期刊文献+

一种基于穿戴式MEMS传感器状态识别的多部位PDR算法 被引量:7

A Multi-mouted PDR Algorithm Based on Wearable MEMS Sensors State Recognition
原文传递
导出
摘要 随着位置服务(location based service,LBS)应用需求的日益增加以及多部位微机电系统(micro electro mechanical system,MEMS)导航传感器的广泛普及,行人航位推算(pedestrian dead reckoning,PDR)越来越受关注,成为行人导航研究中主流的技术之一。但是,低成本的MEMS传感器测量噪声大,PDR解算误差积累严重;且PDR算法的普适性差,不同穿戴位置的MEMS导航传感器约束条件的可用性差异明显。提出了一种基于穿戴式MEMS传感器状态识别的多部位PDR算法。首先,采用支持向量机(support vector machine,SVM)进行全监督训练,实现了静止状态及运动状态下手部、腿部、腰部、足部4种穿戴位置的准确识别;然后,分析了不同穿戴位置下PDR算法的适用性,根据适用性分析结果提出了多部位PDR的综合解算策略。实测结果表明,该方法能够动态、准确地实现穿戴式MEMS传感器的状态识别,正确率达97%以上;应用PDR综合解算策略后,足部PDR能够实现高精度解算,累计误差为0.74%,而其他位置(手部、腿部、腰部)解算效果得到显著改善,累计误差从识别前的6.76%~21.19%减小为2.92%~5.62%。 Objectives:With the increasing demand for location-based service(LBS)applications and the wide popularity of multi-mounted micro electro mechanical system(MEMS)navigation sensors,pedestrian dead reckoning(PDR)algorithm has attracted more and more attention and has become one of the mainstream algorithms in pedestrian navigation research.However,the low-cost MEMS sensor has high measurement noise and serious accumulation of PDR solution error.Moreover,the universality of PDR algorithm is poor,and the availability of constraints of MEMS navigation sensors with different wearing statte is significantly different.Methods:A multi-mounted PDR algorithm based on wearable MEMS sensor state recognition is proposed.Firstly,support vector machine is used for fully supervised training to realize the accurate recognition of five wearing modes(hand,leg,waist,foot and stationary state).Then the applicability of PDR algorithm in different wearing states is analyzed,and a comprehensive solution strategy of multi position PDR is proposed based on the applicability analysis results.Results:The measured results show that the wear recognition accuracy of MEMS sensor is more than 97%.The foot PDR can achieve high-precision solution,and the cumulative error is 0.74%,while the solution effect of other positions(hand,leg and waist)has been significantly improved,and the cumulative error has been reduced from 6.76%—21.19%before recognition to 2.92%—5.62%after recognition.Conclusions:Therefore,the proposed algorithm can dynamically and accurately realize the state recognition of wearable MEMS sensors.After applying the PDR comprehensive solution strategy,the solution accuracy of PDR is significantly im-proved.
作者 张小红 罗科干 陶贤露 胡鑫 刘万科 ZHANG Xiaohong;LUO Kegan;TAO Xianlu;HU Xin;LIU Wanke(School of Geodesy and Geomatics,Wuhan University,Wuhan 430079,China)
出处 《武汉大学学报(信息科学版)》 EI CAS CSCD 北大核心 2021年第12期1791-1801,F0002,共12页 Geomatics and Information Science of Wuhan University
基金 国家重点研发计划(2016YFB0501803) 湖北省技术创新专项(重大项目)(2019AAA043) 武汉市科技计划项目(2020010601012185)。
关键词 行人航位推算 惯性导航系统 穿戴式MEMS传感器 支持向量机 组合导航 pedestrian dead reckoning(PDR) inertial navigation system(INS) wearable MEMS sensor support vector machine integrated navigation
  • 相关文献

参考文献4

二级参考文献14

  • 1Roberts R. Ranging Subcommittee Final Report[R]. IEEE 802.15 WPAN Documents, 15 -04- 0581 -07- 004a, 2004.
  • 2Niculescu D , Nath B. Ad Hoc Positioning System (APS) Using AOA[C]. IEEE INFOCOM, Piscataway, USA, 2003.
  • 3Djuknic G M , Richton R E. Geo-location and Assisted GPS[J]. IEEE Computer, 2001, 34(2) : 123- 125.
  • 4Pahlavan K , Li X, Makela J P. Indoor Geolocation Science and Technology[J]. IEEE Commun Mag, 2002, 40(2) :112-118.
  • 5Jan R H, Lee Y R. An Indoor Geo-Location System for Wireless LANS[J]. IEEE Commun Mag, 1998, 36(4) :60-65.
  • 6Rabinowitz M, Spilker J J. A New Positioning Systern Using Television Synchronization Signals[J] IEEE Transactions on Broadcasting, 2005, 51 (1) 51- 61.
  • 7Tian H, Esmond M. A New Pedestrian Geolocation Technique Based on Outdoor Public WiFi Signals in Hong Kong[C]. ASSIST08, Hong Kong, China, 2008.
  • 8杨元喜,张菊清,张亮.基于方差分量估计的拟合推估及其在GIS误差纠正的应用[J].测绘学报,2008,37(2):152-157. 被引量:35
  • 9杨元喜,何海波,徐天河.论动态自适应滤波[J].测绘学报,2001,30(4):293-298. 被引量:186
  • 10杨元喜.综合PNT体系及其关键技术[J].测绘学报,2016,45(5):505-510. 被引量:193

共引文献273

同被引文献64

引证文献7

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部