EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLOv8-PaveDet: Lightweight UAV Pavement Distress Detection With Context-Enhanced Features and Class-Aware Reweighting

Yuchun Li, Yuan Xu

IEEE Access · 2026 · 14 · 96840-96853

DOI: 10.1109/access.2026.3707232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Yuchun Li und 1 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2025 Higher Education Institution Scientific Research Program of Anhui Provincial Department of Education, 2024 University-Level Scientific Research Program of Tongling University, 2024 Talent Research Start-Up Fund Project of Tongling University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution pavement imagery collected by uncrewed aerial vehicles (UAVs) enables scalable, non-intrusive road distress inspection. Combined with lightweight detectors, it supports flexible automated detection of surface distress across large road networks. However, accurate detection remains challenging because thin cracks are visually subtle and easily fragmented, scale variation across UAV altitudes is pronounced, and safety-critical categories such as potholes are severely underrepresented. Existing approaches address these challenges only in isolation: context-enhanced Transformer architectures achieve strong feature modeling but are computationally prohibitive for high-resolution UAV tiles; lightweight detectors preserve efficiency but sacrifice contextual aggregation; and existing long-tail loss functions are designed for generic benchmarks without accounting for the joint difficulty of thin-structure localization and severe class imbalance in UAV pavement scenes. To address these limitations, we propose YOLOv8-PaveDet, a task-oriented extension of YOLOv8n with three coordinated components: GhostConv for efficient backbone computation, ConvFormer-enhanced C2f blocks for long-range spatial aggregation over elongated crack structures, and a lightweight shared-channel detection head (LSCD) for scale-consistent multi-level prediction. A hybrid training loss combining IoU-aware SlideLoss with class-weighted binary cross-entropy provides explicit minority-class rebalancing. Experiments on UAV-PDD show that the architectural modifications raise mAP@0.5 from 62.9% to 73.4% and mAP@0.5:0.95 from 32.4% to 42.5%, while reducing parameters from 3.01M to 1.83M and GFLOPs from 4.10 to 2.78. Adding the hybrid loss further improves mAP@0.5 to 81.68% (Aggressive) and mAP@0.5:0.95 to 45.54% (Conservative), with Pothole AP@0.5 rising from 39.70% to 75.81%. These results demonstrate that coordinated lightweight design, combining contextual aggregation with explicit class rebalancing, achieves a stronger accuracy–efficiency balance for UAV pavement inspection; the resulting detections can serve as upstream sensing inputs for public infrastructure management.

Förderung

  • 2025 Higher Education Institution Scientific Research Program of Anhui Provincial Department of Education
  • 2024 University-Level Scientific Research Program of Tongling University
  • 2024 Talent Research Start-Up Fund Project of Tongling University

Zitieren

APA

Li, Y., & Xu, Y. (2026). YOLOv8-PaveDet: Lightweight UAV Pavement Distress Detection With Context-Enhanced Features and Class-Aware Reweighting. IEEE Access, 14, 96840-96853. https://doi.org/10.1109/access.2026.3707232

Vancouver

Li Y, Xu Y. YOLOv8-PaveDet: Lightweight UAV Pavement Distress Detection With Context-Enhanced Features and Class-Aware Reweighting. IEEE Access. 2026;14:96840-96853. doi:10.1109/access.2026.3707232

BibTeX
@article{Li2026,
  author = {Li, Yuchun and Xu, Yuan},
  title = {YOLOv8-PaveDet: Lightweight UAV Pavement Distress Detection With Context-Enhanced Features and Class-Aware Reweighting},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {96840--96853},
  doi = {10.1109/access.2026.3707232}
}
Kostenlos starten →