图像非刚体匹配的多模型估计算法设计与实现

Design and Implementation of Multimodel Estimation Algorithm for Nonrigid Matching Images

针对非刚体匹配图像的外点去除问题,提出了一种多匹配模型估计方法。首先,考虑到匹配点集合中可能存在高外点率,用基于近邻内点分布的一致性对匹配点集合的内点率进行提升;然后,为了降低内点距离误差阈值对内点提取的影响,用内点距离误差边缘化进行多模型估计;最后,考虑到提取的内点集合中可能残留部分外点,用基于匹配点位置变化矢量方向的一致性对残留外点进行去除。实验中,所提方法与MAGSAC、NM-NET、P-NAPSAC、SC-RANSAC、Adalam、OANET、SuperGlue、PEARL、Multi-H、Multi-X以及CONSAC等方法进行对比,结果表明所提方法的内点距离误差可降低30%以上,外点残留率可降低50%以上,内点召回率可提高8%以上,运行时间可降低10%以上,多平面估计的错分率可降低16%以上。

An algorithm of multimatching model estimation is proposed for the problem of outliers removed from nonrigid matching images. First, considering the high probability of outlier ratio in the matched point set, the inlier ratio promotion based on the consensus of the distribution of neighbor inliers was applied. Second, to reduce the influence of the inlier distance error threshold on the inlier extraction, a multimodel estimation was applied using the inlier distance error marginalization. Finally, considering the probability of residual outliers in the extracted inlier set,residual outliers were removed based on the consensus of the direction of the matching point position change vector. In the experiments, the proposed method is compared with MAGSAC, NM-NET, P-NAPSAC, SC-RANSAC,Adalam, OANET, SuperGlue, PEARL, Multi-H, Multi-X, and CONSAC, etc. Results indicate over 30%reduction in the inlier distance error, 50% reduction in the outlier residual rate, 8% increase in the recall of inlier, 10%reduction in the running time, and 16% reduction in the misclassification rate of multiplanar estimation.