基于二进制粒子群优化算法的线状目标简化  

Research on simplification of linear objects based on BPSO algorithm

作　　者：郑春燕[1] 郭庆胜[2] 胡华科[1] 

机构地区：[1]嘉应学院地理科学与旅游学院,广东梅州514015 [2]武汉大学资源与环境科学学院,武汉430079

出　　处：《测绘科学》2016年第6期168-172,共5页Science of Surveying and Mapping

基　　金：国家自然科学基金项目(41101351;41471384);数字制图与国土信息工程国家测绘地理信息局重点实验室开放研究基金项目(GCWD201102)

摘　　要：针对如何从线状目标的简化可行解中选取近似最优解的问题,该文基于二进制粒子群优化算法原理,将线状目标的可行解抽象为节点是否取舍两种状态的二进制序列,由粒子群根据个体经验和社会经验判断构成线状目标上的节点取舍,提出并设计了一种简化线状目标的算法。目标函数主要由节点压缩率和矢量偏差确定,文中给出了算法实现的关键步骤。通过与道格拉斯-普克算法作对比实验分析,证明了该算法的有效性,保留了重要的几何特征点,图形有良好的外观视觉效果,且有更高的节点压缩率。The simplification of linear objects can be looked upon as a 0-1integer programming problem.In this paper,in order to select one approximate optimal solution from the feasible simplified results of linear objects,an algorithm which could be used to simplify linear objects was proposed based on the principle of binary particle swarm optimization algorithm.The feasible solution for the simplification of linear object was abstracted as binary sequence,which could explain the two states（be selected or discarded）for the nodes on linear object.According to the Bias formula,the nodes on the linear object were determined to be selected or be discarded by particle individual experience and social experience of particle group to determine the node.The objective function for evaluating fitness value mainly took into account the geometric accuracy and node compression ratio.The key steps about the new simplification algorithm of linear objects were given in the paper based on binary particle swarm optimization algorithm.The proposed algorithm was tested and compared with Douglas algorithm.The results demonstrated that this algorithm was feasible and effective,the basic geometric characteristics of linear objects were maintained with good visual effect,and higher compression ratio was achieved.

关 键 词：线状目标 二进制粒子群优化 0-1整数规划 简化 

分 类 号：P208[天文地球—地图制图学与地理信息工程]