Uporaba lokalnih značilnic v aplikacijah spoznavnega vida za urbana okolja (Local features in cognitive vision applications for urban environments)

In this paper we present a performance evaluation of MSER and Hessian-Affine local feature detectors in a typical use case of cognitive vision applications in urban environments. By using a wide baseline stereo matching approach we try to find camera motion between a user image and images stored in a database. Running this application on test images twice while only changing the underlying local feature type has shown that the MSER local feature detector outperforms the Hessian-Affine detector. Additionally, we have shown that local features can perform well in cognitive vision applications for urban environments.