计算机应用 ›› 2017, Vol. 37 ›› Issue (7): 2118-2123.DOI: 10.11772/j.issn.1001-9081.2017.07.2118

• 应用、前沿交叉与综合 • 上一篇    下一篇

基于智能手机感知室内有效位移的方法

钟勇1, 关济昌1,2, 杨凡1,3   

  1. 1. 中国科学院 成都计算机应用研究所, 成都 610041;
    2. 中国科学院大学, 北京 100190;
    3. 香港理工大学 电子计算学系, 香港 999077
  • 收稿日期:2016-12-28 修回日期:2017-03-14 出版日期:2017-07-10 发布日期:2017-07-18
  • 通讯作者: 关济昌
  • 作者简介:钟勇(1966-),男,四川岳池人,研究员,博士生导师,博士,主要研究方向:大数据、云计算、数据库;关济昌(1991-),男,河南商丘人,硕士研究生,主要研究方向:大数据、室内位置服务;杨凡(1978-),男,江苏丹阳人,博士研究生,主要研究方向:移动计算、数据挖掘、机器学习、软件工程。
  • 基金资助:
    四川省科技厅项目(2014GZ0104);中国科学院西部青年学者项目(2015XBZG)。

Indoor displacement calculation method based on smart phone sensors

ZHONG Yong1, GUAN Jichang1,2, YANG Fan1,3   

  1. 1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
    2. University of Chinese Academy of Science, Beijing 100190, China;
    3. Department of Computing, The Hong Kong Polytechnic University, Hong Kong 999077, China
  • Received:2016-12-28 Revised:2017-03-14 Online:2017-07-10 Published:2017-07-18
  • Supported by:
    This work is partially supported by the Project of Science & Technology Department of Sichuan Province (2014GZ0104), West Light Foundation of the Chinese Academy of Sciences (2015XBZG).

摘要: 结构构建是室内地图构建的基础,而室内测距是结构构建中的核心问题。为克服现有测距方法中成本高或精度低的不足,在融合了多种智能手机传感器数据的基础上,重新设计了基于步数步幅统计的测距方法。在步数统计阶段,参照机器学习方法支持向量机(SVM)的设计思想计算最优阈值,使得模型具有极好的泛化能力;在检测步伐有效性阶段,利用磁力传感器数据的方差来筛选产生有效位移的步数;最后通过步幅估计模型计算步幅,进而实现有效位移的测算。通过实时构建室内地图等项目的验证,所提方法被证明是有效的,整体误差率在4%左右,可以达到构建室内地图所要求的精度,为室内地图构建中的有效位移计算提供了一种低成本、高可靠性的方法。

关键词: 位移计算, 手机感知, 室内地图, 有效计步, 采样

Abstract: The construction of structure is the foundation of indoor map constructing, and the indoor distance measuring is one of the core problems in this process. In order to solve the problem of high cost or low accuracy in the existing methods, a distance measuring method based on the statistical steps and strides with the multi-sensor data was proposed. In the stage of counting steps, the optimal threshold was calculated according to the ideas of Support Vector Machine (SVM), which made the model have excellent generalization ability. In the stage of detecting the validity of the step, the variance of the direction sensor data was used to filter the effective displacement steps. Finally, the stride estimation model was used to estimate the stride, and then the effective displacement was calculated. In the practical application, the proposed method is proved to be effective, and the overall error is about 4%, which can achieve the accuracy required to build indoor maps. It is a low cost and reliable displacement calculation method for indoor map constructing.

Key words: displacement calculation, smart phone awareness, indoor map, effective steps counting, sampling

中图分类号: