一种基于粒子滤波的智能移动终端室内行人定位算法

A Particle Filter Based Smart Mobile Terminal Indoor Pedestrian Localization Algorithm

针对现有室内定位算法精度较低、部署维护成本高、鲁棒性不足等缺点,提出一种基于粒子滤波的室内无线定位自学习算法,将在室内环境下行人定位问题描述为动态系统状态估计问题,将智能移动终端与室内定位相结合,分别利用智能移动终端内置的传感器和Wi-Fi模块感知用户运动和用户所在环境,并利用粒子滤波对得到的定位数据进行滤波融合.同时将定位结果实时上传至服务器,递增式地构建位置指纹库,并根据时间标签不断地更新指纹库,以适应室内环境的动态变化.实验结果表明,该定位算法有效克服了现有室内定位的局限性,提高了定位精度及鲁棒性.

For existing indoor localization algorithm has low accuracy, high cost in deployment and maintenance and lack of robust- ness, this paper proposes a particle filter based indoor wireless self-learning algorithm, the pedestrians localization in indoor environ- ment is described as dynamic system state estimation problem, combines the smart mobile terminal with indoor localization, uses the built-in sensors of smart mobile terminal and Wi-Fi module to apperceive the user＇s movement and his environment, and filters the re- sulting localization data with a particle filter. And uploads the localization results to the server in time, incrementaly builds the loca- tion fingerprint database, and the fingerprint database is constantly updated according to the time stamp, to adapt to the dynamic chan- ges in the indoor environment. Experimental results show that the localization algorithm is effective to overcome the limitations of ex- isting localization algorithm, improves the localization accuracy and robustness.