EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Laser Stripe Segmentation Network Based on Evidential Uncertainty Theory Modeling Fine-Tuning Optimization Symmetric Algorithm

Chenbo Shi, Delin Wang, Xiangyu Zhang, Chun Zhang, Jia Yan, Changsheng Zhu, Xiaobing Feng

Symmetry · 09.08.2025 · 17 (8) · 1280

DOI: 10.3390/sym17081280 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 09.08.2025. Verfasst von Chenbo Shi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Projects of Scientific and Technological Innovation in Daiyue District, Tai’an City.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In welding applications, line-structured-light vision is widely used for seam tracking, but intense noise from arc glow, spatter, smoke, and reflections makes reliable laser-stripe segmentation difficult. To address these challenges, we propose EUFNet, an uncertainty-driven symmetrical two-stage segmentation network for precise stripe extraction under real-world welding conditions. In the first stage, a lightweight backbone generates a coarse stripe mask and a pixel-wise uncertainty map; in the second stage, a functionally mirrored refinement network uses this uncertainty map to symmetrically guide fine-tuning of the same image regions, thereby preserving stripe continuity. We further employ an uncertainty-weighted loss that treats ambiguous pixels and their corresponding evidence in a one-to-one, symmetric manner. Evaluated on a large-scale dataset of 3100 annotated welding images, EUFNet achieves a mean IoU of 89.3% and a mean accuracy of 95.9% at 236.7 FPS (compared to U-Net’s 82.5% mean IoU and 90.2% mean accuracy), significantly outperforming existing approaches in both accuracy and real-time performance. Moreover, EUFNet generalizes effectively to the public WLSD benchmark, surpassing state-of-the-art baselines in both accuracy and speed. These results confirm that a structurally and functionally symmetric, uncertainty-driven two-stage refinement strategy—combined with targeted loss design and efficient feature integration—yields high-precision, real-time performance for automated welding vision.

Förderung

  • Projects of Scientific and Technological Innovation in Daiyue District, Tai’an City

Zitieren

APA

Shi, C., Wang, D., Zhang, X., Zhang, C., Yan, J., Zhu, C., & Feng, X. (2025). Laser Stripe Segmentation Network Based on Evidential Uncertainty Theory Modeling Fine-Tuning Optimization Symmetric Algorithm. Symmetry, 17(8), 1280. https://doi.org/10.3390/sym17081280

Vancouver

Shi C, Wang D, Zhang X, Zhang C, Yan J, Zhu C, et al. Laser Stripe Segmentation Network Based on Evidential Uncertainty Theory Modeling Fine-Tuning Optimization Symmetric Algorithm. Symmetry. 2025;17(8):1280. doi:10.3390/sym17081280

BibTeX
@article{Shi2025,
  author = {Shi, Chenbo and Wang, Delin and Zhang, Xiangyu and Zhang, Chun and Yan, Jia and Zhu, Changsheng and Feng, Xiaobing},
  title = {Laser Stripe Segmentation Network Based on Evidential Uncertainty Theory Modeling Fine-Tuning Optimization Symmetric Algorithm},
  journal = {Symmetry},
  year = {2025},
  volume = {17},
  number = {8},
  pages = {1280},
  doi = {10.3390/sym17081280}
}
Kostenlos starten →