Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding
There is a strong correlation between the geometry of the weld pool surface and the degree of penetration in arc welding. To measure the geometry of the weld pool surface robustly, many structured light laser line based monitoring systems have been proposed in recent years. The geometry of the specu...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/8/12/2445 |
| _version_ | 1819129163441766400 |
|---|---|
| author | Zhenzhou Wang Cunshan Zhang Zhen Pan Zihao Wang Lina Liu Xiaomei Qi Shuai Mao Jinfeng Pan |
| author_facet | Zhenzhou Wang Cunshan Zhang Zhen Pan Zihao Wang Lina Liu Xiaomei Qi Shuai Mao Jinfeng Pan |
| author_sort | Zhenzhou Wang |
| collection | DOAJ |
| description | There is a strong correlation between the geometry of the weld pool surface and the degree of penetration in arc welding. To measure the geometry of the weld pool surface robustly, many structured light laser line based monitoring systems have been proposed in recent years. The geometry of the specular weld pool could be computed from the reflected laser lines based on different principles. The prerequisite of accurate computation of the weld pool surface is to segment the reflected laser lines robustly and efficiently. To find the most effective segmentation solutions for the images captured with different welding parameters, different image processing algorithms are combined to form eight approaches and these approaches are compared both qualitatively and quantitatively in this paper. In particular, the gradient detection filter, the difference method and the GLCM (grey level co-occurrence matrix) are used to remove the uneven background. The spline fitting enhancement method is used to remove the fuzziness. The slope difference distribution-based threshold selection method is used to segment the laser lines from the background. Both qualitative and quantitative experiments are conducted to evaluate the accuracy and the efficiency of the proposed approaches extensively. |
| first_indexed | 2024-12-22T08:39:21Z |
| format | Article |
| id | doaj.art-49dff42516824b0e82458ef02b62eca7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-22T08:39:21Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-49dff42516824b0e82458ef02b62eca72022-12-21T18:32:16ZengMDPI AGApplied Sciences2076-34172018-12-01812244510.3390/app8122445app8122445Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc WeldingZhenzhou Wang0Cunshan Zhang1Zhen Pan2Zihao Wang3Lina Liu4Xiaomei Qi5Shuai Mao6Jinfeng Pan7College of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaCollege of Electrical and Electronic Engineering, Shandong University of Technology, ChinaThere is a strong correlation between the geometry of the weld pool surface and the degree of penetration in arc welding. To measure the geometry of the weld pool surface robustly, many structured light laser line based monitoring systems have been proposed in recent years. The geometry of the specular weld pool could be computed from the reflected laser lines based on different principles. The prerequisite of accurate computation of the weld pool surface is to segment the reflected laser lines robustly and efficiently. To find the most effective segmentation solutions for the images captured with different welding parameters, different image processing algorithms are combined to form eight approaches and these approaches are compared both qualitatively and quantitatively in this paper. In particular, the gradient detection filter, the difference method and the GLCM (grey level co-occurrence matrix) are used to remove the uneven background. The spline fitting enhancement method is used to remove the fuzziness. The slope difference distribution-based threshold selection method is used to segment the laser lines from the background. Both qualitative and quantitative experiments are conducted to evaluate the accuracy and the efficiency of the proposed approaches extensively.https://www.mdpi.com/2076-3417/8/12/2445Image processingsegmentationsplinegrey level co-occurrence matrixgradient detectionthreshold selection |
| spellingShingle | Zhenzhou Wang Cunshan Zhang Zhen Pan Zihao Wang Lina Liu Xiaomei Qi Shuai Mao Jinfeng Pan Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding Applied Sciences Image processing segmentation spline grey level co-occurrence matrix gradient detection threshold selection |
| title | Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding |
| title_full | Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding |
| title_fullStr | Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding |
| title_full_unstemmed | Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding |
| title_short | Image Segmentation Approaches for Weld Pool Monitoring during Robotic Arc Welding |
| title_sort | image segmentation approaches for weld pool monitoring during robotic arc welding |
| topic | Image processing segmentation spline grey level co-occurrence matrix gradient detection threshold selection |
| url | https://www.mdpi.com/2076-3417/8/12/2445 |
| work_keys_str_mv | AT zhenzhouwang imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT cunshanzhang imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT zhenpan imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT zihaowang imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT linaliu imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT xiaomeiqi imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT shuaimao imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding AT jinfengpan imagesegmentationapproachesforweldpoolmonitoringduringroboticarcwelding |