EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Shaopeng Kang, Hongbin Qiang, Jing Yang, Kailei Liu, Wenbin Qian, Wenpeng Li, Yanfei Pan

Electronics · 18.10.2024 · 13 (20) · 4117

DOI: 10.3390/electronics13204117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 18.10.2024. Verfasst von Shaopeng Kang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of the Jiangsu Higher Education Institutions of China, Changzhou Leading Innovative Talents Introduction and Cultivation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of the Jiangsu Higher Education Institutions of China
  • Changzhou Leading Innovative Talents Introduction and Cultivation Project

Zitieren

APA

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

Vancouver

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

BibTeX
@article{Kang2024,
  author = {Kang, Shaopeng and Qiang, Hongbin and Yang, Jing and Liu, Kailei and Qian, Wenbin and Li, Wenpeng and Pan, Yanfei},
  title = {Research on a Feature Point Detection Algorithm for Weld Images Based on Deep Learning},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {20},
  pages = {4117},
  doi = {10.3390/electronics13204117}
}
Kostenlos starten →