by Attila Tanács, András Majdik, József Molnár, Atul Rai, Zoltan Kato
Abstract:
Finding correspondences between image pairs is a fundamental task in computer vision. Herein, we focus on establishing matches between images of urban scenes which are typically composed of planar surface patches with highly repetitive structures. The latter property makes traditional point-based methods unreliable. The basic idea of our approach is to formulate the correspondence problem in terms of homography estimation between planar image regions: given a planar region in one image, we are simultaneously looking for its corresponding segmentation in the other image and the planar homography acting between the two regions. We will show, that due to the overlapping views the general 8 degree of freedom (DOF) of the homography mapping can be geometrically constrained to 3 DOF and the resulting segmentation/registration problem can be efficiently solved by finding the region's occurrence in the second image using pyramid representation and normalized mutual information as the intensity similarity measure. The method has been validated on a large database of building images taken by different mobile cameras and quantitative evaluation confirms robustness against intensity variations, occlusions or the presence of non-planar parts. We also show examples of 3D planar surface reconstruction as well as 2D mosaicking.
Reference:
Attila Tanács, András Majdik, József Molnár, Atul Rai, Zoltan Kato, Establishing Correspondences between Planar Image Patches, In Proceedings of International Conference on Digital Image Computing: Techniques and Applications, Wollongong, New South Wales, Australia, pp. 1-7, 2014, IEEE. (Best Paper Award)
Bibtex Entry:
@string{dicta="Proceedings of International Conference on Digital Image Computing: Techniques and Applications"}
@INPROCEEDINGS{Tanacs-etal2014b,
author = {Attila Tan\'{a}cs and Andr\'as Majdik and J\'ozsef
Moln\'ar and Atul Rai and Zoltan Kato},
title = {Establishing Correspondences between Planar Image
Patches},
booktitle = dicta,
year = 2014,
address = {Wollongong, New South Wales, Australia},
month = nov,
pages = {1-7},
publisher = {IEEE},
note = {Best Paper Award},
abstract = {Finding correspondences between image pairs is a
fundamental task in computer vision. Herein, we
focus on establishing matches between images of
urban scenes which are typically composed of planar
surface patches with highly repetitive
structures. The latter property makes traditional
point-based methods unreliable. The basic idea of
our approach is to formulate the correspondence
problem in terms of homography estimation between
planar image regions: given a planar region in one
image, we are simultaneously looking for its
corresponding segmentation in the other image and
the planar homography acting between the two
regions. We will show, that due to the overlapping
views the general 8 degree of freedom (DOF) of the
homography mapping can be geometrically constrained
to 3 DOF and the resulting segmentation/registration
problem can be efficiently solved by finding the
region's occurrence in the second image using
pyramid representation and normalized mutual
information as the intensity similarity measure. The
method has been validated on a large database of
building images taken by different mobile cameras
and quantitative evaluation confirms robustness
against intensity variations, occlusions or the
presence of non-planar parts. We also show examples
of 3D planar surface reconstruction as well as 2D
mosaicking.}
}