地理科学进展 ›› 2014, Vol. 33 ›› Issue (7): 938-948.doi: 10.11820/dlkxjz.2014.07.009

• • 上一篇    下一篇

人类活动轨迹的分类、模式和应用研究综述

李婷1,2(), 裴韬1, 袁烨城1(), 宋辞1, 王维一1,2, 杨格格1,2   

  1. 1. 中国科学院地理科学与资源研究所 资源与环境信息系统国家重点实验室,北京,100101
    2. 中国科学院大学,北京,100049
  • 出版日期:2014-07-25 发布日期:2014-07-25
  • 作者简介:

    作者简介:李婷(1990-),女,新疆乌鲁木齐人,硕士研究生,主要研究方向为时空数据挖掘,E-mail:lit@lreis.ac.cn

  • 基金资助:
    国家自然科学基金项目(41171345,41231171);国家863计划项目(2012AA12A403)

A review on the classification, patterns and applied research of human mobility trajectory

Ting LI1,2(), Tao PEI1, Yecheng YUAN1(), Ci SONG1, Weiyi WANG1,2, Gege YANG1,2   

  1. 1. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Online:2014-07-25 Published:2014-07-25

摘要:

各种传感器的应用与发展,如车载GPS、手机、公交卡、银行卡等,记录了人类的活动轨迹。这些海量的人类活动轨迹数据中蕴含着人类行为的时空分布模式。通过对这些轨迹的研究可以挖掘个体轨迹模式,理解人类动力学特征,进而为对轨迹预测、城市规划、交通监测等提供支持。因此,研究各类传感器记录的人类活动轨迹数据成为当前的研究热点。本文对人类活动轨迹的获取与表达方式进行剖析,并将人类的活动轨迹按照采样方式和驱动因素的不同分为基于时间间隔采样、基于位置采样和基于事件触发采样等3类轨迹数据。由于各类轨迹数据均由起始点、锚点和一般节点等构成,因而将轨迹模式挖掘的研究按照锚点、出行范围、形状模式、OD流模式、时间模式等进行组织,研究成果揭示人类活动轨迹在时间、空间的从聚模式、周期性等特点。在此基础上,将人类活动轨迹在城市研究中的应用,按照用户轨迹预测、城市动态景观、城市交通模拟与监控、城市功能单元识别以及城市中其他方面的研究应用进行系统综述,认为人类活动模式挖掘是城市规划、城市交通、公共安全等方面应用的基础。

关键词: 轨迹特征, 活动模式, 轨迹数据

Abstract:

Various sensors such as GPS units, mobile phones, public transportation passes, and bank cards record the trajectory of human activities. These massive trajectory data contain distribution pattern of human behavior in space and time. The study of trajectory data can reveal individual trajectory patterns, facilitate the understanding of characteristics of human dynamics, and thus support trajectory prediction, urban planning, traffic monitoring and the like. Therefore the study of trajectory data recorded by various sensors has become a focus of research at present. In this paper, we analyze the acquisition and expression of human activity trajectory. The trajectory of human activities can be classified into three broad categories according to the sampling methods and driving factors-through interval sampling, position sampling and event trigger sampling. The trajectory data are composed of origin points, destination points, anchor points and general nodes. The study of trajectory patterns is organized in accordance with anchor points, travel range, shape, origin-destination (OD) flow pattern, and temporal pattern. The results can reflect periodicity and clustering patterns of activities in space and time. On this basis, we summarize the application of human activity trajectory in urban studies from five aspects, including trajectory prediction, dynamic urban landscape delineation, urban traffic simulation and monitoring, urban functional unit identification, and other urban applications. We argue that exploring human activity patterns provides the basis for other studies in urban planning, urban traffic, public security, and so on.

Key words: trajectory characteristics, activity pattern, trajectory data

中图分类号: 

  • P237