EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AUHF-DETR: A Lightweight Transformer with Spatial Attention and Wavelet Convolution for Embedded UAV Small Object Detection

Hengyu Guo, Qunyong Wu, Yuhang Wang

Remote Sensing · 31.05.2025 · 17 (11) · 1920

DOI: 10.3390/rs17111920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 31.05.2025. Verfasst von Hengyu Guo und 2 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fujian Provincial Science and Technology Program “University-Industry Cooperation Project”, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time object detection on embedded unmanned aerial vehicles (UAVs) is crucial for emergency rescue, autonomous driving, and target tracking applications. However, UAVs’ hardware limitations create conflicts between model size and detection accuracy. Moreover, challenges such as complex backgrounds from the UAV’s perspective, severe occlusion, densely packed small targets, and uneven lighting conditions complicate real-time detection for embedded UAVs. To tackle these challenges, we propose AUHF-DETR, an embedded detection model derived from RT-DETR. In the backbone, we introduce a novel WTC-AdaResNet paradigm that utilizes reversible connections to decouple small-object features. We further replace the original global attention mechanism with the PSA module to strengthen inter-feature relationships within each ROI, thereby resolving the embedded challenges posed by RT-DETR’s complex token computations. In the encoder, we introduce a BDFPN for multi-scale feature fusion, effectively mitigating the small-object detection difficulties caused by the baseline’s Hungarian assignment. Extensive experiments on the public VisDrone2019, HIT-UAV, and CARPK datasets demonstrate that compared with RT-DETR-r18, AUHF-DETR achieves a 2.1% increase in APs on VisDrone2019, reduces the parameter count by 49.0%, and attains 68 FPS (AGX Xavier), thus satisfying the real-time requirements for small-object detection in embedded UAVs.

Förderung

  • Fujian Provincial Science and Technology Program “University-Industry Cooperation Project”
  • National Natural Science Foundation of China

Zitieren

APA

Guo, H., Wu, Q., & Wang, Y. (2025). AUHF-DETR: A Lightweight Transformer with Spatial Attention and Wavelet Convolution for Embedded UAV Small Object Detection. Remote Sensing, 17(11), 1920. https://doi.org/10.3390/rs17111920

Vancouver

Guo H, Wu Q, Wang Y. AUHF-DETR: A Lightweight Transformer with Spatial Attention and Wavelet Convolution for Embedded UAV Small Object Detection. Remote Sensing. 2025;17(11):1920. doi:10.3390/rs17111920

BibTeX
@article{Guo2025,
  author = {Guo, Hengyu and Wu, Qunyong and Wang, Yuhang},
  title = {AUHF-DETR: A Lightweight Transformer with Spatial Attention and Wavelet Convolution for Embedded UAV Small Object Detection},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {11},
  pages = {1920},
  doi = {10.3390/rs17111920}
}
Kostenlos starten →