基于SIFT特征匹配的图像拼接算法  

Algorithm of Image Stitching Based on SIFT Feature Matching

作　　者：李云霞[1] 曾毅[1] 钟瑞艳[1] 郭涛[1] 

机构地区：[1]山东大学控制科学与工程学院,山东济南250061

出　　处：《计算机技术与发展》2009年第1期43-45,52,共4页Computer Technology and Development

基　　金：国家863计划重点项目(2006AA040206)

摘　　要：基于SIFT特征匹配思想,提出一种快速、准确的图像拼接算法。SIFT特征匹配算法是目前国内外特征点匹配研究领域的热点与难点,其匹配能力较强,可以处理两幅图像之间发生平移、旋转、仿射变换情况下的匹配问题,甚至在某种程度上对任意角度拍摄的图像也具备较为稳定的特征匹配能力。在这一匹配思想的基础上结合多分辨率样条提出一种新的图像拼接算法,它采用多分辨率样条来确定拼接区域宽度和加权函数,使图像在不同分辨率下分别拼合,这样使拼合出的图像既清晰又光滑无缝。算法在大多数情况下能自动完成,实验结果证明该方法提高了拼接速度,降低了图像亮度差异的影响,使结果图像自然逼真。A fast and accurate image stitching algorithm based on SIFT feature matching is proposed. SIFT feature matching algorithm is hot and difficult in the field of matching feature points research at home and abroad. Its match ability is strong, and can be dealt with translation, rotation, affine transformation circumstances matching problem between the two images. To some extent, images also have a more stable feature matching capacity even in the perspective of arbitrary capture. In this paper, a new image stitching algorithm is proposed on the basis of this match thinking and multi - resolution spline. It uses multi - resolution spline to determine the width and splicing regional weighting function, so that images are blended at different resolutions, thus the blended - image is dear and smooth seamless. Algorithm in most cases can be automatically completed, the experimental results show that it improves the stitching speed and reduces the difference of image brightness. It makes the blended- image natural and realistic.

关 键 词：SIFT特征匹配 图像拼接 多分辨率融合RANSAC算法 L—M算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]