基于人行为地图的室内PIR定位方法  

PIR-based Indoor Localization Method Combined with Human Behavior-based Map

作　　者：杨丹[1] 徐彬[1] YANG Dan;XU Bin(School of Information Science ＆ Engineering,Northeastern University,Shenyang 110819,China)

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110819

出　　处：《东北大学学报（自然科学版）》2018年第6期776-780,共5页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(51607029)

摘　　要：针对老人家庭看护中的室内定位问题,提出了一种基于人行为地图的室内热红外释电传感器(pyroelectric infrared sensor,PIR)定位方法.首先采集PIR传感器检测身体运动信号来确定人在室内的初步位置信息;利用惯性测量单元(inertial measurement unit,IMU)检测3D加速度信号识别人在室内的基本日常行为——躺、坐、站、走;利用IMU的3D加速度信号估计人的室内移动速度和方向;通过行为习惯观察,建立相应的躺、坐、站、走的行为地图;通过粒子滤波方法融合上述传感器信息,实现定位.实验结果表明,提出的方法在定位时,既保护人的隐私,也提高基于PIR传感器定位的精度及稳定性.Aiming to human localization method for elder people assisting in smart home, a method was proposed to realize the indoor localization by pyroelectric infrared sensor （ PIR） combined with human behavior-based map. PIRs were used for collecting body motion signal to localize the subject＇s raw position in the room. One inertial measurement unit （IMU） was used to collect 3D motion data for human daily body activity recognition such as lying, sitting, and standing. The other IMU was used for velocity and direction estimation. The related behavior- based maps were built by human habits observation. Particle filters method was presented to fuse the data from PIR and IMU,and took into account these prior behavior-based maps to get more accurate localization. Experimental results showed that the proposed approach has the advantage of protecting the privacy while maintaining high accuracy and stability of indoor localization.

关 键 词：室内定位 行为地图 热红外释电传感器 惯性测量单元 粒子滤波 

分 类 号：TN98[电子电信—信息与通信工程]