改进平均Frechet距离法及在化简评价中的应用  

An improved average Frechet distance method and application in simplification evaluation

作　　者：程绵绵 孙群[1] 季晓林[1] 赵云鹏[1] CHENG Mianmian;SUN Qun;JI Xiaolin;ZHAO Yunpeng(Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学,郑州450001

出　　处：《测绘科学》2020年第3期170-177,共8页Science of Surveying and Mapping

基　　金：国家自然科学基金项目(41571399)。

摘　　要：针对平均Frechet距离易受节点分布及采样精度影响不足的问题,该文提出一种改进的平均Frechet距离计算方法。依据节点到待匹配曲线的最近距离,在待匹配曲线上插入辅助节点,在此基础上构造节点的欧式距离矩阵和离散Frechet距离矩阵,据此搜索节点的最短路径,计算两曲线的平均Frechet距离。为验证相同形状情况下,相似度值对节点的依赖程度,向曲线上插入随机节点,比较传统平均Frechet距离和本文改进的平均Frechet距离。结果表明,本文方法对形状的采样点依赖度更小,且计算结果更稳定。In view of this deficiency that average Frechet distance was susceptible to the influence of node distribution and sampling precision,an improved average Frechet distance calculation method was proposed in this paper.According to the nearest distance from the node to the matching curve,the auxiliary node was inserted on the matching curve.The shortest path of the node was searched by Euclidean distance matrix and discrete Frechet distance matrix,and the average Frechet distance of the two curves was calculated.To verify the method,the traditional and improved average Frechet distance were compared under the circumstances of inserting random nodes into the curve.Results showed that the proposed method was less dependent on the sampling point,and the value was more stable.

关 键 词：相似性度量 Frechet距离 线状要素 制图综合 化简 

分 类 号：P283.7[天文地球—地图制图学与地理信息工程]