Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor
To overcome the drawbacks of pairwise registration for mobile laser scanner (MLS) point clouds, such as difficulty in searching the corresponding points and inaccuracy registration matrix, a robust coarse-to-fine registration method is proposed to align different frames of MLS point clouds into a co...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/7/2431 |
_version_ | 1797539181775290368 |
---|---|
author | Yongjian Fu Zongchun Li Wenqi Wang Hua He Feng Xiong Yong Deng |
author_facet | Yongjian Fu Zongchun Li Wenqi Wang Hua He Feng Xiong Yong Deng |
author_sort | Yongjian Fu |
collection | DOAJ |
description | To overcome the drawbacks of pairwise registration for mobile laser scanner (MLS) point clouds, such as difficulty in searching the corresponding points and inaccuracy registration matrix, a robust coarse-to-fine registration method is proposed to align different frames of MLS point clouds into a common coordinate system. The method identifies the correct corresponding point pairs from the source and target point clouds, and then calculates the transform matrix. First, the performance of a multiscale eigenvalue statistic-based descriptor with different combinations of parameters is evaluated to identify the optimal combination. Second, based on the geometric distribution of points in the neighborhood of the keypoint, a weighted covariance matrix is constructed, by which the multiscale eigenvalues are calculated as the feature description language. Third, the corresponding points between the source and target point clouds are estimated in the feature space, and the incorrect ones are eliminated via a geometric consistency constraint. Finally, the estimated corresponding point pairs are used for coarse registration. The value of coarse registration is regarded as the initial value for the iterative closest point algorithm. Subsequently, the final fine registration result is obtained. The results of the registration experiments with Autonomous Systems Lab (ASL) Datasets show that the proposed method can accurately align MLS point clouds in different frames and outperform the comparative methods. |
first_indexed | 2024-03-10T12:41:34Z |
format | Article |
id | doaj.art-6da7e35d7b2a45e4ab967a38dc0a2a50 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T12:41:34Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-6da7e35d7b2a45e4ab967a38dc0a2a502023-11-21T13:48:57ZengMDPI AGSensors1424-82202021-04-01217243110.3390/s21072431Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based DescriptorYongjian Fu0Zongchun Li1Wenqi Wang2Hua He3Feng Xiong4Yong Deng5School of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaSchool of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaSchool of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaSchool of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaSchool of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaSchool of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaTo overcome the drawbacks of pairwise registration for mobile laser scanner (MLS) point clouds, such as difficulty in searching the corresponding points and inaccuracy registration matrix, a robust coarse-to-fine registration method is proposed to align different frames of MLS point clouds into a common coordinate system. The method identifies the correct corresponding point pairs from the source and target point clouds, and then calculates the transform matrix. First, the performance of a multiscale eigenvalue statistic-based descriptor with different combinations of parameters is evaluated to identify the optimal combination. Second, based on the geometric distribution of points in the neighborhood of the keypoint, a weighted covariance matrix is constructed, by which the multiscale eigenvalues are calculated as the feature description language. Third, the corresponding points between the source and target point clouds are estimated in the feature space, and the incorrect ones are eliminated via a geometric consistency constraint. Finally, the estimated corresponding point pairs are used for coarse registration. The value of coarse registration is regarded as the initial value for the iterative closest point algorithm. Subsequently, the final fine registration result is obtained. The results of the registration experiments with Autonomous Systems Lab (ASL) Datasets show that the proposed method can accurately align MLS point clouds in different frames and outperform the comparative methods.https://www.mdpi.com/1424-8220/21/7/2431MLS point cloudspairwise registrationweighted covariance matrixmultiscale eigenvalues |
spellingShingle | Yongjian Fu Zongchun Li Wenqi Wang Hua He Feng Xiong Yong Deng Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor Sensors MLS point clouds pairwise registration weighted covariance matrix multiscale eigenvalues |
title | Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor |
title_full | Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor |
title_fullStr | Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor |
title_full_unstemmed | Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor |
title_short | Robust Coarse-to-Fine Registration Scheme for Mobile Laser Scanner Point Clouds Using Multiscale Eigenvalue Statistic-Based Descriptor |
title_sort | robust coarse to fine registration scheme for mobile laser scanner point clouds using multiscale eigenvalue statistic based descriptor |
topic | MLS point clouds pairwise registration weighted covariance matrix multiscale eigenvalues |
url | https://www.mdpi.com/1424-8220/21/7/2431 |
work_keys_str_mv | AT yongjianfu robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor AT zongchunli robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor AT wenqiwang robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor AT huahe robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor AT fengxiong robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor AT yongdeng robustcoarsetofineregistrationschemeformobilelaserscannerpointcloudsusingmultiscaleeigenvaluestatisticbaseddescriptor |