SIFT Detectors for Matching Aerial Images in Reduced Space

In this paper we propose a novel approach for matching cartographic images over detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: Interest points extracted with the SIFT detector which is adapted to affine transformations and give repeatable results (geometrically stable). This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. The characteristic scale and the affine shape of neighbourhood determine an affine invariant region for each point. We apply an unsupervised classification to reduce the space of sets of interest points by using weighted bipartite graph matching in solving the point correspondence. Diffusion map: projection of the bipartite graph in a reduce space on which we apply K-means to classify the representatives clusters. The performance of our approach detector is also confirmed by excellent matching results.