EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Structure-Aware Deep Learning Framework for Automated Bridge Inspection Integrating SegFormer-Based Structural Member Segmentation and YOLOv8 Damage Detection

Sushama De Silva, Pang-Jo Chun iD

Sensors · 04.07.2026 · 26 (13) · 4255

DOI: 10.3390/s26134255 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.07.2026. Verfasst von Sushama De Silva und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Engineering Innovation, School of Engineering, The University of Tokyo, Tokyo 113-8656, Japan. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Public Works Research Institute, JSPS Grant-in-Aid for Scientific Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a pilot-scale feasibility study, aging bridge infrastructure and limited inspection resources have created an urgent need for automated and reliable bridge condition assessment systems. Most existing deep learning-based inspection approaches detect damage types from images without considering the structural member on which the damage occurs, limiting their practical utility for maintenance decision-making. This study proposes a structure-aware deep learning framework for automated bridge inspection that integrates structural member segmentation, two-class damage detection, and spatial damage-to-member association within a unified pipeline. A SegFormer-based semantic segmentation model was trained on a custom bridge inspection dataset comprising 1339 images to identify three primary structural member classes—main girder, deck slab, and abutment—achieving a test mean Intersection over Union (mIoU) of 0.851. Boundary refinement using the Segment Anything Model (SAM) in mask-prompt mode was applied to improve mask precision during training data preparation. A YOLOv8s object detection model was trained on a custom bridge damage dataset of 9142 annotated images (6531 training, 1740 validation, and 871 test images) to detect two damage classes—crack and corrosion—achieving a mean Average Precision (mAP50) of 0.445 at a confidence threshold of 0.30. The framework associates detected damage with segmented structural members using a region-based spatial assignment strategy, enabling structure-aware outputs such as “crack on main girder” and “corrosion on deck slab.” Manual evaluation on 100 bridge inspection images demonstrated a fully correct damage detection accuracy of 70.0% and a fully correct member assignment accuracy of 62.0%. When partially correct predictions were additionally considered for qualitative analysis, the corresponding accuracies increased to 84.0% and 87.0%, respectively. The main girder class achieved the highest combined accuracy for both damage detection (90.9%) and member assignment (93.9%). These results demonstrate the potential of the proposed framework as a first layer for AI-assisted bridge inspection by associating detected damage with structural members, providing structured inspection information to support subsequent maintenance assessment and infrastructure monitoring.

Schlagwörter

Stichwörter der Autor:innen

SegFormerSegment Anything ModelYOLOv8bridge inspectiondamage detectiondamage-to-member associationdeep learningsemantic segmentationspatial damage mappingstructural member segmentationstructure-aware analysis

Autor:innen und Institutionen

  • Institute of Engineering Innovation, School of Engineering, The University of Tokyo, Tokyo 113-8656, Japan.

ORCID-Profile: Pang-Jo Chun

Förderung

  • Public Works Research Institute
  • JSPS Grant-in-Aid for Scientific Research

Zitieren

APA

De Silva, S., & Chun, P. J. (2026). A Structure-Aware Deep Learning Framework for Automated Bridge Inspection Integrating SegFormer-Based Structural Member Segmentation and YOLOv8 Damage Detection. Sensors, 26(13), 4255. https://doi.org/10.3390/s26134255

Vancouver

De Silva S, Chun PJ. A Structure-Aware Deep Learning Framework for Automated Bridge Inspection Integrating SegFormer-Based Structural Member Segmentation and YOLOv8 Damage Detection. Sensors. 2026;26(13):4255. doi:10.3390/s26134255

BibTeX
@article{DeSilva2026,
  author = {De Silva, Sushama and Chun, Pang-Jo},
  title = {A Structure-Aware Deep Learning Framework for Automated Bridge Inspection Integrating SegFormer-Based Structural Member Segmentation and YOLOv8 Damage Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4255},
  doi = {10.3390/s26134255}
}
Kostenlos starten →