Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes
The application of point cloud registration technology for workpiece positioning compensation using optical three-dimensional measurement methods has attracted widespread attention in the manufacturing industry, particularly point cloud registration methods integrated with deep learning are booming....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10852299/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832088044141805568 |
|---|---|
| author | Fenglin Han Hang Peng Xian Wu Haonan Ren Yiwei Sun Bin Su |
| author_facet | Fenglin Han Hang Peng Xian Wu Haonan Ren Yiwei Sun Bin Su |
| author_sort | Fenglin Han |
| collection | DOAJ |
| description | The application of point cloud registration technology for workpiece positioning compensation using optical three-dimensional measurement methods has attracted widespread attention in the manufacturing industry, particularly point cloud registration methods integrated with deep learning are booming. Since the training of current deep learning registration methods is often based on public datasets, the performance of point cloud registration of guide vanes depends on the relevance, quality, and quantity of the training dataset, if the training is directly based on the current public dataset used for guide vanes, the accuracy of the registration criteria cannot meet the requirements. Additionally, in real industrial scenarios, manually obtaining the real dataset is time-consuming, labor-intensive, and error-prone. To address these issues, this paper proposes a virtual simulation method based on the CAD model of the workpiece to set up a virtual camera so that a large number of near-real datasets can be generated quickly. The method can simulate the incomplete vane point cloud obtained by real shooting due to self-occlusion by setting multi-angle virtual cameras on the hemispherical surface wrapped in the CAD model. The experimental results show that the combination of the deep learning registration method and the virtual dataset method in this paper can improve the accuracy, efficiency, and stability of the deep learning registration for workpiece positioning compensation, which has a good prospect for practical application. |
| format | Article |
| id | doaj-art-9c3c223e034a4a4b81196c998b2a03d1 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-9c3c223e034a4a4b81196c998b2a03d12025-02-06T00:00:27ZengIEEEIEEE Access2169-35362025-01-0113215692157910.1109/ACCESS.2025.353362910852299Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide VanesFenglin Han0https://orcid.org/0000-0003-4392-9752Hang Peng1https://orcid.org/0009-0001-0470-3681Xian Wu2https://orcid.org/0009-0000-3143-2429Haonan Ren3https://orcid.org/0009-0006-8121-4503Yiwei Sun4https://orcid.org/0009-0006-0986-3752Bin Su5https://orcid.org/0009-0006-2178-0300State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Changsha, Hunan, ChinaCollege of Mechanical and Electrical Engineering, Central South University, Changsha, Hunan, ChinaCollege of Mechanical and Electrical Engineering, Central South University, Changsha, Hunan, ChinaCollege of Mechanical and Electrical Engineering, Central South University, Changsha, Hunan, ChinaDundee International Institute, Central South University, Changsha, Hunan, ChinaCollege of Mechanical and Electrical Engineering, Central South University, Changsha, Hunan, ChinaThe application of point cloud registration technology for workpiece positioning compensation using optical three-dimensional measurement methods has attracted widespread attention in the manufacturing industry, particularly point cloud registration methods integrated with deep learning are booming. Since the training of current deep learning registration methods is often based on public datasets, the performance of point cloud registration of guide vanes depends on the relevance, quality, and quantity of the training dataset, if the training is directly based on the current public dataset used for guide vanes, the accuracy of the registration criteria cannot meet the requirements. Additionally, in real industrial scenarios, manually obtaining the real dataset is time-consuming, labor-intensive, and error-prone. To address these issues, this paper proposes a virtual simulation method based on the CAD model of the workpiece to set up a virtual camera so that a large number of near-real datasets can be generated quickly. The method can simulate the incomplete vane point cloud obtained by real shooting due to self-occlusion by setting multi-angle virtual cameras on the hemispherical surface wrapped in the CAD model. The experimental results show that the combination of the deep learning registration method and the virtual dataset method in this paper can improve the accuracy, efficiency, and stability of the deep learning registration for workpiece positioning compensation, which has a good prospect for practical application.https://ieeexplore.ieee.org/document/10852299/Guide vanes registrationvirtual datasetdeep learningguide vanes positioning |
| spellingShingle | Fenglin Han Hang Peng Xian Wu Haonan Ren Yiwei Sun Bin Su Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes IEEE Access Guide vanes registration virtual dataset deep learning guide vanes positioning |
| title | Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes |
| title_full | Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes |
| title_fullStr | Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes |
| title_full_unstemmed | Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes |
| title_short | Simulation of Self-Occlusion Virtual Dataset Method for Robust Point Matching Algorithm, With Applications to Positioning of Guide Vanes |
| title_sort | simulation of self occlusion virtual dataset method for robust point matching algorithm with applications to positioning of guide vanes |
| topic | Guide vanes registration virtual dataset deep learning guide vanes positioning |
| url | https://ieeexplore.ieee.org/document/10852299/ |
| work_keys_str_mv | AT fenglinhan simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes AT hangpeng simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes AT xianwu simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes AT haonanren simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes AT yiweisun simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes AT binsu simulationofselfocclusionvirtualdatasetmethodforrobustpointmatchingalgorithmwithapplicationstopositioningofguidevanes |