GPU-boosted online image matching

Alexandre Chariot (1, 2, 3) , Renaud Keriven (2)

1 CERTIS - Centre d'Enseignement et de Recherche en Technologies de l'Information et Systèmes
2 imagine [Marne-la-Vallée]
3 LIGM - Laboratoire d'Informatique Gaspard-Monge

Matching feature points between images is a key point in many Computer Vision tasks. As the number of images increases, this rapidly becomes a bottleneck. We here present how to use the power of GPUs to obtain image matching in typically 20 ms for one thousand points. This speedup makes applications like interactive image matching possible. Such a portable system, dedicated to 3D large scale reconstruction, is reported.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Alexandre Chariot, Renaud Keriven. GPU-boosted online image matching. ICPR, Dec 2008, Tampa, United States. pp.1-4. ⟨hal-00835096⟩