基于标记点的图像特征匹配的鲁棒算法

Robust Algorithm for Image Feature Matching Based on Reference Points

提出了基于标记点的图像特征匹配的鲁棒算法,该算法采用编码点和非编码点等标记点的方式。与已有方法相比较,该方法有两个主要特点:①首先用编码点的ID进行两幅图像间编码点的对应匹配,然后从已匹配的编码点开始,进行非编码点的匹配;②采用标记点的亚像素定位方法,提高了三维重建精度。实验结果表明,该算法既有非常高的正确匹配率,又有很高的三维重建精度。

This paper present an automatic matching algorithm for image feature based on reference points. This method used the non--coded points and the coded points. The coded points matched easily were utilized for determination of distance relation between primitives. The non--coded points were utilized for 3--D point reconstruction. Compared to previous methods, the novelties of the proposed method are as follows. Firstly, while it is difficult to blind search within two images for corresponding points, it will be easier to start from an already matched pair. To facilitate this, the coded points with- in two images were matched by using their IDs, and then the matching process of the non--coded points within two images is performed based on the matching results of the coded points. Secondly, the 3--D reconstruction precision is remarkably increased since the method of subpixel reference point center location was utilized. The experimental results show that the proposed algorithm can acquire both very high ratio of correct match and very high precision of 3--D reconstruction.