Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/105616
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Fast rotation search with stereographic projections for 3D registration |
Author: | Parra Bustos, A. Chin, T. Eriksson, A. Li, H. Suter, D. |
Citation: | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 38(11):2227-2240 |
Publisher: | IEEE Computer Society |
Issue Date: | 2016 |
ISSN: | 0162-8828 1939-3539 |
Statement of Responsibility: | Alvaro Parra Bustos, Tat-Jun Chin, Anders Eriksson, Hongdong Li and David Suter |
Abstract: | Registering two 3D point clouds involves estimating the rigid transform that brings the two point clouds into alignment. Recently there has been a surge of interest in using branch-and-bound (BnB) optimisation for point cloud registration. While BnB guarantees globally optimal solutions, it is usually too slow to be practical. A fundamental source of difficulty lies in the search for the rotational parameters. In this work, first by assuming that the translation is known, we focus on constructing a fast rotation search algorithm. With respect to an inherently robust geometric matching criterion, we propose a novel bounding function for BnB that is provably tighter than previously proposed bounds. Further, we also propose a fast algorithm to evaluate our bounding function. Our idea is based on using stereographic projections to precompute and index all possible point matches in spatial R-trees for rapid evaluations. The result is a fast and globally optimal rotation search algorithm. To conduct full 3D registration, we co-optimise the translation by embedding our rotation search kernel in a nested BnB algorithm. Since the inner rotation search is very efficient, the overall 6DOF optimisation is speeded up significantly without losing global optimality. On various challenging point clouds, including those taken out of lab settings, our approach demonstrates superior efficiency. |
Keywords: | Point cloud registration; rotation search; branch-and-bound; stereographic projections; R-trees; three-dimensional displays; optimization; transforms; iterative closest point algorithm; robustness; kernel; search problems |
Rights: | © 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. |
DOI: | 10.1109/TPAMI.2016.2517636 |
Grant ID: | http://purl.org/au-research/grants/arc/DP130102524 http://purl.org/au-research/grants/arc/DE130101775 http://purl.org/au-research/grants/arc/DP120103896 http://purl.org/au-research/grants/arc/DP130104567 http://purl.org/au-research/grants/arc/CE140100016 |
Published version: | http://dx.doi.org/10.1109/tpami.2016.2517636 |
Appears in Collections: | Aurora harvest 8 Electrical and Electronic Engineering publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_105616.pdf Restricted Access | Restricted Access | 1.44 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.