Advanced

Point Track Creation in Unordered Image Collections Using Gomory-Hu Trees

Svärm, Linus LU ; Simayijiang, Zhayida LU ; Enqvist, Olof LU and Olsson, Carl LU (2012) 21st International Conference on Pattern Recognition Applications and Methods (IPCRAM 2012) In Pattern Recognition (ICPR) 2012 21st International Conference on p.2116-2119
Abstract
Geometric reconstruction from image collections is a classical computer vision problem. The problem essentially consists of two steps; First, the identification of matches and assembling of point tracks, and second, multiple view geometry computations. In this paper we address the problem of constructing point tracks using graph theoretical algorithms. From standard descriptor matches between all pairs of images we construct a graph representing all image points and all possible matches. Using Gomory-Hu trees we make cuts in the graph to construct the individual point tracks. We present both theoretical and experimental results (on real datasets) that clearly demonstrates the benefits of using our approach.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
computer vision, structure from motion, Gomory-Hu trees
in
Pattern Recognition (ICPR) 2012 21st International Conference on
pages
4 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
21st International Conference on Pattern Recognition Applications and Methods (IPCRAM 2012)
external identifiers
  • Scopus:84874556132
ISBN
978-1-4673-2216-4 (print)
language
English
LU publication?
yes
id
09e973d8-9cd4-4366-a85b-d294799b5ca9 (old id 3327304)
alternative location
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6460579&tag=1
date added to LUP
2013-03-22 19:45:34
date last changed
2016-10-13 04:39:18
@misc{09e973d8-9cd4-4366-a85b-d294799b5ca9,
  abstract     = {Geometric reconstruction from image collections is a classical computer vision problem. The problem essentially consists of two steps; First, the identification of matches and assembling of point tracks, and second, multiple view geometry computations. In this paper we address the problem of constructing point tracks using graph theoretical algorithms. From standard descriptor matches between all pairs of images we construct a graph representing all image points and all possible matches. Using Gomory-Hu trees we make cuts in the graph to construct the individual point tracks. We present both theoretical and experimental results (on real datasets) that clearly demonstrates the benefits of using our approach.},
  author       = {Svärm, Linus and Simayijiang, Zhayida and Enqvist, Olof and Olsson, Carl},
  isbn         = {978-1-4673-2216-4 (print)},
  keyword      = {computer vision,structure from motion,Gomory-Hu trees},
  language     = {eng},
  pages        = {2116--2119},
  publisher    = {ARRAY(0x7e135f0)},
  series       = {Pattern Recognition (ICPR) 2012 21st International Conference on},
  title        = {Point Track Creation in Unordered Image Collections Using Gomory-Hu Trees},
  year         = {2012},
}