EUVIMEDEUVIMED entdecken
Crossref

A Lightweight YOLO26 Pavement Defect Detection Method for Complex Pavement Environments

Borong Zhu, Kaiying Tian, Qihao Xu, Yixuan Wang, Dingyu Wu, Tianyuan Liu

Journal of Big Data and Computing · 2026-06 · 4 (2) · 133-141

DOI: 10.62517/jbdc.202601219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Big Data and Computing, 2026-06. Verfasst von Borong Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 12 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Timely identification of pavement deterioration plays a vital role in upholding traffic safety standards and optimizing the efficiency of road maintenance operations. Current approaches often struggle with extracting discriminative features for small-scale defects embedded in cluttered backgrounds, while surface textures and cast shadows frequently trigger both missed detections and spurious alarms. To overcome these limitations, a lightweight road damage detection framework built upon YOLO26 is presented in this work, specifically tailored for challenging pavement conditions. Taking the recently released YOLO26n model from Ultralytics as the foundation, and while strictly constraining model parameters and underlying computational expenditure, an Efficient Multi-Scale Attention (EMA) mechanism is appended and integrated at the terminal stage of the backbone network to further enhance detection accuracy. Through adaptive orthogonal and cross-spatial calibration of channel-wise feature responses, this mechanism effectively suppresses irrelevant background clutter and reinforces the representational strength of critical damage signatures. Evaluation on the China partition of the publicly available RDD2022 dataset reveals that the proposed E-YOLO26 model attains a Precision of 78.0% and an mAP@0.5 of 74.0%, accompanied by an exceptionally low computational burden of merely 5.9 GFLOPs. These figures correspond to gains of 2.6 and 0.1 percentage points relative to the baseline YOLO26 model, respectively. The findings of this study furnish an optimized computational trade-off solution along with practical engineering support for automated detection on embedded devices deployed in real-world road inspection scenarios.

Zitieren

APA

Zhu, B., Tian, K., Xu, Q., Wang, Y., Wu, D., & Liu, T. (2026). A Lightweight YOLO26 Pavement Defect Detection Method for Complex Pavement Environments. Journal of Big Data and Computing, 4(2), 133-141. https://doi.org/10.62517/jbdc.202601219

Vancouver

Zhu B, Tian K, Xu Q, Wang Y, Wu D, Liu T. A Lightweight YOLO26 Pavement Defect Detection Method for Complex Pavement Environments. Journal of Big Data and Computing. 2026;4(2):133-141. doi:10.62517/jbdc.202601219

BibTeX
@article{Zhu2026,
  author = {Zhu, Borong and Tian, Kaiying and Xu, Qihao and Wang, Yixuan and Wu, Dingyu and Liu, Tianyuan},
  title = {A Lightweight YOLO26 Pavement Defect Detection Method for Complex Pavement Environments},
  journal = {Journal of Big Data and Computing},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {133--141},
  doi = {10.62517/jbdc.202601219}
}
Kostenlos starten →