Wide-baseline stereo matching with line segments

We present a new method for matching line segments between two uncalibrated wide-baseline images. Most current techniques for wide-baseline matching are based on viewpoint invariant regions. Those methods work well with highly textured scenes, but fail with poorly textured ones. We show that such sc...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 329 - 336 vol. 1
Main Authors Bay, H., Ferraris, V., Van Gool, L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Computer vision
Constitution
Geometry
Histograms
Image segmentation
Laboratories
Layout
Robustness
Stereo vision
Transmission line matrix methods
Online AccessGet full text

Cover

More Information
Summary:We present a new method for matching line segments between two uncalibrated wide-baseline images. Most current techniques for wide-baseline matching are based on viewpoint invariant regions. Those methods work well with highly textured scenes, but fail with poorly textured ones. We show that such scenes can be successfully matched using line segments. Moreover, since line segments and regions provide complementary information, their combined matching allows to deal with a broader range of scenes. We generate an initial set of line segment correspondences, and then iteratively increase their number by adding matches consistent with the topological structure of the current ones. Finally, a coplanar grouping stage allows to estimate the fundamental matrix even from line segments only.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.375