Point Cloud Registration Based on Consistency Evaluation of Rigid Transformation in Parameter Space

TL;DR

This paper introduces a highly accurate and stable point cloud registration method that evaluates the consistency of rigid transformations using triplets and histograms, outperforming existing methods.

Contribution

The proposed method uniquely combines keypoint detection, triplet generation with multiple descriptors, and histogram-based consistency evaluation for improved registration accuracy.

Findings

Minimal registration errors achieved

No major failures in experiments

Outperforms comparative methods in accuracy and stability

Abstract

We can use a method called registration to integrate some point clouds that represent the shape of the real world. In this paper, we propose highly accurate and stable registration method. Our method detects keypoints from point clouds and generates triplets using multiple descriptors. Furthermore, our method evaluates the consistency of rigid transformation parameters of each triplet with histograms and obtains the rigid transformation between the point clouds. In the experiment of this paper, our method had minimul errors and no major failures. As a result, we obtained sufficiently accurate and stable registration results compared to the comparative methods.