EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Industrial Weld Defect Detection Based on Monocular Depth Estimation and Dual-Attention Point Cloud Network

Nannan Zhao, Shijie Chen

Sensors · 23.05.2026 · 26 (11) · 3321

DOI: 10.3390/s26113321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.05.2026. Verfasst von Nannan Zhao und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Guangdong Ocean University, Yangjiang 529568, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial quality control, the precise identification of severe structural weld defects is paramount. Traditional 2D image-based detection methods are susceptible to illumination and texture interference, while high-precision 3D laser scanning solutions are costly and impractical for large-scale deployment. To achieve reliable geometric defect detection at low cost, this paper proposes a detection framework based on monocular depth estimation and a dual-attention point cloud network. First, YOLOv8 is employed for rapid region of interest extraction, and an advanced monocular depth estimation model generates 3D pseudo-point clouds containing geometric information. Secondly, addressing the challenge of distinct spatial orientation features in missed weld defects that are prone to confusion, this paper introduces a dual-attention-enhanced point cloud classification network named DA-PointNet++. This model embeds dual-attention modules within the PointNet++ backbone network, enhancing key feature representation in both the channel and spatial dimensions. Experimental results demonstrate that this approach achieves an accuracy of 93.67% and a recall rate of 90.51% in a unified binary classification task for general weld defect detection, effectively identifying both normal welds and complex missed weld defects. Compared to PointConv, Dynamic Graph Convolutional Neural Network (DGCNN), and mainstream Point Cloud Transformer, this method significantly reduces false negative rates while maintaining low computational costs, offering a cost-effective solution for industrial automation.

Schlagwörter

Stichwörter der Autor:innen

PointNet++dual attention mechanismindustrial quality inspectionmonocular depth estimationpseudo-point cloudweld defect detection

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Guangdong Ocean University, Yangjiang 529568, China.
  • College of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China.

Zitieren

APA

Zhao, N., & Chen, S. (2026). Industrial Weld Defect Detection Based on Monocular Depth Estimation and Dual-Attention Point Cloud Network. Sensors, 26(11), 3321. https://doi.org/10.3390/s26113321

Vancouver

Zhao N, Chen S. Industrial Weld Defect Detection Based on Monocular Depth Estimation and Dual-Attention Point Cloud Network. Sensors. 2026;26(11):3321. doi:10.3390/s26113321

BibTeX
@article{Zhao2026,
  author = {Zhao, Nannan and Chen, Shijie},
  title = {Industrial Weld Defect Detection Based on Monocular Depth Estimation and Dual-Attention Point Cloud Network},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3321},
  doi = {10.3390/s26113321}
}
Kostenlos starten →