结合Harris和改进K-means的遥感图像配准算法

Remote Sensing Images Registration Algorithm Combining with Harris and Improved K-means

针对高分辨率遥感图像中,特征点数目大且易存在误匹配点的问题,提出结合Harris和改进K-means的遥感图像配准算法。首先,利用Harris提取特征点;然后,使用改进K-means算法进行区域划分,进行特征点匹配;最后,区域间利用RANSAC方法剔除错误匹配点,得到精确匹配点对。该算法减少了特征点数目,提高配准精确度。实验结果表明了算法的有效性。

Aiming at the problems such as false matching points and large volume remote sensing image registration,a remote sensing image registration algorithm based on Harris and improved K-means is proposed.Firstly,the feature points were extracted with Harris.Secondly,feature point is matching after the improved K-means algorithm used for region division.Finally,RANSAC method is used to eliminate the wrong matching points among regions,and the precise feature points are obtained.The proposed algorithm can reduce the number of feature points,and it can increase the registration accuracy.The experimental results indicate that the proposed method is effective.