Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.00836 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915317286961152 |
|---|---|
| author | Li, Baolu Yu, Hongkai Sun, Huiming Ma, Jin Lin, Yuewei Ma, Lu Du, Yonghua |
| author_facet | Li, Baolu Yu, Hongkai Sun, Huiming Ma, Jin Lin, Yuewei Ma, Lu Du, Yonghua |
| contents | The synchrotron light source, a cutting-edge large-scale user facility, requires autonomous synchrotron beamline operations, a crucial technique that should enable experiments to be conducted automatically, reliably, and safely with minimum human intervention. However, current state-of-the-art synchrotron beamlines still heavily rely on human safety oversight. To bridge the gap between automated and autonomous operation, a computer vision-based system is proposed, integrating deep learning and multiview cameras for real-time collision detection. The system utilizes equipment segmentation, tracking, and geometric analysis to assess potential collisions with transfer learning that enhances robustness. In addition, an interactive annotation module has been developed to improve the adaptability to new object classes. Experiments on a real beamline dataset demonstrate high accuracy, real-time performance, and strong potential for autonomous synchrotron beamline operations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00836 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing from Automated to Autonomous Beamline by Leveraging Computer Vision Li, Baolu Yu, Hongkai Sun, Huiming Ma, Jin Lin, Yuewei Ma, Lu Du, Yonghua Computer Vision and Pattern Recognition The synchrotron light source, a cutting-edge large-scale user facility, requires autonomous synchrotron beamline operations, a crucial technique that should enable experiments to be conducted automatically, reliably, and safely with minimum human intervention. However, current state-of-the-art synchrotron beamlines still heavily rely on human safety oversight. To bridge the gap between automated and autonomous operation, a computer vision-based system is proposed, integrating deep learning and multiview cameras for real-time collision detection. The system utilizes equipment segmentation, tracking, and geometric analysis to assess potential collisions with transfer learning that enhances robustness. In addition, an interactive annotation module has been developed to improve the adaptability to new object classes. Experiments on a real beamline dataset demonstrate high accuracy, real-time performance, and strong potential for autonomous synchrotron beamline operations. |
| title | Advancing from Automated to Autonomous Beamline by Leveraging Computer Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.00836 |