Webbläsaren som du använder stöds inte av denna webbplats. Alla versioner av Internet Explorer stöds inte längre, av oss eller Microsoft (läs mer här: * https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Var god och använd en modern webbläsare för att ta del av denna webbplats, som t.ex. nyaste versioner av Edge, Chrome, Firefox eller Safari osv.

Stable Structure from Motion for Unordered Image Collections

Författare

Redaktör

  • Heyden Anders
  • Kahl Fredrik

Summary, in English

We present a non-incremental approach to structure from motion. Our solution is based on robustly computing global rotations from relative geometries and feeding these into the known-rotation framework to create an initial solution for bundle adjustment. To increase robustness we present a new method for constructing reliable point tracks from pairwise matches. We show that our method can be seen as maximizing the reliability of a point track if the quality of the weakest link in the track is used to evaluate reliability. To estimate the final geometry we alternate between bundle adjustment and a robust version of the known-rotation formulation. The ability to compute both structure and camera translations independent of initialization makes our algorithm insensitive to degenerate epipolar geometries. We demonstrate the performance of our system on a number of image collections.

Publiceringsår

2011

Språk

Engelska

Sidor

524-535

Publikation/Tidskrift/Serie

Lecture Notes in Computer Science (Image Analysis : 17th Scandinavian Conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings)

Volym

6688

Dokumenttyp

Konferensbidrag

Förlag

Springer

Ämne

  • Computer Vision and Robotics (Autonomous Systems)
  • Mathematics

Nyckelord

  • Structure from motion
  • computer vision

Conference name

17th Scandinavian Conference on Image Analysis (SCIA 2011)

Conference date

2011-05-23 - 2011-05-27

Conference place

Ystad, Sweden

Status

Published

Forskningsgrupp

  • Mathematical Imaging Group

ISBN/ISSN/Övrigt

  • ISSN: 0302-9743
  • ISSN: 1611-3349
  • ISBN: 978-3-642-21226-0 (print)
  • ISBN: 978-3-642-21227-7 (online)