Title :
Robust geometric registration of overlapping range images
Author_Institution :
Dept. of Comput. Sci., Univ. of Wales, Aberystwyth, UK
Abstract :
In this paper, we propose a novel algorithm to evaluate the possible point matches established by the traditional ICP algorithm in the process of registering two overlapping range images represented as two sets of unorganised points. While the existing methods mainly use feature matching to establish or evaluate possible correspondences between the images to be registered, our novel approach applies motion consistency constraints to evaluate the possible correspondences. In order to accelerate the search for the closest points from the transformed first image points to the second image points, the optimised K-D tree data structure is employed. A comparative study based on real images has shown that the proposed algorithm is accurate, robust and efficient for the automatic registration of overlapping range images.
Keywords :
image matching; image motion analysis; image registration; tree data structures; iterative closest point; motion consistency constraints; overlapping range images; point matches; robust geometric registration; tree data structure; Cameras; Computer science; Feature extraction; Image analysis; Iterative closest point algorithm; Machine vision; Optical scattering; Robot kinematics; Robot vision systems; Robustness;
Conference_Titel :
Industrial Electronics Society, 2003. IECON '03. The 29th Annual Conference of the IEEE
Print_ISBN :
0-7803-7906-3
DOI :
10.1109/IECON.2003.1280637