Edge detection from point cloud of worn parts
3D scanners are able to quickly and accurately digitise objects into Point Cloud Data (PCD). It has been used in various applications, including damage identification for automated repair via additive manufacturing. Useful information, such as the geometrical edge information, has to be extracted fr...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/88666 http://hdl.handle.net/10220/45981 |
| _version_ | 1826119342449754112 |
|---|---|
| author | Nguyen, Keith Wei Liang Aprilia, A. Khairyanto, Ahmad Pang, Wee Ching Seet, Gerald Gim Lee Tor, Shu Beng |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Nguyen, Keith Wei Liang Aprilia, A. Khairyanto, Ahmad Pang, Wee Ching Seet, Gerald Gim Lee Tor, Shu Beng |
| author_sort | Nguyen, Keith Wei Liang |
| collection | NTU |
| description | 3D scanners are able to quickly and accurately digitise objects into Point Cloud Data (PCD). It has been used in various applications, including damage identification for automated repair via additive manufacturing. Useful information, such as the geometrical edge information, has to be extracted from the PCD for damage identification. A common edge detection method is by thresholding high curvature points from a point cloud. However, edges on worn parts tend to have less distinct edges from wear. This would cause errors in curvature based edge detection such that a band of points is detected along the edge, instead of a single row of points. Other edge detection methods are also unable to accurately or robustly detect the worn edges. Hence, this paper seeks to solve the limitation of the state of the art of PCD based edge detection for detecting worn edges. In this paper, we present a method of detecting geometrical edges, which involves curvature thresholding, iterative non-maximal suppression, and feature line generation. The proposed method has been validated on a physically scanned part, and the results are presented. |
| first_indexed | 2024-10-01T04:58:43Z |
| format | Conference Paper |
| id | ntu-10356/88666 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:58:43Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/886662020-09-24T20:12:16Z Edge detection from point cloud of worn parts Nguyen, Keith Wei Liang Aprilia, A. Khairyanto, Ahmad Pang, Wee Ching Seet, Gerald Gim Lee Tor, Shu Beng School of Mechanical and Aerospace Engineering Proceedings of the 3rd International Conference on Progress in Additive Manufacturing (Pro-AM 2018) Singapore Centre for 3D Printing Point Cloud Edge Detection DRNTU::Engineering::Mechanical engineering::Prototyping 3D scanners are able to quickly and accurately digitise objects into Point Cloud Data (PCD). It has been used in various applications, including damage identification for automated repair via additive manufacturing. Useful information, such as the geometrical edge information, has to be extracted from the PCD for damage identification. A common edge detection method is by thresholding high curvature points from a point cloud. However, edges on worn parts tend to have less distinct edges from wear. This would cause errors in curvature based edge detection such that a band of points is detected along the edge, instead of a single row of points. Other edge detection methods are also unable to accurately or robustly detect the worn edges. Hence, this paper seeks to solve the limitation of the state of the art of PCD based edge detection for detecting worn edges. In this paper, we present a method of detecting geometrical edges, which involves curvature thresholding, iterative non-maximal suppression, and feature line generation. The proposed method has been validated on a physically scanned part, and the results are presented. NRF (Natl Research Foundation, S’pore) Published version 2018-09-13T02:16:27Z 2019-12-06T17:08:23Z 2018-09-13T02:16:27Z 2019-12-06T17:08:23Z 2018 Conference Paper Nguyen, K. W. L., Aprilia A., Khairyanto, A., Pang, W. C., Seet, G. G. L., & Tor, S. B. (2018). Edge detection from point cloud of worn parts. Proceedings of the 3rd International Conference on Progress in Additive Manufacturing (Pro-AM 2018), 595-600. doi:10.25341/D45C7S https://hdl.handle.net/10356/88666 http://hdl.handle.net/10220/45981 10.25341/D45C7S en © 2018 Nanyang Technological University. Published by Nanyang Technological University, Singapore. 6 p. application/pdf |
| spellingShingle | Point Cloud Edge Detection DRNTU::Engineering::Mechanical engineering::Prototyping Nguyen, Keith Wei Liang Aprilia, A. Khairyanto, Ahmad Pang, Wee Ching Seet, Gerald Gim Lee Tor, Shu Beng Edge detection from point cloud of worn parts |
| title | Edge detection from point cloud of worn parts |
| title_full | Edge detection from point cloud of worn parts |
| title_fullStr | Edge detection from point cloud of worn parts |
| title_full_unstemmed | Edge detection from point cloud of worn parts |
| title_short | Edge detection from point cloud of worn parts |
| title_sort | edge detection from point cloud of worn parts |
| topic | Point Cloud Edge Detection DRNTU::Engineering::Mechanical engineering::Prototyping |
| url | https://hdl.handle.net/10356/88666 http://hdl.handle.net/10220/45981 |
| work_keys_str_mv | AT nguyenkeithweiliang edgedetectionfrompointcloudofwornparts AT apriliaa edgedetectionfrompointcloudofwornparts AT khairyantoahmad edgedetectionfrompointcloudofwornparts AT pangweeching edgedetectionfrompointcloudofwornparts AT seetgeraldgimlee edgedetectionfrompointcloudofwornparts AT torshubeng edgedetectionfrompointcloudofwornparts |