基于WiFi-GM指纹的室内定位算法

doi:10.16180/j.cnki.issn1007-7820.2019.05.010

摘要/Abstract

摘要：

针对室内环境中单一指纹定位方法存在定位误差较大、定位漂移的问题,提出了一种融合室内Wi-Fi指纹和地磁指纹的定位算法。首先在大范围区域中通过K-means聚类方法将较大的匹配区域划分成更小的且特征更加明显集中的子区域,然后在在线阶段通过WiFi指纹粗定位到小区域,再通过地磁指纹定位系统进行近一步精匹配定位。实验表明,该融合算法缩小了地磁匹配的初始搜索范围,大大减少了指纹定位中的误匹配问题。实验中,平均定位误差仅2.17 m,最大定位误差3.61 m,较单一指纹定位系统性能均有大幅度提升,证明该定位方法具有一定的可行性与先进性。

关键词: 室内定位, WiFi, 地磁场, 指纹, K-means聚类, 磁匹配

Abstract:

For the problem that the single fingerprint location results were large errors and drifting in indoor environment, an improved algorithm of geomagnetic and WiFi fingerprint system was proposed. First, the larger matching area was divided into smaller sub-regions with more distinctive features by K-means clustering method. In the online phase, Wi-Fi fingerprints were used to coarsely locate small areas, and then a further fine-match positioning was performed through the geomagnetic fingerprint positioning system. Experimental results showed that the integration of algorithm reduced the searching area, and greatly reduced the problem of mis-matching. In the experiment, the average positioning error was only 2.17 m, and the maximum positioning error was 3.61 m. Compared with the single fingerprint positioning system, the performance was greatly improved, which proved that the positioning method had certain feasibility and advancement.

Key words: indoor location, WiFi, geomagnetic field, fingerprint, K-means clustering, magnetic matching

中图分类号:

TN92

章裕润,吴飞,毛万葵. 基于WiFi-GM指纹的室内定位算法[J]. 电子科技, 2019, 32(5): 49-54.

ZHANG Yurun,WU Fei,MAO Wankui. Indoor Location Algorithm Based on WiFi-geomagnetism[J]. Electronic Science and Technology, 2019, 32(5): 49-54.

图/表 10

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

参考文献 16

[1]	Vo Q D, De P . A Survey of fingerprint-based outdoor localization[J]. IEEE Communications Surveys & Tutorials, 2017,18(1):491-506.
[2]	Youssef M A, Agrawala A. The horus WLAN location determination system[C]. Seattle:The Third International Conference on Mobile systems,Applications,and Services, 2005.
[3]	Mendoza Silva G M, Torres Sospedra J, Huerta J. Locations selection for periodic radio map update in WiFi fingerprinting[C]. Zurich:The 14th International Conference on Location Based Services, 2018.
[4]	Chung J, Donahoe M, Schmandt C, et al. Indoor location sensing using GeoMagnetism [C]. Washington DC:The Ninth International Conference on Mobile Systems,Applications and Service, 2011.
[5]	Sen S, Radunovic B, Choudhury R R, et al. You are facing the mona lisa:spot localization using PHY layer information[C]. Low Wood Bay:The Tenth International Conference on Mobile Systems,Applications,and Service, 2012.
[6]	曹雪朋, 施伟斌 . 基于RSSI的WSN室内定位系统研究[J]. 电子科技, 2017,30(1):94-96.
	Cao Xuepeng, Shi Weibin . Based on RSSI to research indoor positioning system of WSN[J]. Electronic Science and Technology, 2017,30(1):94-96.
[7]	Microsoft.Microsoft indoor localization competition IPSN 2015[EB/OL].( 2015- 02- 11) [2018-04-02] .
[8]	陈璇, 董仕鹏 . 基于修正RSSI值的加权质心定位算法[J]. 电子科技, 2017,30(4):92-94.
	Chen Xuan, Dong Shipeng . Study of WSN indoor positioning system based RSSI[J]. Electronic Science and Technology, 2017,30(4):92-94.
[9]	蔡劲, 蔡成林, 张首刚 , 等. GNSS/地磁组合的室内外无缝定位平滑过渡方法[J]. 测绘通报, 2018(2):30-34.
	Cai Jin, Cai Chenglin, Zhang Shougang , et al. A smooth transition method for indoor and outdoor seamless positioning of GNSS/magnetic combination[J]. Bulletin of Surveying and Mapping, 2018(2):30-34.
[10]	马明, 宋千, 李杨寰 , 等. 基于地磁辅助的室内行人定位航向校正方法[J]. 电子与信息学报, 2017,39(3):647-653.
	Ma Ming, Song Qian, Li Yanghuan , et al. Magnetic-aided heading error calibration approach for indoor pedestrian positioning[J]. Journal of Electronics & Information Technology, 2017,39(3):647-653.
[11]	Cong C, Men X. An innovative indoor location algorithm based on supervised learning and WiFi fingerprint classification[C]. Beijing:Proceeding of Signal and Information Processing, Networking and Computers, 2018.
[12]	吴泽泰, 蔡仁钦, 徐书燕 , 等. 基于K近邻法的WiFi定位研究与改进[J]. 计算机工程, 2017,43(3):289-293.
	Wu Zetai, Cai Renqin, Xu Shuyan , et al. Resrearch and improvement of WiFi positioning based on K nesarest neighbor method[J]. Computer Engineering, 2017,43(3):289-293.
[13]	李桢, 黄劲松 . 基于RSSI抗差滤波的WiFi定位[J]. 武汉大学学报:信息科学版, 2016,41(3):361-366.
	Li Zhen, Huang Jingsong . WiFi positioning using robust filtering with RSSI[J]. Geomatics and Information Science of Wuhan University, 2016,41(3):361-366.
[14]	杨帆 . 基于改进KNN算法的室内WiFi定位技术研究[D]. 西安:西北工业大学, 2016.
	Yang Fan . Research on indoor WiFi positioning technology based on improved KNN algorithm[D]. Xi’an:Northwestern Polytechnical University, 2016.
[15]	Edel J B, Duringer P . The apparent polar wander path of the European plate in upper triassic-lower jurassic times and the liassic intraplate fracturing of Pangaea: new palaeomagnetic constraints from NW France and SW germany[J]. Geophysical Journal of the Royal Astronomical Society, 2018,128(2):331-344.
[16]	Rahman M A, Hossain M S. A location-based mobile crowdsensing framework supporting a massive Ad Hoc social network environment[M]. Bostorn: IEEE Press, 2017.

1类	2类	3类	4类	5类	6类
1号点	3号点	12号点	14号点	16号点	22号点
2号点	7号点	13号点	15号点	17号点	23号点
4号点	8号点	16号点	26号点	18号点	24号点
5号点	9号点	17号点	27号点	19号点	25号点
6号点	10号点		28号点	20号点
	11号点			21号点

	WiFi	GM	WiFi-GM
中误差/m	5.06	2.58	2.11
平均误差/m	4.65	2.84	2.17
最大误差/m	7.38	5.81	3.61