基于图像匹配与WiFi信号匹配的室内PDR定位方法  

PDR indoor positioning method based on image matching and WiFi fingerprinting

作　　者：刘水清[1,2] Liu Shuiqing(Huazhong University of Science and Technology,Wuhan 430074,China;Shandong Dazhong News Group,Jinan 250002,China)

机构地区：[1]华中科技大学,武汉430074 [2]大众报业集团信息技术部,济南250002

出　　处：《电子测量技术》2023年第1期154-159,共6页Electronic Measurement Technology

摘　　要：由于智能手机中存在丰富的传感器,可对周围环境进行感知并进而估计位置。本文提出一种融合室内定位方法,融合的信息包含图像信息、WiFi信号指纹信息以及惯性数据观测信息。通过实测实验结果表明,本文提出的方法相比于惯性定位、WiFi定位、图像匹配定位三种单一的定位方法,定位精度分别提高了48%、24%和4%。相比于经典WiFi和图像融合方法,平均定位时间下降了92%。相比于经典融合方法,定位的精度提高了0.7 m,并且平均定位时间下降了87%。Smart phone based indoor positioning has great potential usage in LbS(Location based Service)applications,due to the abundant sensors embedded in smart phones.This paper proposed a hybrid positioning method,which adopted a particle filter to fuse three types of independent positioning results,including image matching positioning result,WiFi fingerprinting results and PDR positioning results,which achieve continuous and accurate positioning results.According to real scenario experiments,the proposed method has an accuracy improvement of about 48%,24%and 4%over pure PDR,WiFi fingerprinting and image matching based methods.Compared with classical WiFi and image matching fusion method,our method can provide a decrease of 92%average positioning time.Compared with another classical fusion method,the accuracy has increased by 0.7 m and the positioning time has decreased by 87%.

关 键 词：室内定位 融合定位 WiFi信号指纹 图像处理 惯性定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]