Image Registration Based on KLT Features for UAV Platform

摘要：

Image registration technology is great significant in he virtual scene,automatic navigation,computer science,remote sensing image processing and many other aspect. It takes lots of difficulties for video tracking that the UAV platform are always unstable. In this paper,we use improved KLT algorithm to feature extraction,and use distance constraint to speed up matching,then apply the RANSAC to precise matching,and finally get the affine transform parameters. The experiment results are very well,and can solve the problem of UAV camera shake.

关键词： component KLT UAV Image Registration Feature point

作者: Wen Gao Ming Zhu

作者单位: Changchun Institute of Optics,Fine Mechanics and Physics Chinese Academy of Sciences,Changchun,China Changchun Institute of Optics,Fine Mechanics and Physics Chinese Academy of Sciences,Changchun,China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 1078-1081

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）