Robust geometric registration of overlapping range images

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.