CoBigICP: Robust and Precise Point Set Registration using Correntropy Metrics and Bidirectional Correspondence
Pengyu Yin, Di Wang, Shaoyi Du, Shihui Ying, Yue Gao, Nanning Zheng
Abstract
In this paper, we propose a novel probabilistic variant of iterative closest point (ICP) dubbed as CoBigICP. The method leverages both local geometrical information and global noise characteristics. Locally, the 3D structure of both target and source clouds are incorporated into the objective function through bidirectional correspondence. Globally, error metric of correntropy is introduced as noise model to resist outliers. Importantly, the close resemblance between normal-distributions transform (NDT) and correntropy is revealed. To ease the minimization step, an on-manifold parameterization of the special Euclidean group is proposed. Extensive experiments validate that CoBigICP outperforms several well-known and state-of-the-art methods.
BibTeX
@inproceedings{iros2020_cobigicprobustan,
title = {CoBigICP: Robust and Precise Point Set Registration using Correntropy Metrics and Bidirectional Correspondence},
author = {Pengyu Yin and Di Wang and Shaoyi Du and Shihui Ying and Yue Gao and Nanning Zheng},
booktitle = {IROS 2020},
year = {2020}
}