基于Harris与RANSAC算法的无人机影像拼接方法研究  

Research on the Mosaic Method of UAV Image Based on Harris and RANSAC

作　　者：刘金萍 刘文宋 陈勇[2] 刘善伟[2] 

机构地区：[1]中石化石油工程地球物理有限公司胜利分公司,山东东营257086 [2]中国石油大学(华东),山东青岛266580

出　　处：《测绘与空间地理信息》2014年第9期103-105,共3页Geomatics & Spatial Information Technology

基　　金：校级重点教学试验技术改革项目(SY-A201203);中央高校基本科研业务费专项资金(12CX04012A)资助

摘　　要：针对Harris算法在进行无人机影像拼接时的特征点误匹配问题,利用RANSAC算法对误匹配的特征点进行剔除,进而实现无人机影像的无缝拼接。首先,基于Harris算法提取兴趣点,利用最短欧式距离进行特征匹配;然后,利用RANSAC算法实现对特征点的精确匹配;最后,利用RANSAC算法得到的单应性矩阵完成无人机影像拼接。实验结果表明:本文方法能够较好地剔除无人机影像拼接时误匹配的特征点,实现对无人机影像的拼接,拼接效果良好。Harris algorithm, which is used for the mismatched problems, can stitch feature points in image from UAV. We can remove the mistaken matched feature points using the RANSAC algorithm, thus achieving seamless UAV images. First of all, we can use the shortest Euclidean distance feature to extract points of interest which is based on Harris algorithm. Then RANSAC algorithm is used to achieve an exact match for the feature points; finally, homography is obtained by using RANSAC algorithm to complete UAV image stitching. The experimental results show that the method is well for eliminating false matching feature points and it has a good result for UAV image stitching.

关 键 词：无人机影像 图像拼接 HARRIS算法 RANSAC算法 

分 类 号：P231.4[天文地球—摄影测量与遥感]