加权Hausdorff距离算法在SAR/INS景象匹配中的应用  

Application of Weighted Hausdorff Distance Algorithm in SAR/INS Scene Matching

作　　者：冷雪飞[1] 刘建业[1] 熊智[1] 邢广华[1] 

机构地区：[1]南京航空航天大学自动化学院,南京210016

出　　处：《控制与决策》2006年第1期42-45,共4页Control and Decision

基　　金：国防科技预研跨行业基金项目(51409040201HK0206)

摘　　要：提出了一种基于特征图像分支点提取的加权H ausdorff距离图像匹配算法,并给出了相应的权值求解公式.为满足景象匹配导航系统实时性的要求,给出了细化处理的预处理方法,减少了特征文件的冗余度,提高了匹配搜索的快速性.同时,基于细化后提取出的分支特征点,应用加权H ausdorff距离算法进行图像匹配,克服了斑点噪声对合成孔径雷达(SAR)图像匹配的影响.仿真分析表明,该算法能满足SAR/IN S景象匹配辅助导航系统实时性和准确性的要求.A weighted Hausdorff distance image matching algorithm based on extracting bifurcating points on feature image is proposed. The corresponding weight formula is also put forward. A preprocessing of thinning the binary image is presented to meet the real-time need of scene matching aided navigation system. This preprocessing can reduce the redundancy of the database and speed up the global search time. Then, based on the bifurcating points extracted from thinning image, the application of the weighted Hausdorff distance algorithm to image matching can overcome the effect of speckle noise in the synthetic aperture radar （SAR） image. Simulation shows that this algorithm meet the real-time and accuracy needs of SAR/INS scene matching aided navigation system.

关 键 词：加权HAUSDORFF距离 合成孔径雷达 组合导航 图像匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]