基于角点检测的高精度点匹配算法  

Point matching algorithm with high accuracy based on corner detection

作　　者：曹晓光[1] 徐琳[1] 郁文霞[1] 

机构地区：[1]北京航空航天大学图像处理中心,北京100083

出　　处：《仪器仪表学报》2006年第z2期1269-1271,共3页Chinese Journal of Scientific Instrument

摘　　要：针对多光谱、多传感器遥感图像的自动配准,本文提出新的基于角点检测的高精度点匹配算法。该算法充分利用图像的点特征以及灰度和位置信息,先由Harris算子检测得到待匹配的角点集合,随后采用局部灰度相关进行粗匹配得到多对多匹配对,然后进行迭代由精匹配得到一对一的匹配对,最后利用角点间距离比进行全局一致性检测,进一步保证匹配的准确率。初步实验表明,本算法对于存在仿射变换的遥感图像可以精确自动匹配,其精度和速度都优于传统的点匹配算法。For automatic registration of multi-spectral and multi-sensor remote sensing images, a new high accuracy point matching algorithm based on Harris corner detection is described in this paper. It makes full use of graphic point feature, gray-level pixel and location information. At first, after the corner sets are detected by Harris operator, N-to-N corner pairs are found through local gray-level matching. Next, one-to-one matched corner pairs are extracted using iterative accurate matching. Finally, a global consistency checking of corner distance rates is used to further ensure the correction of point pairs. Experimental results on remote sensing image pairs with affine geometric transform showed that the algorithm could do accurate automatic matching and it outperforms traditional point matching algorithms both in accuracy and running speed.

关 键 词：角点检测 点匹配 一致性检测 仿射变换 

分 类 号：TH7-55[机械工程—仪器科学与技术]