-800.

[3] CHANG H W, TAI Y C, HSU Y. Context- aware taxi demand hotspots prediction[J]. International Journal of Business Intelligence & Data Mining, 2010, 5(1): 3-18.

[4] ELGAMMAL A, DURISWAMI R, HARWOOD D, et al. Background and foreground modelling using nonparametric kernel density estimation for visual surveil[J]. Proceedings of the IEEE, 2002, 90(7): 1151- 1163.

[5] XIE Z X, YAN J. Kernel density estimation of traffic accidents in a network space[J]. Computers Environment & Urban Systems, 2008, 32(5): 396-406.

[6] CAO X, CONG G, Jensen C S. Mining significant semantic locations from GPS data[J]. Proceedings of the VLDB Endowment, 2010, 3(1): 1009-1020.

[7] XU X L, DOU W C, ZHANG X Y, et al. A traffic hotline discovery method over cloud of things using big taxi GPS data[J]. Software Practice & Experience, 2017, 47 (3): 361-377.

[8] LEE J, SHIN I, PARK G L. Analysis of the passenger pick- up pattern for taxi location recommendation[C]// IEEE. 4th International Conference on Networked Computing and Advanced Information Management, LOS ALAMITOS: IEEE, 2008: 199-204.

[9] GUI Z M, YU H P. Mining traffic hot spots from massive taxi trace[J]. Journal of Computational Information Systems, 2014, 10(7): 2751-2760.

[10] ZOU H X, YUE Y, LI Q Q, et al. A spatial analysis approach for describing spatial pattern of urban traffic state[C]// IEEE. 13th International IEEE Conference on Intelligent Transportation Systems, Piscataway: IEEE , 2010: 557-562.

[11] WESTGATE B S, WOODARD D B, MATTESON D S, et al. Travel time estimation for ambulances using Bayesian data augmentation[J]. Annals of Applied Statistics, 2013, 7(2): 1139-1161.

[12] LI B, ZHANG D Q, SUN L, et al. Hunting or waiting? Discovering passenger- finding strategies from a largescale real- world taxi dataset[C]// IEEE. 2011 IEEE International Conference on Pervasive Computing and Communications Workshops, Piscataway: IEEE, 2011: 63-68.

[13] YUAN J, ZHENG Y, ZHANG L H, et al. Where to find my next passenger[C]// Landay J, SHI Yuan- chun, Patterson D，Rogers Y, XIE Xing. Proceedings of the 13th International Conference on Ubiquitous Computing, New York: ACM, 2011: 109-118.

[14] SHEATHER S J, JONES M C. A reliable data- based bandwidth selection method for kernel density estimation[J]. Journal of the Royal Statistical Society, 1991, 53(3): 683-690.

[15] BORRUSO G. Network density estimation: A GIS approach for analysing point patterns in a network space[J]. Transactions in Gis, 2008, 12(3): 377-402.

[16] ANDERSON T K. Kernel density estimation and Kmeans clustering to profile road accident hotspots[J]. Accident Analysis & Prevention, 2009, 41(3): 359-364.

[17] GB51038-2015. 城市道路交通标志和标线设置规范[S]. 北京：中国计划出版社，2015. [GB51038-2015. Specification for layout of urban road traffic signs and markings[S]. Beijing: China Planning Press, 2015.]