Stable Structure from Motion for Unordered Image Collections
(2011) 17th Scandinavian Conference on Image Analysis (SCIA 2011) 6688. p.524-535- Abstract
- 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... (More)
- 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3327363
- author
- Olsson, Carl LU and Enqvist, Olof LU
- organization
- publishing date
- 2011
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Structure from motion, computer vision
- host publication
- Lecture Notes in Computer Science (Image Analysis : 17th Scandinavian Conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings)
- editor
- Anders, Heyden and Fredrik, Kahl
- volume
- 6688
- pages
- 12 pages
- publisher
- Springer
- conference name
- 17th Scandinavian Conference on Image Analysis (SCIA 2011)
- conference location
- Ystad, Sweden
- conference dates
- 2011-05-23 - 2011-05-27
- external identifiers
-
- wos:000308543900049
- scopus:79957476352
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 978-3-642-21226-0 (print)
- 978-3-642-21227-7 (online)
- DOI
- 10.1007/978-3-642-21227-7_49
- language
- English
- LU publication?
- yes
- id
- 570b6496-ae56-4542-84f1-93253b72a346 (old id 3327363)
- date added to LUP
- 2016-04-01 10:50:17
- date last changed
- 2024-08-12 07:18:35
@inproceedings{570b6496-ae56-4542-84f1-93253b72a346, abstract = {{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.}}, author = {{Olsson, Carl and Enqvist, Olof}}, booktitle = {{Lecture Notes in Computer Science (Image Analysis : 17th Scandinavian Conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings)}}, editor = {{Anders, Heyden and Fredrik, Kahl}}, isbn = {{978-3-642-21226-0 (print)}}, issn = {{0302-9743}}, keywords = {{Structure from motion; computer vision}}, language = {{eng}}, pages = {{524--535}}, publisher = {{Springer}}, title = {{Stable Structure from Motion for Unordered Image Collections}}, url = {{http://dx.doi.org/10.1007/978-3-642-21227-7_49}}, doi = {{10.1007/978-3-642-21227-7_49}}, volume = {{6688}}, year = {{2011}}, }