基于图像校准的多源融合的室内定位方法  

Multi-source Data Fusion Indoor Localization Method Based on Image Matching

作　　者：刘镇华 黄嘉俊 LIU Zhenhua;HUANG Jiajun(College of Civil and Transportation Engineering,Shenzhen University,Shenzhen 518060,China;Research Institute for Smart City,Shenzhen University,Shenzhen 518060,China)

机构地区：[1]深圳大学土木与交通工程学院,广东深圳518060 [2]深圳大学智慧城市研究院,广东深圳518060

出　　处：《测绘地理信息》2021年第S01期272-275,共4页Journal of Geomatics

基　　金：深圳市科技创新委员会基础研究(学科布局)项目(JCYJ20170412105839839)

摘　　要：提出一种基于图像校准的多源融合的室内定位方法。结合WiFi信号,图像及惯性传感器数据的特点,在空间连续性和方向连续性的基础上,设定一系列客观规则来提高定位精度,给出了多源融合的室内定位方法框架。试验结果表明:本方法在2 m范围内匹配精度在85%以上,平均定位误差在2 m精度范围内的准确率达到70%。通过与单纯使用WiFi或图像定位对比,该算法分别在速度和精度上得到了较大的提升。A multi-source fusion indoor positioning method based on image calibration is proposed.Combined the characteristics of WiFi signal,image and inertial sensor data,a series of objective rules are set to improve the positioning accuracy on the basis of spatial continuity and directional continuity.This paper also proposes a"diffusion search"method to improve the efficiency of image matching.The experimental results show that the matching accuracy of this method within 2 m is over 85%,and the accuracy of the average positioning error within 2 m is up to 70%.By comparison,we find that the fusion algorithm is more accurate than the WiFi algorithm.And it also faster than the image algorithm.

关 键 词：室内定位 图像校准 WIFI 惯性传感器定位 多源数据融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN92[自动化与计算机技术—计算机科学与技术]