Abstract: Map matching algorithms include on-line and off-line matching algorithms. Aiming at the problem of the lower precision and indistinct multiple solutions of Marchal’s off-line matching algorithm, this paper presents an improved map matching algorithm based on Pseudo-Zernike moments, which uses the Pseudo-Zernike moments to obtain the road points by describing the trace course and road curve and then carrying out feature matching. The results of simulation and experiment show that the new algorithm can correct the errors resulted from the incomplete vector map, it can improve the precision of map matching greatly with higher efficiency better than the existing algorithm.

Key words: vector map, map matching, pseudo-Zernike moments, trace fitting

摘要： 地图匹配算法分为在线和离线匹配，针对离线地图匹配中Marchal算法精度较低以及存在模糊多解的问题，利用伪Zenike矩对其进行改进，将行驶轨迹与道路曲线利用伪Zenike矩进行形状描述，然后对曲线进行特征匹配，获取道路点。实验结果表明，新算法可以较好地纠正矢量数据不完整时Marchal算法产生的错误结果，很大程度上提高了匹配的准确性，而且匹配的效率优于现有算法。

关键词: 矢量数据, 地图匹配, 伪Zenike矩, 轨迹拟合