A fast registration method for multi-view point clouds with low overlap in robotic measurement
With the rapid advancement of mechanical automation and intelligent processing technology, accurately measuring the surfaces of complex parts has emerged as a significant research challenge. Robotic measurement technology plays a crucial role in facilitating rapid quality inspections during the manu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Biomimetic Intelligence and Robotics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667379724000536 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590016885293056 |
|---|---|
| author | Chuangchuang Li Xubin Lin Zhaoyang Liao Hongmin Wu Zhihao Xu Xuefeng Zhou |
| author_facet | Chuangchuang Li Xubin Lin Zhaoyang Liao Hongmin Wu Zhihao Xu Xuefeng Zhou |
| author_sort | Chuangchuang Li |
| collection | DOAJ |
| description | With the rapid advancement of mechanical automation and intelligent processing technology, accurately measuring the surfaces of complex parts has emerged as a significant research challenge. Robotic measurement technology plays a crucial role in facilitating rapid quality inspections during the manufacturing process due to its inherent flexibility. However, the irregular shapes and viewpoint occlusions of complex parts complicate precise measurement. To address these challenges, this work proposes a point cloud registration network for robotic scanning systems and introduces a DBR-Net (Dual-line Registration Network) to overcome the issues of low overlap rates and perspective occlusion that currently impede the registration of certain workpieces. First, feature extraction is performed using a bilinear encoder and multi-level feature interactions of both point-wise and global features. Subsequently, the features are sampled through unanimous voting and fed into the RANSAC (Random Sample Consensus) algorithm for pose estimation, enabling multi-view point cloud registration. Experimental results demonstrate that this method significantly outperforms many existing techniques in terms of feature extraction and registration accuracy, thereby enhancing the overall performance of point cloud registration. |
| format | Article |
| id | doaj-art-e84c5658335d49ea9fad5e0f3f4f0917 |
| institution | Kabale University |
| issn | 2667-3797 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Biomimetic Intelligence and Robotics |
| spelling | doaj-art-e84c5658335d49ea9fad5e0f3f4f09172025-01-24T04:45:56ZengElsevierBiomimetic Intelligence and Robotics2667-37972025-06-0152100195A fast registration method for multi-view point clouds with low overlap in robotic measurementChuangchuang Li0Xubin Lin1Zhaoyang Liao2Hongmin Wu3Zhihao Xu4Xuefeng Zhou5College of Electronic and Information Engineering, Wuyi University, Jiangmen 529020, ChinaInstitute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangdong Key Laboratory of Modern Control Technology, Guangzhou 510095, ChinaInstitute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangdong Key Laboratory of Modern Control Technology, Guangzhou 510095, China; Corresponding author.Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangdong Key Laboratory of Modern Control Technology, Guangzhou 510095, ChinaInstitute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangdong Key Laboratory of Modern Control Technology, Guangzhou 510095, ChinaInstitute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangdong Key Laboratory of Modern Control Technology, Guangzhou 510095, ChinaWith the rapid advancement of mechanical automation and intelligent processing technology, accurately measuring the surfaces of complex parts has emerged as a significant research challenge. Robotic measurement technology plays a crucial role in facilitating rapid quality inspections during the manufacturing process due to its inherent flexibility. However, the irregular shapes and viewpoint occlusions of complex parts complicate precise measurement. To address these challenges, this work proposes a point cloud registration network for robotic scanning systems and introduces a DBR-Net (Dual-line Registration Network) to overcome the issues of low overlap rates and perspective occlusion that currently impede the registration of certain workpieces. First, feature extraction is performed using a bilinear encoder and multi-level feature interactions of both point-wise and global features. Subsequently, the features are sampled through unanimous voting and fed into the RANSAC (Random Sample Consensus) algorithm for pose estimation, enabling multi-view point cloud registration. Experimental results demonstrate that this method significantly outperforms many existing techniques in terms of feature extraction and registration accuracy, thereby enhancing the overall performance of point cloud registration.http://www.sciencedirect.com/science/article/pii/S2667379724000536Point cloud registrationFeature interactionMulti-viewRobotic measurement |
| spellingShingle | Chuangchuang Li Xubin Lin Zhaoyang Liao Hongmin Wu Zhihao Xu Xuefeng Zhou A fast registration method for multi-view point clouds with low overlap in robotic measurement Biomimetic Intelligence and Robotics Point cloud registration Feature interaction Multi-view Robotic measurement |
| title | A fast registration method for multi-view point clouds with low overlap in robotic measurement |
| title_full | A fast registration method for multi-view point clouds with low overlap in robotic measurement |
| title_fullStr | A fast registration method for multi-view point clouds with low overlap in robotic measurement |
| title_full_unstemmed | A fast registration method for multi-view point clouds with low overlap in robotic measurement |
| title_short | A fast registration method for multi-view point clouds with low overlap in robotic measurement |
| title_sort | fast registration method for multi view point clouds with low overlap in robotic measurement |
| topic | Point cloud registration Feature interaction Multi-view Robotic measurement |
| url | http://www.sciencedirect.com/science/article/pii/S2667379724000536 |
| work_keys_str_mv | AT chuangchuangli afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT xubinlin afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT zhaoyangliao afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT hongminwu afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT zhihaoxu afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT xuefengzhou afastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT chuangchuangli fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT xubinlin fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT zhaoyangliao fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT hongminwu fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT zhihaoxu fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement AT xuefengzhou fastregistrationmethodformultiviewpointcloudswithlowoverlapinroboticmeasurement |