Robust feature matching and selection methods for multisensor image registration

The crucial problem of multisensor image registration is how to establish the correspondences between the features extracted from reference and input images. Generally, most existing methods only consider how to extract features, the quality of the features is ignored. In this paper, we combine scale invariant feature transform (SIFT) and maximally stable extremal region (MSER) to initialize the process of extracting plenty of control points(CPs) pairs. A concept of distribution quality(DQ) is introduced to quantify the distribution of CPs pairs, experimental analysis is illustrated to analyze the effects of CPs pairs number and DQ on the registration root mean square error(RMSE). An automatic feature matching and selection algorithm is then proposed, extensive experiments demonstrate the effectiveness of the proposed algorithm by aligning real images.