6DOF Point Cloud Alignment Using Geometric Algebra-Based Adaptive Filtering
Abstract
In this paper we show that a Geometric Algebra-based least-mean-squares adaptive filter (GA-LMS) can be used to recover the 6-degree-of-freedom alignment of two point clouds related by a set of point correspondences. We present a series of techniques that endow the GA-LMS with outlier (false correspondence) resilience to outperform standard least squares (LS) methods that are based on Singular Value Decomposition (SVD). We furthermore show how to derive and compute the step size of the GA-LMS.
Cite
Text
Al-Nuaimi et al. "6DOF Point Cloud Alignment Using Geometric Algebra-Based Adaptive Filtering." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477642Markdown
[Al-Nuaimi et al. "6DOF Point Cloud Alignment Using Geometric Algebra-Based Adaptive Filtering." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/alnuaimi2016wacv-dof/) doi:10.1109/WACV.2016.7477642BibTeX
@inproceedings{alnuaimi2016wacv-dof,
title = {{6DOF Point Cloud Alignment Using Geometric Algebra-Based Adaptive Filtering}},
author = {Al-Nuaimi, Anas and Steinbach, Eckehard G. and Lopes, Wilder Bezerra and Lopes, Cássio Guimarães},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2016},
pages = {1-9},
doi = {10.1109/WACV.2016.7477642},
url = {https://mlanthology.org/wacv/2016/alnuaimi2016wacv-dof/}
}