EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection

Yutian Jiang, Haotian Yan, Yiru Zhang, Keqiang Wu, Ruiyuan Liu, Ciyun Lin iD

Sensors · 03.10.2023 · 23 (19) · 8241

DOI: 10.3390/s23198241 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.10.2023. Verfasst von Yutian Jiang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Transportation, Jilin University, Changchun 130022, China. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qingdao Social Science Planning Research Project, Scientific Research Project of the Education Department of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road defect detection is a crucial aspect of road maintenance projects, but traditional manual methods are time-consuming, labor-intensive, and lack accuracy. Leveraging deep learning frameworks for object detection offers a promising solution to these challenges. However, the complexity of backgrounds, low resolution, and similarity of cracks make detecting road cracks with high accuracy challenging. To address these issues, a novel road crack detection algorithm, termed Road Defect Detection YOLOv5 (RDD-YOLOv5), was proposed. Firstly, a model was proposed to integrate the transformer structure and explicit vision center to capture the long-distance dependency and aggregate key characteristics. Additionally, the Sigmoid-weighted linear activations in YOLOv5 were replaced with the Gaussian Error Linear Units to enhance the model’s nonlinear fitting capability. To evaluate the algorithm’s performance, a UAV flight platform was constructed, and experimental freebies were provided to boost inspection efficiency. The experimental results demonstrate the effectiveness of RDD-YOLOv5, achieving a mean average precision of 91.48%, surpassing the original YOLOv5 by 2.5%. The proposed model proves its ability to accurately identify road cracks, even under challenging and complex traffic backgrounds. This advancement in road crack detection technology has significant implications for improving road maintenance and safety.

Schlagwörter

Stichwörter der Autor:innen

GELUYOLOv5deep learningroad crack detectiontransformer

Autor:innen und Institutionen

  • College of Transportation, Jilin University, Changchun 130022, China.
  • College of Communication Engineering, Jilin University, Changchun 130022, China.
  • Jilin Engineering Research Center for Intelligent Transportation System, Changchun 130022, China.

ORCID-Profile: Ciyun Lin

Förderung

  • Qingdao Social Science Planning Research Project
  • Scientific Research Project of the Education Department of Jilin Province

Zitieren

APA

Jiang, Y., Yan, H., Zhang, Y., Wu, K., Liu, R., & Lin, C. (2023). RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection. Sensors, 23(19), 8241. https://doi.org/10.3390/s23198241

Vancouver

Jiang Y, Yan H, Zhang Y, Wu K, Liu R, Lin C. RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection. Sensors. 2023;23(19):8241. doi:10.3390/s23198241

BibTeX
@article{Jiang2023,
  author = {Jiang, Yutian and Yan, Haotian and Zhang, Yiru and Wu, Keqiang and Liu, Ruiyuan and Lin, Ciyun},
  title = {RDD-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {19},
  pages = {8241},
  doi = {10.3390/s23198241}
}
Kostenlos starten →