针对单一室内定位技术的局限性,提出了一种基于扩展卡尔曼滤波(EKF)融合WiFi和行人航位推算(PDR)的定位方法。不同于传统WiFi指纹定位,本文基于随机森林(RF)模型建立多个基分类器,取投票结果的众数作为输出结果;通过采集手机内置传感器数据解算行人的步频、步长,并基于四元数进行航向估计。本文在EKF融合定位时,根据状态模型得到状态的预测值,RF模型输出观测值,根据观测值更新状态估计,推算下一时刻位置。试验表明,本文研究的融合算法的定位精度可达到1.26 m
An Indoor Multi-source Fusion Positioning Approach Based on PDR/MM/WiFi[J]. chen Jian;Song Shaojing;Yu Haihua.AEU - International Journal of Electronics and Communications,2021
DeepLocBox: Reliable Fingerprinting-Based Indoor Area Localization[J]. Laska Marius;Blankenbach Jörg.Sensors,2021
Research on multi-sensor pedestrian dead reckoning method with UKF algorithm[J]. HuiXia Li;Hang Guo;Yuhui Qi;Linkun Deng;Min Yu.Measurement,2021
Symmetric Position Drift of Integration Approach in Pedestrian Dead Reckoning with Dual Foot-mounted IMU[J]. .Journal of Positioning, Navigation, and Timing,2020
On cleaning strategies for WiFi positioning to monitor dynamic crowds[J]. Ciro Gioia;Francesco Sermi;Dario Tarchi;Michele Vespe.Applied Geomatics,2019
WIFI POSITIONING BASED ON USER ORIENTATION ESTIMATION AND SMARTPHONE CARRYING POSITION RECOGNITION[J]. Zhi-An Deng;Zhiyu Qu;Changbo Hou;Weijian Si;Chunjie Zhang.Wireless Communications & Networking,2019