采用指纹SD权重的FM两级室内定位方法

FM two-stage indoor positioning method using fingerprint SD-weight

针对在室内定位中使用调频广播时指纹模糊的问题,提出一种基于指纹标准差权重的指纹定位方法:根据当前指纹数据库的标准差,调整用户与参考点之间的欧氏距离的权重,有效降低指纹的模糊性;同时为了降低定位过程中错误近邻点的影响,将定位过程分为区域定位和精确定位2个阶段,首先对用户进行区域定位来判定用户所在位置区域,然后进行精确定位,根据判定规则判断剔除不属于区域定位结果的近邻点。实验结果表明,在50次蒙特卡洛的情况下,该方法能够获得较高的定位精度。

Aiming at the problem of fingerprint blurred using FM radio in indoor positioning,the paper proposed a fingerprint positioning method based on the standard deviation weight of fingerprints:the weight of the Euclidean distance between the user and the reference point was adjusted according to the standard deviation of the current fingerprint database,which effectively reduced the fuzziness of the fingerprints;at the same time,in order to reduce the impact of the wrong near neighbors in the positioning process,the localization process was divided into two stages:regional positioning and precise positioning,in which the user was located by the regional positioning firstly,and the precise positioning was carried out to determine removing the nearest neighbor that does not belong to the regional positioning result according to the judgment rule.Experimental result showed that in the case of 50 Monte Carlo,the proposed method could help obtain the high positioning accuracy.