Self-adaptive optical image registration based on optimized analysis of feature points

详细信息    查看全文 | 下载全文 | 推荐本文 |

• 作者：Shi YueZhang Daobing
• 会议时间：2013-12-01
• 关键词：Image Registration ; Scale Invariant Feature Transform (SIFT) ; Self-adaptive ; keypoint refinement
• 作者单位：Shi Yue(Institute of Electronic,Chinese Academy of Sciences,Beijing 100190,China)Zhang Daobing(Key Laboratory of Spatial Information Processing and Application System Technology,Chinese Academy of Sciences,Beijing 100190,China)
• 母体文献：第二届高分辨率对地观测学术年会论文集
• 会议名称：第二届高分辨率对地观测学术年会
• 会议地点：北京
• 主办单位：中国宇航学会
• 语种：chi

摘要

Image registration is an important preprocessing step for image processing such as change detection,image mosaicking in remote sensing,however a crucial problem involved feature-based image registration is how to reliably establish correspondent features between sensed image and reference image.This paper presents an automatic self-adaptive image registration method based on analytic energy of control points to improve the traditional algorithm.Firstly,an multi-scale segment method based on digital curvelet transform is used to evaluate the quality difference of image pairs,and then self-adaptive parameters of SIFT feature-matching algorithm based on multi-scale grey relation of image quality is proposed to increase the feature points and correspondences; At last,to make sure the accuracy of geometrical transform parameters,a method of correspondences selection based on the distribution and matching energy of control points is developed.Experimental results demonstrate that the proposed method works well in increasing control points and the correspondences of low quality remote sensing images.