Abstract
Inspection of welding beads is important to achieve reliability of welding condition. Radiography testing is a widely used method in ship piping systems to verify welding quality. In our industry problem, a mobile robot was utilized to radiate X-ray outwards from inside of a pipe. Because small amount of radiation is allowed by the legal regulation, precise localization of a weld line is required. This paper proposes a robot vision algorithm to precisely localize the position of a weld line in a piping system. The proposed algorithm detects a weld line and loosely localizes the position by using a difference of Gaussian. For a sub-region that contains the loosely localized weld line, morphological operations are applied to precisely localize the position of the weld line. Experiments were conducted on real industry data to demonstrate the effectiveness of the proposed algorithm.
| Original language | English |
|---|---|
| Title of host publication | ICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings |
| Publisher | IEEE Computer Society |
| Pages | 1356-1359 |
| Number of pages | 4 |
| ISBN (Electronic) | 9788993215137 |
| DOIs | |
| State | Published - 13 Dec 2017 |
| Event | 17th International Conference on Control, Automation and Systems, ICCAS 2017 - Jeju, Korea, Republic of Duration: 18 Oct 2017 → 21 Oct 2017 |
Publication series
| Name | International Conference on Control, Automation and Systems |
|---|---|
| Volume | 2017-October |
| ISSN (Print) | 1598-7833 |
Conference
| Conference | 17th International Conference on Control, Automation and Systems, ICCAS 2017 |
|---|---|
| Country/Territory | Korea, Republic of |
| City | Jeju |
| Period | 18/10/17 → 21/10/17 |
Bibliographical note
Publisher Copyright:© 2017 Institute of Control, Robotics and Systems - ICROS.
Keywords
- Computer vision
- Image processing
- Ship piping system
- Weld line detection
- Welding bead