一种基于区域特征的景象匹配算法研究  

Research of scene matching algorithm based on regions

作　　者：李竹林[1] 张根耀[1] 

机构地区：[1]延安大学计算机学院,陕西延安716000

出　　处：《计算机应用研究》2012年第9期3578-3580,共3页Application Research of Computers

基　　金：陕西省自然科学基金资助项目(2009JM8004-7);陕西省教育厅专项科研计划资助项目(2010JK904)

摘　　要：景象匹配技术是飞行器匹配定位辅助导航系统的核心,如何提高其正确匹配率一直是研究的热点与难点。提出一种基于区域特征的景象匹配算法。首先,提取基准景象和实时景象的稳定极值区域,并计算出区域的灰度、形状、纹理以及起伏程度特性作为相似性度量的主要因素构造相似性度量函数;然后,计算区域对的Hausdorff距离,决定是否是对应区域。大量的模拟实验表明,该算法的匹配时间能达到0.138 s,正确匹配率达到92.67%,不仅能满足景象匹配的要求,且大大提高了匹配的时间与正确率,对导航系统的定位具有实用价值。Scene matching is core technology of the vehicle matching aided navigation system.Improving the correct matching rate is the difficult point and hotspot in research.This paper proposed a scene matching algorithm based on regions feature.Its basic method was： extracting the regions feature of the reference image and real image and computing the gray value,shape parameter,texture information and variance of region as the decisive factors to design the similarity measurement function firstly;then computing the Hausdorff distance of the region pair to decide whether corresponding regions or not.Plenty simulation experiments show that the matching time may achieve 0.138 s,the best correct matching rate is 92.67%.The result shows the algorithm not only meets the requirements of the scene matching,but also improves the matching time and correct rate greatly,and has practical value for the positioning of the navigation system

关 键 词：区域特征 景象匹配 HAUSDORFF距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]