MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template
With advancements in photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually being applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy di...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/22/10535 |
| _version_ | 1827677518417625088 |
|---|---|
| author | Shijie Su Chao Wang Ke Chen Jian Zhang Hui Yang |
| author_facet | Shijie Su Chao Wang Ke Chen Jian Zhang Hui Yang |
| author_sort | Shijie Su |
| collection | DOAJ |
| description | With advancements in photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually being applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy directly affects the accuracy of 3D measurements. In this study, we designed a novel MPCR-Net for multiple partial point cloud registration networks. First, an ideal point cloud was extracted from the CAD model of the workpiece and used as the global template. Next, a deep neural network was used to search for the corresponding point groups between each partial point cloud and the global template point cloud. Then, the rigid body transformation matrix was learned according to these correspondence point groups to realize the registration of each partial point cloud. Finally, the iterative closest point algorithm was used to optimize the registration results to obtain the final point cloud model of the workpiece. We conducted point cloud registration experiments on untrained models and actual workpieces, and by comparing them with existing point cloud registration methods, we verified that the MPCR-Net could improve the accuracy and robustness of the 3D point cloud registration. |
| first_indexed | 2024-03-10T05:44:09Z |
| format | Article |
| id | doaj.art-63d4eee0502d4cc19005343ef53e2046 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T05:44:09Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-63d4eee0502d4cc19005343ef53e20462023-11-22T22:15:09ZengMDPI AGApplied Sciences2076-34172021-11-0111221053510.3390/app112210535MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global TemplateShijie Su0Chao Wang1Ke Chen2Jian Zhang3Hui Yang4School of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaPlasma Environment Technology Group, Research Institute for Environmental Innovation (Suzhou) Tsinghua, Suzhou 215163, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaComplex Systems Monitoring, Modeling and Control Lab, The Pennsylvania State University, University Park, PA 16802, USAWith advancements in photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually being applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy directly affects the accuracy of 3D measurements. In this study, we designed a novel MPCR-Net for multiple partial point cloud registration networks. First, an ideal point cloud was extracted from the CAD model of the workpiece and used as the global template. Next, a deep neural network was used to search for the corresponding point groups between each partial point cloud and the global template point cloud. Then, the rigid body transformation matrix was learned according to these correspondence point groups to realize the registration of each partial point cloud. Finally, the iterative closest point algorithm was used to optimize the registration results to obtain the final point cloud model of the workpiece. We conducted point cloud registration experiments on untrained models and actual workpieces, and by comparing them with existing point cloud registration methods, we verified that the MPCR-Net could improve the accuracy and robustness of the 3D point cloud registration.https://www.mdpi.com/2076-3417/11/22/10535point cloud registrationtemplate point cloudmultiple partial point clouddeep learning |
| spellingShingle | Shijie Su Chao Wang Ke Chen Jian Zhang Hui Yang MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template Applied Sciences point cloud registration template point cloud multiple partial point cloud deep learning |
| title | MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template |
| title_full | MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template |
| title_fullStr | MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template |
| title_full_unstemmed | MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template |
| title_short | MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template |
| title_sort | mpcr net multiple partial point clouds registration network using a global template |
| topic | point cloud registration template point cloud multiple partial point cloud deep learning |
| url | https://www.mdpi.com/2076-3417/11/22/10535 |
| work_keys_str_mv | AT shijiesu mpcrnetmultiplepartialpointcloudsregistrationnetworkusingaglobaltemplate AT chaowang mpcrnetmultiplepartialpointcloudsregistrationnetworkusingaglobaltemplate AT kechen mpcrnetmultiplepartialpointcloudsregistrationnetworkusingaglobaltemplate AT jianzhang mpcrnetmultiplepartialpointcloudsregistrationnetworkusingaglobaltemplate AT huiyang mpcrnetmultiplepartialpointcloudsregistrationnetworkusingaglobaltemplate |