A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy
In this paper, we introduce a modified Generalized Iterative Closest Point (GICP) algorithm by presenting a coarse-to-fine strategy. Our contributions can be summarized as: Firstly, we use adaptively a plane-to-plane probabilistic matching model by gradually reducing the neighborhood range for given...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9007699/ |
id |
doaj-96c89b4ddcd54f24a7590ef45674371d |
---|---|
record_format |
Article |
spelling |
doaj-96c89b4ddcd54f24a7590ef45674371d2021-03-30T02:43:05ZengIEEEIEEE Access2169-35362020-01-018406924070310.1109/ACCESS.2020.29761329007699A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed StrategyXin Wang0https://orcid.org/0000-0001-8714-4928Yun Li1https://orcid.org/0000-0001-9534-1614Yaxin Peng2https://orcid.org/0000-0002-2983-555XShihui Ying3https://orcid.org/0000-0001-9423-0146Department of Mathematics, School of Science, Shanghai University, Shanghai, ChinaDepartment of Mathematics, School of Science, Shanghai University, Shanghai, ChinaDepartment of Mathematics, School of Science, Shanghai University, Shanghai, ChinaDepartment of Mathematics, School of Science, Shanghai University, Shanghai, ChinaIn this paper, we introduce a modified Generalized Iterative Closest Point (GICP) algorithm by presenting a coarse-to-fine strategy. Our contributions can be summarized as: Firstly, we use adaptively a plane-to-plane probabilistic matching model by gradually reducing the neighborhood range for given two point sets. It is an inner coarse-to-fine iteration process. Secondly, we use an outer coarse-to-fine strategy to bridge the point-to-point and plane-to-plane registration for refining the matching. Thirdly, we use the trimmed method to gradually eliminate the effects of incorrect correspondences, which improves the robustness of the methods especially for the low overlap cases. Moreover, we also extend our method to the scale registration case. Finally, we conduct extensive experiments to demonstrate that our method is more reliable and robust in various situations, including missing points, noise and different scale factors. Experimental results show that our approach outperforms several state-of-the-art registration methods.https://ieeexplore.ieee.org/document/9007699/Registrationmodified GICPtrimmed method |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xin Wang Yun Li Yaxin Peng Shihui Ying |
spellingShingle |
Xin Wang Yun Li Yaxin Peng Shihui Ying A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy IEEE Access Registration modified GICP trimmed method |
author_facet |
Xin Wang Yun Li Yaxin Peng Shihui Ying |
author_sort |
Xin Wang |
title |
A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy |
title_short |
A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy |
title_full |
A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy |
title_fullStr |
A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy |
title_full_unstemmed |
A Coarse-to-Fine Generalized-ICP Algorithm With Trimmed Strategy |
title_sort |
coarse-to-fine generalized-icp algorithm with trimmed strategy |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
In this paper, we introduce a modified Generalized Iterative Closest Point (GICP) algorithm by presenting a coarse-to-fine strategy. Our contributions can be summarized as: Firstly, we use adaptively a plane-to-plane probabilistic matching model by gradually reducing the neighborhood range for given two point sets. It is an inner coarse-to-fine iteration process. Secondly, we use an outer coarse-to-fine strategy to bridge the point-to-point and plane-to-plane registration for refining the matching. Thirdly, we use the trimmed method to gradually eliminate the effects of incorrect correspondences, which improves the robustness of the methods especially for the low overlap cases. Moreover, we also extend our method to the scale registration case. Finally, we conduct extensive experiments to demonstrate that our method is more reliable and robust in various situations, including missing points, noise and different scale factors. Experimental results show that our approach outperforms several state-of-the-art registration methods. |
topic |
Registration modified GICP trimmed method |
url |
https://ieeexplore.ieee.org/document/9007699/ |
work_keys_str_mv |
AT xinwang acoarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT yunli acoarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT yaxinpeng acoarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT shihuiying acoarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT xinwang coarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT yunli coarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT yaxinpeng coarsetofinegeneralizedicpalgorithmwithtrimmedstrategy AT shihuiying coarsetofinegeneralizedicpalgorithmwithtrimmedstrategy |
_version_ |
1724184760003067904 |