基于SURF和改进配准的图像拼接算法

Image Stitching Based on SURF and Improved Registration

图像拼接算法中拼接效果和效率是该研究领域的两个重要问题。针对图像拼接中拼接效率低的问题,提出一种固定相机平台下,基于SURF和改进配准的图像拼接算法。该算法首先使用SURF算法提取待拼接图像重叠区域特征点,对重叠区域进行分块,对应块之间进行特征点匹配;利用单应性变换模型计算出图像之间的几何变换关系。融合阶段采用加权融合算法拼接配准后的图像。实验表明该算法提高拼接效率的同时,还有着良好的拼接效果。

The stitching effect and efficiency in the image stitching algorithm are two important issues in this research field.Aiming at the problem of low stitching efficiency in image stitching,proposes an image stitching algorithm based on surf and improved registration under a fixed cam⁃era platform.Firstly,the SURF algorithm is used to extract the feature points of the overlapping regions of the image to be stitched,and the overlapping regions are segmented,and the feature points are matched between the corresponding blocks.The homography transformation model is used to calculate the geometric transformation relationship between the images.The stitching phase uses a weighted algorithm to stitch the image after registration The experiment shows that the algorithm improves the stitching efficiency and has a good stitching effect.