城市出租车乘客出行特征可视化分析方法
|
摘要
可视化技术通过图形表现数据的内在规律,并可利用交互的形式实现数据的层次化展示,其在分析交通数据、发现交通问题以及辅助决策中扮演着越来越重要的角色。为了更加清晰、直观地展示城市出租车GPS轨迹数据传递的信息,解决因其数据量庞大和时空信息复杂而带来的分析难题,提出一种集成聚集可视化、特征可视化对出租车GPS轨迹数据进行可视化分析的方法。首先,通过数据处理得到可用于可视化的特征数据,而后对乘客上下车点进行聚集可视化,并利用多视图协同交互的方法对轨迹数据进行了特征可视化;最后,根据可视化结果对城市出租车乘客出行特征时空分布情况进行了分析。在此基础上,设计了一个交互式可视分析系统,并通过真实数据集案例验证了系统的有效性。
Visual analysis technology plays an increasingly important role in the analysis of traffic data, discovery of traffic problems and auxiliary decision-making through graphical and interactive forms of data. In order to show the information obtained from the GPS trajectory data clearly and intuitively, this paper presents an integrated clustering visualization and feature visualization method for the taxi GPS trajectory, aiming to solve the hard problem arising from the large data volume and complex spatial-temporal information. Firstly, the feature data used for visualization is extracted by data processing, then the visualization of the passenger pick-up point is carried out, and the trajectory data is visualized by the method of multi-view collaborative interaction. Finally, according to the visualization results, temporal and spatial distribution of the travel characteristics are analyzed. On this basis, an interactive visual analysis system is designed and the validity of the system is proved through case studies of real data sets.
Visual analysis technology plays an increasingly important role in the analysis of traffic data, discovery of traffic problems and auxiliary decision-making through graphical and interactive forms of data. In order to show the information obtained from the GPS trajectory data clearly and intuitively, this paper presents an integrated clustering visualization and feature visualization method for the taxi GPS trajectory, aiming to solve the hard problem arising from the large data volume and complex spatial-temporal information. Firstly, the feature data used for visualization is extracted by data processing, then the visualization of the passenger pick-up point is carried out, and the trajectory data is visualized by the method of multi-view collaborative interaction. Finally, according to the visualization results, temporal and spatial distribution of the travel characteristics are analyzed. On this basis, an interactive visual analysis system is designed and the validity of the system is proved through case studies of real data sets.
引文
[1]齐观德,潘纲,李石坚,等.当出租车轨迹挖掘遇见智能交通[J].中国计算机学会通讯,2013,9(8):30-37.
[2]高强,张凤荔,王瑞锦,等.轨迹大数据:数据处理关键技术研究综述[J/OL].软件学报,2017,28(4):959-992.http://www.jos.org.cn/1000-9825/5143.htm.
[3]任磊,杜一,马帅,等.大数据可视分析综述[J/OL].软件学报,2014,25(9):1909-1936.http://www.jos.org.cn/1000-9825/4645.htm.
[4]蒲剑苏,屈华民,倪明选.移动轨迹数据的可视化[J].计算机辅助设计与图形学学报,2012,24(10):1273-1282.
[5]Chen Wei,Guo Fangzhou,Wang Feiyue.A survey of traffic data visualization[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(6):2970-2984.
[6]Andrienko G,Andrienko N.Spatio-temporal aggregation for visual analysis of movements[C]//IEEE Symposium on Visual Analytics Science and Technology,2008:51-58.
[7]Guo Hanqi,Wang Zuchao,Yu Bowen,et al.TripVista:triple perspective visual trajectory analytics and its application on microscopic traffic data at a road intersection[C]//IEEE Pacific Visualization Symposium,2011:163-170.
[8]Ferreira N,Poco J,Vo H T,et al.Visual exploration of big spatio-tem-poral urban data:a study of new york city taxi trips[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(12):2149-2158.
[9]Wang Zuchao,Lu Min,Yuan Xiaoru,et al.Visual traffic jam analysis based on trajectory data[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(12):2159-2168.
[10]Al-Dohuki S,Kamw F,Zhao Y,et al.SemanticTraj:a new approach to interacting with massive taxi trajectories[J].IEEE Transactions on Visualization&Computer Graphics,2016,23(1):11-20.
[11]Sun Guodao,Liang Ronghua,Qu Huamin,et al.Embedding spatio-temporal information into maps by routezooming[J].IEEE Transactions on Visualization&Computer Graphics,2017,23(5):1506-1519.
[12]Kumar K M,Reddy A R M.A fast DB-SCAN clustering algorithm by accelerating neighbor searching using groups method[J].Pattern Recognition,2016,58:39-48.
[13]李宗林,罗可.DBSCAN算法中参数的自适应确定[J].计算机工程与应用,2016,52(3):70-73.
[14]段宗涛,陈志明,陈柘,等.基于Spark平台城市出租车乘客出行特征分析[J].计算机系统应用,2017,26(3):37-43.
[15]王祖超,袁晓如.轨迹数据可视分析研究[J].计算机辅助设计与图形学报,2015(1):9-25.
[16]吕之华.精通D3.js:交互式数据可视化高级编程[M].北京:电子工业出版社,2005:1-2.
[2]高强,张凤荔,王瑞锦,等.轨迹大数据:数据处理关键技术研究综述[J/OL].软件学报,2017,28(4):959-992.http://www.jos.org.cn/1000-9825/5143.htm.
[3]任磊,杜一,马帅,等.大数据可视分析综述[J/OL].软件学报,2014,25(9):1909-1936.http://www.jos.org.cn/1000-9825/4645.htm.
[4]蒲剑苏,屈华民,倪明选.移动轨迹数据的可视化[J].计算机辅助设计与图形学学报,2012,24(10):1273-1282.
[5]Chen Wei,Guo Fangzhou,Wang Feiyue.A survey of traffic data visualization[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(6):2970-2984.
[6]Andrienko G,Andrienko N.Spatio-temporal aggregation for visual analysis of movements[C]//IEEE Symposium on Visual Analytics Science and Technology,2008:51-58.
[7]Guo Hanqi,Wang Zuchao,Yu Bowen,et al.TripVista:triple perspective visual trajectory analytics and its application on microscopic traffic data at a road intersection[C]//IEEE Pacific Visualization Symposium,2011:163-170.
[8]Ferreira N,Poco J,Vo H T,et al.Visual exploration of big spatio-tem-poral urban data:a study of new york city taxi trips[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(12):2149-2158.
[9]Wang Zuchao,Lu Min,Yuan Xiaoru,et al.Visual traffic jam analysis based on trajectory data[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(12):2159-2168.
[10]Al-Dohuki S,Kamw F,Zhao Y,et al.SemanticTraj:a new approach to interacting with massive taxi trajectories[J].IEEE Transactions on Visualization&Computer Graphics,2016,23(1):11-20.
[11]Sun Guodao,Liang Ronghua,Qu Huamin,et al.Embedding spatio-temporal information into maps by routezooming[J].IEEE Transactions on Visualization&Computer Graphics,2017,23(5):1506-1519.
[12]Kumar K M,Reddy A R M.A fast DB-SCAN clustering algorithm by accelerating neighbor searching using groups method[J].Pattern Recognition,2016,58:39-48.
[13]李宗林,罗可.DBSCAN算法中参数的自适应确定[J].计算机工程与应用,2016,52(3):70-73.
[14]段宗涛,陈志明,陈柘,等.基于Spark平台城市出租车乘客出行特征分析[J].计算机系统应用,2017,26(3):37-43.
[15]王祖超,袁晓如.轨迹数据可视分析研究[J].计算机辅助设计与图形学报,2015(1):9-25.
[16]吕之华.精通D3.js:交互式数据可视化高级编程[M].北京:电子工业出版社,2005:1-2.