Alignment of three-dimensional point clouds using combined descriptors

This paper presents a new methodology for aligning three-dimensional (3D) models of objects, based on point correspondences. In this case, objects are modelled as 3D point clouds. The proposed methodology considers pairs of such point clouds and firstly down-samples them in order to further improve processing time. Then, corresponding points are allocated between the processed point clouds, by using a novel combinational descriptor scheme. Finally, a global transformation is estimated from the inliers of the obtained correspondences. This transformation is used to align the two point clouds. The proposed methodology was applied to five pairs of large scale 3D point clouds. Results indicate that the proposed scheme achieved satisfactory alignment accuracy for all tested data pairs.