Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features
In order to solve the problem of the traditional iterative closest point algorithm (ICPA), which requires a high initial position of point cloud and improves the speed and accuracy of point cloud registration, a new registration method is proposed in this paper. Firstly, the rough registration metho...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/3096 |
| _version_ | 1797615710237622272 |
|---|---|
| author | Ruiyang Sun Enzhong Zhang Deqiang Mu Shijun Ji Ziqiang Zhang Hongwei Liu Zheng Fu |
| author_facet | Ruiyang Sun Enzhong Zhang Deqiang Mu Shijun Ji Ziqiang Zhang Hongwei Liu Zheng Fu |
| author_sort | Ruiyang Sun |
| collection | DOAJ |
| description | In order to solve the problem of the traditional iterative closest point algorithm (ICPA), which requires a high initial position of point cloud and improves the speed and accuracy of point cloud registration, a new registration method is proposed in this paper. Firstly, the rough registration method is optimized. As for the extraction of the feature points, a new method of feature point extraction is adopted, which can better keep the features of the original point cloud. At the same time, the traditional point cloud filtering method is improved, and a voxel idea is introduced to filter the point cloud. The edge length data of the voxels is determined by the density, and the experimentally verified noise removal rates for the 3D cloud data are 95.3%, 98.6%, and 93.5%, respectively. Secondly, a precise registration method that combines the curvature feature and fast point feature histogram (FPFH) is proposed in the precise registration stage, and the algorithm is analyzed experimentally. Finally, the two point cloud data sets Stanford bunny and free-form surface are analyzed and verified, and it is concluded that this method can reduce the error by about 40.16% and 36.27%, respectively, and improve the iteration times by about 42.9% and 37.14%, respectively. |
| first_indexed | 2024-03-11T07:30:32Z |
| format | Article |
| id | doaj.art-389ef7549e324191950ca4983bdebd67 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:30:32Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-389ef7549e324191950ca4983bdebd672023-11-17T07:19:12ZengMDPI AGApplied Sciences2076-34172023-02-01135309610.3390/app13053096Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH FeaturesRuiyang Sun0Enzhong Zhang1Deqiang Mu2Shijun Ji3Ziqiang Zhang4Hongwei Liu5Zheng Fu6School of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaSchool of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaSchool of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaSchool of Mechanical and Aerospace Engineering, Jilin University, People’s Street, Changchun 130025, ChinaSchool of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaSchool of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaSchool of Mechanical and Electrical Engineering, Changchun University of Technology, Yan ‘an Avenue, Changchun 130012, ChinaIn order to solve the problem of the traditional iterative closest point algorithm (ICPA), which requires a high initial position of point cloud and improves the speed and accuracy of point cloud registration, a new registration method is proposed in this paper. Firstly, the rough registration method is optimized. As for the extraction of the feature points, a new method of feature point extraction is adopted, which can better keep the features of the original point cloud. At the same time, the traditional point cloud filtering method is improved, and a voxel idea is introduced to filter the point cloud. The edge length data of the voxels is determined by the density, and the experimentally verified noise removal rates for the 3D cloud data are 95.3%, 98.6%, and 93.5%, respectively. Secondly, a precise registration method that combines the curvature feature and fast point feature histogram (FPFH) is proposed in the precise registration stage, and the algorithm is analyzed experimentally. Finally, the two point cloud data sets Stanford bunny and free-form surface are analyzed and verified, and it is concluded that this method can reduce the error by about 40.16% and 36.27%, respectively, and improve the iteration times by about 42.9% and 37.14%, respectively.https://www.mdpi.com/2076-3417/13/5/3096feature extractionpoint cloud filteringedge feature pointsiterative closest point (icp)rough registrationprecise registration |
| spellingShingle | Ruiyang Sun Enzhong Zhang Deqiang Mu Shijun Ji Ziqiang Zhang Hongwei Liu Zheng Fu Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features Applied Sciences feature extraction point cloud filtering edge feature points iterative closest point (icp) rough registration precise registration |
| title | Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features |
| title_full | Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features |
| title_fullStr | Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features |
| title_full_unstemmed | Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features |
| title_short | Optimization of the 3D Point Cloud Registration Algorithm Based on FPFH Features |
| title_sort | optimization of the 3d point cloud registration algorithm based on fpfh features |
| topic | feature extraction point cloud filtering edge feature points iterative closest point (icp) rough registration precise registration |
| url | https://www.mdpi.com/2076-3417/13/5/3096 |
| work_keys_str_mv | AT ruiyangsun optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT enzhongzhang optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT deqiangmu optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT shijunji optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT ziqiangzhang optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT hongweiliu optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures AT zhengfu optimizationofthe3dpointcloudregistrationalgorithmbasedonfpfhfeatures |