基于特征匹配的亚像素级全景图像配准算法  

Sub-pixel image registration algorithm in image panoramic mosaic

作　　者：王丙勤[1] 郭立[1] 郑迈[1] 

机构地区：[1]中国科学技术大学电子科学与技术系,合肥230027

出　　处：《计算机工程与应用》2008年第17期191-194,200,共5页Computer Engineering and Applications

摘　　要：为了提高全景图全自动拼接中图像配准的速度和匹配稳健性,提出了一种基于相对距离法去除外点的亚像素级图像配准算法,并给出了分析和实验结果,亚像素级像素定位误差在0.01～0.1之内。在对12组图像匹配的实验结果表明,该匹配算法的匹配正确率达到100%,且匹配的时间小于目前通用的RANSAC匹配算法。In order to improve the image registration speed and the matching stability,a sub-pixel image registration algorithm based on comparative distance is presented.And also,theoretical deduction and the result of experiments are given.And it has been proved that the algorithm has sub-pixel accuracy,and the precision is between 0.01 and 0.1.The results of matching experiment for 12 couples images have indicated the matching accuracy of presented algorithm has achieved 100%,and the time consumed is less than the RANSAC algorithm which is in common used in present.

关 键 词：HARRIS CORNER Detector 相互关系算法 特征匹配 全景图 亚像素 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]