摘要
针对单一的WiFi定位误差较大的问题,提出了利用IMU人体姿态传感器来辅助WiFi进行室内定位的方案。首先在实验场所建立合适的WiFi位置指纹库,然后利用改进的K-NN算法对终端进行实时定位。同时利用IMU所测得的角度变化和终端前一个位置的坐标来判断终端处于哪一个象限,再和该象限的WiFi指纹库进行匹配计算出终端的坐标,从而不仅缩小了算法的复杂度,也提高了室内定位的精确度。
Aiming at the problem that single WiFi positioning error is large,this paper proposed a method which uses IMU sensor to assist WiFi indoor positioning. Firstly,we need to establish proper WiFi location fingerprint in experimental places,then use the improved K-NN algorithm for real-time positioning terminal. At the same time,we use angle change measured by the IMU and the former coordinate's position of terminal to judge terminal in which quadrant,and then match it with the WiFi fingerprint of this quadrant to calculate the coordinates of the terminal. It not only reduces the complexity of the algorithm,but also improves the accuracy of indoor positioning.
出处
《微型机与应用》
2017年第8期11-14,共4页
Microcomputer & Its Applications
