ABSTRACT

Feature-based image registration requires the identification of correct tie-points between the image pair. In this paper, an improved outlier method is proposed to find correct matching results of optimal distribution based on RANSAC (RANdom SAmple Consensus) algorithm. The main feature of the proposed method is that an optimal spatial designation of tie-points method using stratified random selection (SRS), is integrated into RANSAC framework to filter out the mismatched features that exist in the massive initial matches generated by SIFT operator in order to estimate mapping function accurately. In this way, the selection of relatively disperse and evenly distributed tie-points based on adaptive stratified partition can make RANSAC efficient. We carried out experiments on the registration of three pairs of satellite images. The proposed SIFT-SRS-RANSAC method leads to higher matching and registration accuracy when comparing with the performance of SIFT-RANSAC and SIFT-bucketing-RANSAC algorithms.

摘要

基于特征的图像配准需要识别图像对之间的正确联系点。本文提出一种改进的离群值方法，以基于RANSAC（随机抽样共识）算法寻找最优分布的正确匹配结果。该方法的主要特点是将使用分层随机选择（SRS）的联系点方法的最佳空间指定集成到RANSAC框架中，以按顺序过滤出SIFT运算符生成的大量初始匹配中存在的不匹配特征。准确估计映射功能。这样，基于自适应分层分区选择相对分散且分布均匀的联系点可以提高RANSAC的效率。我们进行了三对卫星图像配准的实验。