基于可穿戴设备的室内定位技术研究

Study on Indoor Position Identification Basing on Wearable Device

针对室内环境严重影响GPS信号的接收,无法实现室内的定位的问题,提出一种基于智能手环的室内定位方法.考虑到低功耗蓝牙(BLE)容易受到室内环境的影响,使得信号强度与物理距离呈非线性的关系,该文提出基于手腕方位角的信号补偿与滤波方法,一方面对蓝牙信号进行补偿,另一方面应用中值滤波方法去除加性噪声和卷积噪声的干扰,从而获取稳定的信号强度(RSSI);另外设计有限状态自动机,用于校正分类模型的分类结果,从而提高室内定位的准确性.实验证明,所提出的信号预处理方法非常有效,构建的室内分类模型具有一定的鲁棒性,能够准确地完成基于智能手环的室内定位.

The reception of GPS signals is affected by indoor environment,so the GPS can not be used in the indoor positioning system.In this paper,an indoor positioning system basing on smart-watch is proposed.The BLE is vulnerable to indoor environment,so the relationship between signal strength and physical distance is non-linear.A signal compensation and filtering method based on the angle of wrist is proposed.In addition to bluetooth signal compensation,median filtering method is also used to remove the interference of additive noise and convolution noise,so as to obtain stable value of RSSI.On this basis,a classification model of indoor positioning is constructed by using random forest.In order to improve the accuracy of indoor positioning,a finite state machine is created basing on the prior knowledge of the indoor environment to correct the positioning results.In our proposed system,the signal preprocessing method is effective,and the indoor classification model is robust.