Next Article in Journal
Threshold Voltage Recovery Time Measurement Technique Post VTH Instability in Normally-Off p-Gate GaN High Electron Mobility Transistors
Next Article in Special Issue
An Evolutionary Deep Learning Framework for Accurate Remaining Capacity Prediction in Lithium-Ion Batteries
Previous Article in Journal
Interpretable Mixture of Experts for Decomposition Network on Server Performance Metrics Forecasting
Previous Article in Special Issue
Multi-Feature Extraction and Selection Method to Diagnose Burn Depth from Burn Images
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 13
Issue 20
10.3390/electronics13204117
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning

by
Shaopeng Kang
1,2,*,
Hongbin Qiang
1,2,
Jing Yang
1,2,
Kailei Liu
1,2,
Wenbin Qian
1,2,
Wenpeng Li
1,2 and
Yanfei Pan
3
1
School of Mechanical Engineering, Jiangsu University of Technology, Changzhou 213001, China
2
Jiangsu Provincial Engineering Research Center for Advanced Fluid Power and Equipment, Changzhou 213001, China
3
Jiangsu Yangtze Intelligent Manufacturing Research Institute Co., Ltd., Changzhou 213001, China
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(20), 4117; https://doi.org/10.3390/electronics13204117
Submission received: 3 September 2024 / Revised: 23 September 2024 / Accepted: 30 September 2024 / Published: 18 October 2024
(This article belongs to the Special Issue Advanced Machine Learning, Pattern Recognition, and Deep Learning Technologies: Methodologies and Applications)
Browse Figures
Versions Notes

Abstract

Laser vision seam tracking enhances robotic welding by enabling external information acquisition, thus improving the overall intelligence of the welding process. However, camera images captured during welding often suffer from distortion due to strong noises, including arcs, splashes, and smoke, which adversely affect the accuracy and robustness of feature point detection. To mitigate these issues, we propose a feature point extraction algorithm tailored for weld images, utilizing an improved Deeplabv3+ semantic segmentation network combined with EfficientDet. By replacing Deeplabv3+’s backbone with MobileNetV2, we enhance prediction efficiency. The DenseASPP structure and attention mechanism are implemented to focus on laser stripe edge extraction, resulting in cleaner laser stripe images and minimizing noise interference. Subsequently, EfficientDet extracts feature point positions from these cleaned images. Experimental results demonstrate that, across four typical weld types, the average feature point extraction error is maintained below 1 pixel, with over 99% of errors falling below 3 pixels, indicating both high detection accuracy and reliability.
Keywords: seam tracking; visual sensing; deep learning; feature point extraction seam tracking; visual sensing; deep learning; feature point extraction

Share and Cite

MDPI and ACS Style

Kang, S.; Qiang, H.; Yang, J.; Liu, K.; Qian, W.; Li, W.; Pan, Y. Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning. Electronics 2024, 13, 4117. https://doi.org/10.3390/electronics13204117

AMA Style

Kang S, Qiang H, Yang J, Liu K, Qian W, Li W, Pan Y. Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning. Electronics. 2024; 13(20):4117. https://doi.org/10.3390/electronics13204117

Chicago/Turabian Style

Kang, Shaopeng, Hongbin Qiang, Jing Yang, Kailei Liu, Wenbin Qian, Wenpeng Li, and Yanfei Pan. 2024. "Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning" Electronics 13, no. 20: 4117. https://doi.org/10.3390/electronics13204117

APA Style

Kang, S., Qiang, H., Yang, J., Liu, K., Qian, W., Li, W., & Pan, Y. (2024). Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning. Electronics, 13(20), 4117. https://doi.org/10.3390/electronics13204117

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop