Optimal relative pose with unknown correspondences

Fredriksson, JohanLund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Lund University Research Groups (författare)

Previous work on estimating the epipolar geometry of two views relies on being able to reliably match feature points based on appearance. In this paper, we go one step further and show that it is feasible to compute both the epipolar geometry and the correspondences at the same time based on geometry only. We do this in a globally optimal manner. Our approach is based on an efficient branch and bound technique in combination with bipartite matching to solve the correspondence problem. We rely on several recent works to obtain good bounding functions to battle the combinatorial explosion of possible matchings. It is experimentally demonstrated that more difficult cases can be handled and that more inlier correspondences can be obtained by being less restrictive in the matching phase.

Larsson, ViktorLund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Lund University Research Groups(Swepub:lu)vi4846la (författare)
Olsson, CarlLund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Lund University Research Groups(Swepub:lu)math-coo (författare)
Kahl, Fredrik,1972Chalmers University of Technology,Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Lund University Research Groups(Swepub:lu)math-fka (författare)
Mathematical Imaging GroupForskargrupper vid Lunds universitet (creator_code:org_t)

Ingår i:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition2016-January, s. 1728-17361063-69199781467388511

Av författaren/redakt...: Fredriksson, Joh ...; Larsson, Viktor; Olsson, Carl; Kahl, Fredrik, 1 ...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorseende och ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.