EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR

Xiaolong Wei iD, Ling Yin, Liangliang Zhang, Fei Wu

Sensors · 19.11.2024 · 24 (22) · 7376

DOI: 10.3390/s24227376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.11.2024. Verfasst von Xiaolong Wei und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Commission of Shanghai Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For drone-based detection tasks, accurately identifying small-scale targets like people, bicycles, and pedestrians remains a key challenge. In this paper, we propose DV-DETR, an improved detection model based on the Real-Time Detection Transformer (RT-DETR), specifically optimized for small target detection in high-density scenes. To achieve this, we introduce three main enhancements: (1) ResNet18 as the backbone network to improve feature extraction and reduce model complexity; (2) the integration of recalibration attention units and deformable attention mechanisms in the neck network to enhance multi-scale feature fusion and improve localization accuracy; and (3) the use of the Focaler-IoU loss function to better handle the imbalanced distribution of target scales and focus on challenging samples. Experimental results on the VisDrone2019 dataset show that DV-DETR achieves an mAP@0.5 of 50.1%, a 1.7% improvement over the baseline model, while increasing detection speed from 75 FPS to 90 FPS, meeting real-time processing requirements. These improvements not only enhance the model’s accuracy and efficiency but also provide practical significance in complex, high-density urban environments, supporting real-world applications in UAV-based surveillance and monitoring tasks.

Schlagwörter

Stichwörter der Autor:innen

RT-DETR algorithmreal-time tasksmall target detectiontransformer

Autor:innen und Institutionen

  • School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.

ORCID-Profile: Xiaolong Wei

Förderung

  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Wei, X., Yin, L., Zhang, L., & Wu, F. (2024). DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR. Sensors, 24(22), 7376. https://doi.org/10.3390/s24227376

Vancouver

Wei X, Yin L, Zhang L, Wu F. DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR. Sensors. 2024;24(22):7376. doi:10.3390/s24227376

BibTeX
@article{Wei2024,
  author = {Wei, Xiaolong and Yin, Ling and Zhang, Liangliang and Wu, Fei},
  title = {DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {22},
  pages = {7376},
  doi = {10.3390/s24227376}
}
Kostenlos starten →