DocumentCode :
595146
Title :
Point track creation in unordered image collections using Gomory-Hu trees
Author :
Svarm, Linus ; Simayijiang, Zhayida ; Enqvist, Olof ; Olsson, Carl
Author_Institution :
Centre for Math. Sci., Lund Univ., Lund, Sweden
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
2116
Lastpage :
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.
Keywords :
computational geometry; computer vision; image matching; image reconstruction; trees (mathematics); Gomory-Hu trees; computer vision problem; geometric reconstruction; graph representation; graph theoretical algorithm; multiple view geometry computation; point track assembling; point track creation; point track match identification; standard descriptor matches; unordered image collections; Cameras; Computer vision; Geometry; Image edge detection; Image reconstruction; Joining processes; Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460579
Link To Document :
بازگشت