EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Improved YOLOv8 with TransXNet Backbone for Pavement Crack Detection

Zitao Du, Yuna Yin, Wenbo Yang

Applied Sciences · 20.04.2026 · 16 (8) · 3982

DOI: 10.3390/app16083982 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 20.04.2026. Verfasst von Zitao Du und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the accuracy and efficiency of road crack detection, this paper proposes an enhanced model based on You Only Look Once version 8 (YOLOv8). The Cross Stage Partial DarkNet (CSPDarkNet) backbone network is replaced with TransXNet, which integrates a Transformer-based self-attention mechanism with convolutional operations to better capture local features. By embedding the attention mechanism into its core module, namely the dual dynamic token mixer (D-Mixer), the TransXNet architecture is further optimized, thereby enabling coordinated attention-based feature selection and enhancement across both global and local dimensions. In addition, the Gaussian Error Linear Unit (GELU) is employed to enhance nonlinear representation capability and training stability. Experiments were conducted on the public Road Damage Dataset 2022 (RDD2022), which contains approximately 47,000 road images. The results demonstrate that, compared with the baseline model, the precision, recall, and mean Average Precision (mAP) of the proposed method are improved by 9.6, 11.7, and 8.2 percentage points, respectively; moreover, the detection accuracy and computational efficiency also outperform those of other methods.

Zitieren

APA

Du, Z., Yin, Y., & Yang, W. (2026). An Improved YOLOv8 with TransXNet Backbone for Pavement Crack Detection. Applied Sciences, 16(8), 3982. https://doi.org/10.3390/app16083982

Vancouver

Du Z, Yin Y, Yang W. An Improved YOLOv8 with TransXNet Backbone for Pavement Crack Detection. Applied Sciences. 2026;16(8):3982. doi:10.3390/app16083982

BibTeX
@article{Du2026,
  author = {Du, Zitao and Yin, Yuna and Yang, Wenbo},
  title = {An Improved YOLOv8 with TransXNet Backbone for Pavement Crack Detection},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {3982},
  doi = {10.3390/app16083982}
}
Kostenlos starten →