Extended Neighborhood Consensus With Affine Correspondence for Outlier Filtering in Feature Matching

Verifying the neighborhood consensus to remove false correspondence is a popular idea in feature matching. However, traditional neighborhood consensus only considers spatial neighborhoods (SNs), which is not robust in challenging remote sensing tasks. This article extends the traditional neighborhood consensus for improving robustness to the two key issues-significant geometric transformation and repetitive patterns. First, we introduce a novel matching neighborhood (MN) that extends the one-to-one correspondence in traditional neighborhood consensus to one-to-multiple structure to address the repetitive patterns, where one-to-multiple means that multiple matching candidates are preserved in calculating descriptor similarity. Second, the traditional SN is also extended using affine correspondence, which can adaptively address the significant geometric transformations without multiscale processing. On the two bases, we construct a novel extended neighborhood (EN) by combining the extended SN with the MN. Consequently, the false feature correspondences are filtered by measuring the consensus between the ENs. Numerous experiments demonstrate that the proposed method is state-of-the-art (SOTA) in comparison with recent learning and traditional methods, especially for the UAV localization task. We also show that the proposed method is robust to the basic settings, such as the prefiltering threshold and the type of local features.