计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (17): 191-194.

• 图形、图像、模式识别 • 上一篇    下一篇

基于特征匹配的亚像素级全景图像配准算法

王丙勤,郭 立,郑 迈   

  1. 中国科学技术大学 电子科学与技术系,合肥 230027
  • 收稿日期:2007-09-14 修回日期:2007-12-05 出版日期:2008-06-11 发布日期:2008-06-11
  • 通讯作者: 王丙勤

Sub-pixel image registration algorithm in image panoramic mosaic

WANG Bing-qin,GUO Li,ZHENG Mai   

  1. Department of Electronic Science and Technology,University of Science and Technology of China,Hefei 230027,China
  • Received:2007-09-14 Revised:2007-12-05 Online:2008-06-11 Published:2008-06-11
  • Contact: WANG Bing-qin

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。

Abstract: 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.