An approach to robust ICP initialization

Autor:	Kolpakov, Alexander, Werman, Michael
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Computational Geometry Mathematics - Optimization and Control
Druh dokumentu:	Working Paper
DOI:	10.1109/TPAMI.2023.3287468
Popis:	In this note, we propose an approach to initialize the Iterative Closest Point (ICP) algorithm to match unlabelled point clouds related by rigid transformations. The method is based on matching the ellipsoids defined by the points' covariance matrices and then testing the various principal half-axes matchings that differ by elements of a finite reflection group. We derive bounds on the robustness of our approach to noise and numerical experiments confirm our theoretical findings. Comment: 9 pages, 18 figures, 1 table; GitHub repository at (https://github.com/sashakolpakov/icp-init)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.05332 Zobrazit plný text záznamu View this record from Arxiv