聚类算法的GPS静态单点定位方法

A method of GPS static single point positioning based on clustering algorithm

摘要:

为有效提高GPS静态单点定位的精度,提出了一种基于模糊聚类算法和卡尔曼滤波算法的组合优化方法. 该方法首先对GPS实测数据进行卡尔曼滤波,消除波动较大的数据,然后应用模糊C-均值聚类算法寻求聚类中心,以该聚类中心为最终定位坐标. 实验结果表明,该组合优化定位方法在降低定位成本的同时,可以有效提升GPS静态单点定位精度,采用该方法得到的定位坐标更接近于真实的地理坐标. 

Abstract:

This paper presents a combination method based on fuzzy C-means clustering algorithm and Kalman filter, which effectively improves the GPS static point positioning accuracy. Firstly, the latitude and longitude data collected by GPS was filtered by Kalman filtering, which could eliminate large fluctuations in the data. Secondly, the fuzzy C-means clustering algorithm was used to find the clustering center as the final positioning coordinate. The experimental result shows that, this method can effectively promote the degree of accuracy of GPS static single point positioning with low cost, and the coordinates of the positioning is more close to the true geographical coordinates. 