地理科学进展 ›› 2016, Vol. 35 ›› Issue (5): 580-588.doi: 10.18306/dlkxjz.2016.05.005

• 研究综述 • 上一篇    下一篇

室内定位数据分析与应用研究进展

舒华1,2(), 宋辞1, 裴韬1,**()   

  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
  • 接受日期:2016-01-01 出版日期:2016-05-27 发布日期:2016-05-27
  • 通讯作者: 裴韬 E-mail:shuh@lreis.ac.cn;peit@lreis.ac.cn
  • 作者简介:

    作者简介:舒华(1989-),男,河南信阳人,博士研究生,主要从事时空数据挖掘研究,E-mail: shuh@lreis.ac.cn

  • 基金资助:
    国家杰出青年科学基金项目(41525004);国家自然科学基金创新研究群体项目(41421001);航空旅客信息服务分类与编码研究(4700003334)

Progress of studies on indoor positioning data analysis and application

Hua SHU1,2(), Ci SONG1, Tao PEI1,*()   

  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
  • Accepted:2016-01-01 Online:2016-05-27 Published:2016-05-27
  • Contact: Tao PEI E-mail:shuh@lreis.ac.cn;peit@lreis.ac.cn
  • Supported by:
    National Science Fund for Distinguished Young Scholars of China, No.41525004;Science Fund for Creative Research Groups of the National Natural Science Foundation of China, No.41421001;Classification and Encoding on Aviation Passengers’ Information Service, No.4700003334

摘要:

现代人文地理学的研究越来越多地关注人的时空行为,而获取个体在出行活动中的时空位置数据是研究人类时空行为的前提。受数据获取技术的限制,之前对时空行为的研究主要集中在室外空间。随着室内定位技术的出现和应用,这类研究由室外空间扩展至室内空间。室内定位技术和方法较多,但从数据的角度来看,根据数据获取中使用定位方法的不同,可将室内定位数据分为几何位置数据、指纹位置数据和符号位置数据3类。目前,基于室内定位数据的研究可以归结为以下4个方面,即:人在室内的时空分布、人在室内的移动模式、人在室内的行为习惯及属性推断、人与室内环境的交互作用。然而,总体上目前的研究还处于探索阶段,理论和方法体系尚未成熟。本文认为后续的研究中需要关注以下问题:①数据获取方面。相对于蓝牙、射频识别、红外等定位技术,“智能手机+WiFi”模式的定位系统具有覆盖范围广、成本低廉、无需专门设备支持、易与用户交互等优势,是一种最具应用前景的室内定位技术;②研究内容方面。时空行为特征的研究是基础,个体属性推断及个体与环境的相互作用形式和机理研究将是重点,多时空尺度数据融合分析是一种趋势;③科学伦理方面。室内定位涉及微观尺度人类活动的记录,隐私保护问题需要高度关注。

关键词: 定位数据, 室内定位, 数据分析, 时空行为, 大数据, 综述

Abstract:

Human spatiotemporal behavior increasingly draws attention in modern human geography, and obtaining individuals’ spatiotemporal location data in travel activities is the precondition to study the spatiotemporal behavior of people. Limited by data acquisition technology, previous studies about behavior in space and time mostly focused on behavior in the outdoor space of a city. With the occurrence of technology for indoor positioning, the spatial scale of this type of study has been extended to the indoor space. Although there is a wide range of technologies and methods for indoor positioning, according to the manner that these data are acquired, indoor positioning data can be divided into three categories, that is, geometric location data, fingerprinting location data, and symbolic location data. Currently, studies based on indoor positioning data can be divided into the following categories: (1) spatiotemporal distribution of people in indoor space; (2) movement pattern of people in indoor space; (3) behavioral habit and attribute inference of people in indoor space; and (4) interaction between people and indoor surroundings. However, most of these studies are still at a primary stage and there are no commonly accepted theories and methodologies at present. We believe that studies in the future may pay attention to the following issues: (1) with regard to data acquisition, the positioning system accomplished through “smart phone plus WiFi” that has wider coverage and lower cost, requires no special equipment, and interacts easily compared with Bluetooth, Radio Frequency Identification (RFID), and Infrared Ray (IR),and so on, is the most promising indoor positioning technology; (2) with regard to research contents, behavioral characteristics in space and time will be the basis, individuals’ attribute inference and interaction between individuals and indoor surroundings will be the focus, and analysis of multiscale fused spatiotemporal location data will be the trend of future development; (3) in terms of scientific ethics, privacy issues must be highlighted concerning the recording of individuals’ travel activity data at the micro scale.

Key words: positioning data, indoor positioning, data analysis, spatiotemporal behavior, big data, review