室内行人移动行为识别及轨迹追踪  

Indoor Pedestrian Mobile Activity Recognition and Trajectory Tracking

作　　者：熊汉江[1] 郭胜 郑先伟[1] 周妍 XIONG Hanjiang;GUO Sheng;ZHENG Xianwei;ZHOU Yan(State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China)

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室

出　　处：《武汉大学学报（信息科学版）》2018年第11期1696-1703,共8页Geomatics and Information Science of Wuhan University

基　　金：国家重点研发计划(2016YFB0502203);测绘地理信息公益研究项目(201512009);测绘遥感信息工程国家重点实验室专项科研经费~~

摘　　要：作为室内位置服务的基础,室内定位技术近年来得到了广泛的关注。针对现有室内定位技术存在成本高、精度有限以及效率不足等问题,提出了一种融合人类活动识别、行人航迹推算（pedestrian dead reckoning,PDR）以及地标匹配修正等技术的室内行人位置推算方法。该方法使用基于智能手机的PDR技术来估算用户的位置信息,而人类活动识别技术则用来感知用户室内移动行为中的特定地标,利用这些地标信息来辅助修正PDR轨迹中产生的累积误差。此外,为了解决用户初始位置未知的问题,引入隐式马尔科夫模型进行推断,并提出了一种顾及室内环境特征的维特比算法来确定用户轨迹。实验结果显示,所提方法在提高室内行人移动行为识别和定位精度的同时,有效实现了用户室内轨迹的追踪。As the basis of indoor location services,indoor localization technology has received more and more attention in recent years.Aiming at the problems of high cost,limited precision and insufficient efficiency in existing indoor positioning technologies,pedestrian dead reckoning（PDR）,human activity recognition（HAR）and landmarks are combined to obtain more accurate pedestrian indoor localization.PDR is used to estimate the user＇s location,and the cumulative error of PDR is reduced by landmarks,which are sensed by HAR.In addition,to solve the initial position determination problem,a hidden Markov model that considers the characteristics of the indoor environment is applied to match the continuous trajectory.The experimental results show that the proposed method has a good performance in activity recognition and positioning accuracy,and can track the user＇s trajectory efficiently.

关 键 词：移动行为识别 室内定位 轨迹追踪 

分 类 号：P208[天文地球—地图制图学与地理信息工程]