EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RT-DETR-EVD: An Emergency Vehicle Detection Method Based on Improved RT-DETR

Jun Hu, Jiahao Zheng, Wenwei Wan, Yongqi Zhou, Zhikai Huang

Sensors · 26.05.2025 · 25 (11) · 3327

DOI: 10.3390/s25113327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.05.2025. Verfasst von Jun Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Youth Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid acceleration of urbanization and the increasing volume of road traffic, emergency vehicles frequently encounter congestion when performing urgent tasks. Failure to yield in a timely manner can result in the loss of critical rescue time. Therefore, this study aims to develop a lightweight and high-precision RT-DETR-EVD emergency vehicle detection model to enhance urban emergency response capabilities. The proposed model replaces ResNet with a lightweight CSPDarknet backbone and integrates an innovative hybrid C2f-MogaBlock architecture. A multi-order gated aggregation mechanism is introduced to dynamically fuse multi-scale features, improving spatial-channel feature representation while reducing the number of parameters. Additionally, an Attention-based Intra-scale Feature Interaction Dynamic Position Bias (AIDPB) module is designed, replacing fixed positional encoding with learnable dynamic position bias (DPB), improving feature discrimination in complex scenarios. The experimental results demonstrate that the improved RT-DETR-EVD model achieves superior performance in emergency vehicle detection under the same training conditions. Specifically, compared to the baseline RT-DETR-r18 model, RT-DETR-EVD reduces parameter count to 14.5 M (a 27.1% reduction), lowers floating-point operations (FLOPs) to 49.5 G (a 13.2% reduction), and improves precision by 0.5%. Additionally, recall and mean average precision (mAP50%) increase by 0.6%, reaching an mAP50% of 88.3%. The proposed RT-DETR-EVD model achieves a breakthrough balance between accuracy, efficiency, and scene adaptability. Its unique lightweight design enhances detection accuracy while significantly reducing model size and accelerating inference. This model provides an efficient and reliable solution for smart city emergency response systems, demonstrating strong deployment potential in real-world engineering applications.

Schlagwörter

Stichwörter der Autor:innen

CSPDarknetMogaBlockRT-DETRdynamic position biasemergency vehicle detectionlightweight

Autor:innen und Institutionen

  • School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China.

Förderung

  • National Key R&D Program of China
  • National Youth Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province
  • Jiangxi Ganpo Talented Support Plan -Young science and technology talent Lift Project
  • Jiangxi Provincial Youth Science Fund Project
  • National Key R&D Program of China

Zitieren

APA

Hu, J., Zheng, J., Wan, W., Zhou, Y., & Huang, Z. (2025). RT-DETR-EVD: An Emergency Vehicle Detection Method Based on Improved RT-DETR. Sensors, 25(11), 3327. https://doi.org/10.3390/s25113327

Vancouver

Hu J, Zheng J, Wan W, Zhou Y, Huang Z. RT-DETR-EVD: An Emergency Vehicle Detection Method Based on Improved RT-DETR. Sensors. 2025;25(11):3327. doi:10.3390/s25113327

BibTeX
@article{Hu2025,
  author = {Hu, Jun and Zheng, Jiahao and Wan, Wenwei and Zhou, Yongqi and Huang, Zhikai},
  title = {RT-DETR-EVD: An Emergency Vehicle Detection Method Based on Improved RT-DETR},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {11},
  pages = {3327},
  doi = {10.3390/s25113327}
}
Kostenlos starten →