EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Superpixel Texture Analysis for Crack Detection in Multi-Modal Infrastructure Images

Sara Shahsavarani, Clemente Ibarra-Castanedo, Fernando Lopez, Xavier P. V. Maldague

NDT · 2024

DOI: 10.3390/ndt2020008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NDT, 2024. Verfasst von Sara Shahsavarani und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Sciences and Engineering Council of Canada (NSERC), CREATE-oN DuTy Program, Canada Research Chair in Multipolar Infrared Vision, Canada Foundation for Innovation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared and visible imaging play crucial roles in non-destructive testing, where accurate defect segmentation and detection are paramount. However, the scarcity of annotated training data or the limited number of data availability often poses a challenge. To address this, we propose an innovative framework tailored to the domain of infrared and visible imaging, integrating segmentation and detection tasks. The proposed approach eliminates the dependency on annotated defect data during training, enabling models to adapt to real-world scenarios with limited annotations. By utilizing super-pixel segmentation and texture analysis, the proposed method enhances the accuracy of defect detection. Concrete structures, globally subjected to aging and degradation, demand constant monitoring for structural health. Traditional manual crack detection methods are labor-intensive, necessitating automated systems. The proposed approach combines deep learning-based super-pixel segmentation with texture analysis, offering a solution for limited-defect-data situations. Utilizing convolutional neural networks (CNNs) for super-pixel segmentation and texture features for defect analysis, the proposed methodology improves the efficiency and accuracy of crack detection, especially in scenarios with limited labeled data or a limited number of data available. Evaluation on public benchmark datasets have validated the effectiveness of the proposed approach in detecting cracks in concrete structures.

Förderung

  • The Natural Sciences and Engineering Council of Canada (NSERC), CREATE-oN DuTy Program
  • Canada Research Chair in Multipolar Infrared Vision
  • Canada Foundation for Innovation

Zitieren

APA

Shahsavarani, S., Ibarra-Castanedo, C., Lopez, F., & Maldague, X. P. V. (2024). Deep Learning-Based Superpixel Texture Analysis for Crack Detection in Multi-Modal Infrastructure Images. NDT. https://doi.org/10.3390/ndt2020008

Vancouver

Shahsavarani S, Ibarra-Castanedo C, Lopez F, Maldague XPV. Deep Learning-Based Superpixel Texture Analysis for Crack Detection in Multi-Modal Infrastructure Images. NDT. 2024. doi:10.3390/ndt2020008

BibTeX
@article{Shahsavarani2024,
  author = {Shahsavarani, Sara and Ibarra-Castanedo, Clemente and Lopez, Fernando and Maldague, Xavier P. V.},
  title = {Deep Learning-Based Superpixel Texture Analysis for Crack Detection in Multi-Modal Infrastructure Images},
  journal = {NDT},
  year = {2024},
  doi = {10.3390/ndt2020008}
}
Kostenlos starten →