Point Cloud Registration Based on Consistency Evaluation of Rigid Transformation in Parameter Space
This work addresses the problem of accurately and stably integrating 3D point clouds for applications like robotics or computer vision, but it appears incremental as it builds on existing registration techniques.
The paper tackles point cloud registration by detecting keypoints, generating triplets with multiple descriptors, and evaluating rigid transformation consistency using histograms, resulting in minimal errors and no major failures compared to existing methods.
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.