物联网学报 ›› 2017, Vol. 1 ›› Issue (1): 55-66.doi: 10.11959/j.issn.2096-3750.2017.00008

• 理论与技术 • 上一篇    下一篇

基于多信息融合的室内定位系统

牛建伟,齐之平,吕卫锋,李辉勇,盛 浩   

  1. 1.北京航空航天大学虚拟现实技术与系统国家重点实验室,北京 100191; 2.北京航空航天大学软件开发环境国家重点实验室,北京 100191
  • 收稿日期:2017-05-20 出版日期:2017-06-30 发布日期:2017-11-02
  • 基金资助:
    国家自然科学基金资助项目 ( No.61572060, No. 61190125); CERNET 创新 2015 基金资助项目(No.NGII20151004); 国家基础研究发展计划( “ 973”计划)基金资助项目( No.2013CB035503)

Indoor localization system based on multi-information fusion

NIU Jian-wei, QI Zhi-ping, LYU Wei-feng, LI Hui-yong, SHENG Hao   

  1.  
  • Received:2017-05-20 Online:2017-06-30 Published:2017-11-02
  • Supported by:
     

摘要: 日常生活中使用 GPS( global position system)进行定位,但 GPS 无法在室内工作,准确地进行室内定 位成为研究的热点之一。在早期的研究中,围绕 Wi-Fi 指纹进行了大量的实验与改进,但 Wi-Fi 指纹受到环境因 素制约,定位误差较大。针对这一问题,提出一种多信息融合的室内定位算法。首先通过 Wi-Fi 指纹进行粗略的 定位,获取 Wi-Fi接入设备的 MAC地址以及其信号强度 RSSI(received signal strength indication),通过 kNN ( k nearest neighbor)算法进行分类,得到 top-n 候选集。再通过地磁信号与图片信息进行候选集的过滤。最后利用社交信息, 给出人在室内的最终定位结果。在 Android 平台和服务器上对该系统进行验证,实验结果表明提出的多信息融合 的方法比 Wi-Fi 指纹的定位算法精度明显提高。

Abstract: GPS is used for localization usually, but cannot be applied indoors. It was a popular topic on how to do the indoor localization accurately. In the early research, indoor localization system based on Wi-Fi fingerprints suffer from the accuracy and site survey problems. Therefore, a novel room-level indoor localization system was designed, which solved the localization problem by using multi-information fusion. Firstly, a top-n candidate through the Wi-Fi fingerprint was gotten, kNN classification algorithm was used after MAC address and the RSSI were gotten. The candidate set was filtered by the geomagnetic signal and the image information. Finally, the social information was used to give the final location results of people in the room. The system was validated on smart phone with Android system. The experimental results show that proposed method is more accurate than the Wi-Fi fingerprint localization algorithm.

中图分类号: