3D Reconstruction of Large Point Clouds with a New Point Correspondence Algorithm

Abstract

The objective of this work is to perform the 3D reconstruction combining cloud points obtained from different viewpoints using structured light. The point cloud is simplified to reduce the computational time. The main task is the point cloud registration algorithm that matches two point clouds. A well known algorithm for point cloud registration is the ICP that determines the rotation and translation that when applied to one of the point clouds, place both point clouds in accordance. The ICP algorithm executes iteratively two main steps: point correspondence determination and registration algorithm. The point correspondence determination is a module that if not executed properly can make the ICP to converge to a local minimum. To overcome such drawback, it is proposed in this work an ICP that uses statistics to generate a dynamic distance threshold on the distance allowed between closest points. Instead of matching all points from the data set, this technique matches subset-subset points.

Shape reconstruction from multiple RGB-D point cloud registration

“…This work improves the research from Takimoto et al [6], [7] by modifying the color information usage. They used the color information to calculate the error in the point correspondence (color and geometric information).…”

“…The proposed methods [3]- [5] presented results with two point clouds. Takimoto et al [6], [7] proposed an ICP that uses color information to improve point correspondence and point cloud registration. The color is used in the error calculation.…”

3D Reconstruction Using Low Precision Scanner

“…As previously said, the ICP has two main steps: transformation and point correspondence determination. The transformation T (see equation 1) is determined using quaternions (Takimoto et al, 2012b). The point correspondence is a key in the evaluation of how near is the global optimum.…”