基于相邻基准子图灰度统计相关的快速互信息匹配算法  

Fast Mutual Information Based Matching Algorithm in Terms of Gray-level Statistical Correlation of Adjacent Reference Sub-images

作　　者：符艳军 孙开锋[2] FU Yanjun;SUN Kaifeng(Xi'an International University,Xi'an 710077,China;Xi'an Precision Machinery Research Institute,Xi'an 710075,China)

机构地区：[1]西安外事学院,西安710077 [2]西安精密机械研究所,西安710075

出　　处：《弹箭与制导学报》2020年第6期5-10,共6页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：西安外事学院博士科研启动基金(XAIU2019010);陕西省自然科学基金(2020JM-637)资助。

摘　　要：针对互信息计算量大所导致的匹配算法实时性差问题,提出了一种快速互信息计算方法。利用相邻基准子图之间的相关性,将前一匹配位置基准子图的灰度统计量更新为当前位置的,避免了大量的重复计算。仿真结果表明:与标准互信息测度计算方法相比,在不影响匹配概率和匹配精度的前提下,匹配耗时平均减少20%以上。文中方法可以与灰度压缩、多分辨率分层匹配等方法相结合进一步提高匹配的实时性。Aiming at the poor real-time performance of the matching algorithm caused by the large amount of mutual information(mutual information,MI for short)computation,a fast MI computation method is proposed in this paper.In the matching process,the gray statistics of the previous matching position reference sub-image is updated to the current position by using the correlation between the adjacent reference sub-images,which avoids a lot of repeated calculation.Experimental results show that,compared with the standard method,the average matching time consumed is reduced by more than 20%without affecting the matching probability and matching accuracy.Furthermore,the proposed method can be combined with the existed gray-level compression based method or multi-resolution based method to further improve the real-time performance of matching.

关 键 词：归一化互信息 图像熵 统计相关 差量法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]