吉林大学学报(工学版) ›› 2023, Vol. 53 ›› Issue (4): 1040-1046.doi: 10.13229/j.cnki.jdxbgxb.20221426

• 交通运输工程·土木工程 • 上一篇    

基于共享单车骑行轨迹的骑行质量识别方法

胡莹1,2(),邵春福1,王书灵2,蒋熙3,孙海瑞4   

  1. 1.北京交通大学 综合交通运输大数据应用技术交通运输行业重点实验室,北京 100044
    2.北京交通发展研究院,北京 100073
    3.北京交通大学 交通运输学院,北京 100044
    4.北京交研都市交通科技有限公司,北京 100044
  • 收稿日期:2022-11-10 出版日期:2023-04-01 发布日期:2023-04-20
  • 作者简介:胡莹(1988-),女,高级工程师,博士研究生.研究方向:交通运输规划和管理,绿色交通,步行和非机动车交通.E-mail: huying@bjtrc.org.cn
  • 基金资助:
    国家自然科学基金项目(52072025);国家自然科学基金创新研究群体项目(71621001)

Identification of road riding quality based on shared bike trajectory data

Ying HU1,2(),Chun-fu SHAO1,Shu-ling WANG2,Xi JIANG3,Hai-rui SUN4   

  1. 1.Key Laboratory of Integrated Transportation Big Data Application Technology for Transportation Industry,Beijing Jiaotong University,Beijing 100044,China
    2.Beijing Transport Institute,Beijing 100073,China
    3.School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China
    4.Beijing Best Transport Tech Co. ,Ltd. ,Beijing 100044,China
  • Received:2022-11-10 Online:2023-04-01 Published:2023-04-20

摘要:

基于共享单车骑行轨迹数据,提出了路网匹配以及骑行质量快速识别的方法。首先,以隐马尔科夫模型(HMM)的匹配算法为基础,提出了改进的骑行轨迹数据匹配方法。然后,基于密度聚类算法识别轨迹停驻点集,利用停驻点集的特征以及定位数据规律实现了关键参数的计算,给出了轨迹数据路网匹配的算法流程。最后,利用匹配后的轨迹数据,提出了基于离群检验的路段骑行质量快速识别方法。以北京市某区域为对象进行了案例分析,并通过沉浸式骑行体验和骑行环境调查相结合方式,验证了本文方法的准确性为87.7%。

关键词: 交通运输规划与管理, 共享单车, 轨迹数据, 路网匹配, 骑行质量, 离群检验

Abstract:

Aiming at the challenges of trajectory data processing and application brought about by the large error of shared bike riding positioning data and the complexity of bicycle riding behavior, the method of data preprocessing, road network matching and rapid identification of road riding quality is studied. Based on the Hidden Markov Model (HMM), an improved shared bike riding trajectory data matching method is proposed. Based on the density clustering algorithm, the identification of the parking point set of the trajectory is realized, the characteristics of the parking point set and the regularity of the positioning data are used to realize the calculation of the key parameters in line with the noise characteristics of shared bikes, and the optimal matching algorithm flow between bicycle trajectory data and road network is given. Using the matched trajectory data, a rapid identification method of bicycle traffic riding quality based on outlier test is proposed, and a case analysis is carried out in a certain area of Beijing. The accuracy of the method was verified by this method to be 87.7%.

Key words: transportation planning and management, share bike, trajectory data, road network matching, riding quality, outlier test

中图分类号: 

  • U491.2

图1

共享单车部分骑行轨迹点地图显示"

图2

共享单车骑行轨迹线地图显示"

图3

轨迹点匹配实际路段示意图"

图4

轨迹点路网匹配的篱笆网络有向图"

图5

骑行过程中的团状无序轨迹点集"

图6

某一停驻点集中各轨迹点"

图7

行程速度畅达率直方图"

图8

空间顺畅度直方图"

图9

模型识别异常路段地图显示"

1 王楠, 王勇峰, 刘积仁. 一个基于位置点匹配的地图匹配算法[J]. 东北大学学报: 自然科学版, 1999, 44(4): 344-347.
Wang Nan, Wang Yong-feng, Liu Ji-ren. A point-based map-matching algorithm[J]. Journal of Northeastern University (Natural Science), 1999, 44(4): 344-347.
2 Mohammed A Q, Washington Y O, Zhao L, et al. A general map matching algorithm for transport telematics applications[J]. GPS Solutions, 2003, 7(3): 157-167.
3 Nagendra R V, Mohammed A Q, Abigail L B. Developing an enhanced weight-based topological map-matching algorithm for intelligent transport systems[J]. Transportation Research Part C: Emerging Technologies, 2009, 17(6): 672-683.
4 Yang H Q, Cheng S W, Jiang H F, et al. An enhanced weight-based topological map matching algorithm for intricate urban road network[J]. Procedia-Social and Behavioral Sciences, 2013, 96: 1670-1678.
5 Li Liang, Mohammed Q, Zhao L. High accuracy tightly-coupled integrity monitoring algorithm for map-matching[J]. Transportation Research Part C: Emerging Technologies, 2013, 36: 13-26.
6 Newson P, Krumm J. Hidden Markov map matching through noise and sparseness[C]∥International Conference on Advances in Geographic Information Systems, New York, United States, 2009: 336-343.
7 Raymond R, Morimura T, Osogami T, et al. Map matching with hidden Markov model on sampled road network[C]∥Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan, 2012: 2242-2245.
8 刘旻, 李梅, 徐晓宇, 等. 一种基于HMM模型改进的地图匹配算法[J]. 北京大学学报: 自然科学版, 2018, 54(6): 1235-1241.
Liu Min, Li Mei, Xu Xiao-yu, et al. An improved map matching algorithm based on HMM model[J]. Acta Scientiarum Naturalium Universitatis Pekinensis,2018, 54(6): 1235-1241.
9 吴刚, 邱煜晶, 王国仁. 基于隐马尔可夫模型和遗传算法的地图匹配算法[J]. 东北大学学报: 自然科学版, 2017, 38(4): 472-475.
Wu Gang, Qiu Yu-jing, Wang Guo-ren. Map Matching algorithm based on hidden markov model and genetic algorithm[J]. Journal of Northeastern University(Natural Science), 2017, 38(4): 472-475.
10 Enns R, Morrell D. Terrain-aided navigation using the viterbi algorithm[J]. Journal of Guidance, Control, and Dynamics, 1995, 18(6): 1444-1449.
11 Zelenkov A V. Calculation of the parameters of hidden Markov models used in the navigation systems of surface transportation for map matching: a review[J]. Automatic Control and Computer Sciences, 2010, 44(6): 309-323.
[1] 王占中,蒋婷,张景海. 基于模糊双边界网络模型的道路运输效率评价[J]. 吉林大学学报(工学版), 2023, 53(2): 385-395.
[2] 闫云娟,查伟雄,石俊刚,李剑. 具有随机充电需求的混合动态网络平衡模型[J]. 吉林大学学报(工学版), 2022, 52(1): 136-143.
[3] 李浩,陈浩. 考虑充电排队时间的电动汽车混合交通路网均衡[J]. 吉林大学学报(工学版), 2021, 51(5): 1684-1691.
[4] 户佐安,夏一鸣,蔡佳,薛锋. 延误条件下综合多种策略的城轨列车运行调整优化[J]. 吉林大学学报(工学版), 2021, 51(5): 1664-1672.
[5] 朱才华,孙晓黎,李岩. 站点分类下的城市公共自行车交通需求预测[J]. 吉林大学学报(工学版), 2021, 51(2): 531-540.
[6] 罗清玉,田万利,贾洪飞. 考虑通勤需求的电动汽车充电站选址与定容模型[J]. 吉林大学学报(工学版), 2019, 49(5): 1471-1477.
[7] 常山,宋瑞,何世伟,黎浩东,殷玮川. 共享单车故障车辆回收模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1677-1684.
[8] 曹骞, 李君, 刘宇, 曲大为. 基于马尔科夫链的长春市乘用车行驶工况构建[J]. 吉林大学学报(工学版), 2018, 48(5): 1366-1373.
[9] 孙宝凤, 高坤, 申琇秀, 梁婷. 基于能力平衡和变覆盖半径的加油站网络扩充选址模型[J]. 吉林大学学报(工学版), 2018, 48(3): 704-711.
[10] 徐亮,程国柱. 基于车速离散度和经济车速的高速公路最低车速限制[J]. 吉林大学学报(工学版), 2010, 40(03): 661-0665.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!