EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ACD-DETR: Adaptive Cross-Scale Detection Transformer for Small Object Detection in UAV Imagery

Yang Tong, Hui Ye, Jishen Yang iD, Xiulong Yang iD

Sensors · 05.09.2025 · 25 (17) · 5556

DOI: 10.3390/s25175556 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.09.2025. Verfasst von Yang Tong und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Central China Normal University, Wuhan 430079, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small object detection in UAV imagery remains challenging due to complex aerial perspectives and the presence of dense, small targets with blurred boundaries. To address these challenges, we propose ACD-DETR, an adaptive end-to-end Transformer detector tailored for UAV-based small object detection. The framework introduces three core modules: the Multi-Scale Edge-Enhanced Feature Fusion Module (MSEFM) to preserve fine-grained details; the Omni-Grained Boundary Calibrator (OG-BC) for boundary-aware semantic fusion; and the Dynamic Position Bias Attention-based Intra-scale Feature Interaction (DPB-AIFI) to enhance spatial reasoning. Furthermore, we introduce ACD-DETR-SBA+, a fusion-enhanced variant that removes OG-BC and DPB-AIFI while deploying densely connected Semantic–Boundary Aggregation (SBA) modules to intensify boundary–semantic fusion. This design sacrifices computational efficiency in exchange for higher detection precision, making it suitable for resource-rich deployment scenarios. On the VisDrone2019 dataset, ACD-DETR achieves 50.9% mAP@0.5, outperforming the RT-DETR-R18 baseline by 3.6 percentage points, while reducing parameters by 18.5%. ACD-DETR-SBA+ further improves accuracy to 52.0% mAP@0.5, demonstrating the benefit of SBA-based fusion. Extensive experiments on the VisDrone2019 and DOTA datasets demonstrate that ACD-DETR achieves a state-of-the-art trade-off between accuracy and efficiency, while ACD-DETR-SBA+ achieves further performance improvements at higher computational cost. Ablation studies and visual analyses validate the effectiveness of the proposed modules and design strategies.

Schlagwörter

Stichwörter der Autor:innen

Transformeredge enhancementfeature fusionpositional encodingsmall object detection

Autor:innen und Institutionen

  • School of Computer Science, Central China Normal University, Wuhan 430079, China.
  • Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA.
  • Amazon, Seattle, WA 98109, USA.
  • Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan 430079, China.

ORCID-Profile: Jishen Yang, Xiulong Yang

Förderung

  • Natural Science Foundation of Hubei Province
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Tong, Y., Ye, H., Yang, J., & Yang, X. (2025). ACD-DETR: Adaptive Cross-Scale Detection Transformer for Small Object Detection in UAV Imagery. Sensors, 25(17), 5556. https://doi.org/10.3390/s25175556

Vancouver

Tong Y, Ye H, Yang J, Yang X. ACD-DETR: Adaptive Cross-Scale Detection Transformer for Small Object Detection in UAV Imagery. Sensors. 2025;25(17):5556. doi:10.3390/s25175556

BibTeX
@article{Tong2025,
  author = {Tong, Yang and Ye, Hui and Yang, Jishen and Yang, Xiulong},
  title = {ACD-DETR: Adaptive Cross-Scale Detection Transformer for Small Object Detection in UAV Imagery},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {17},
  pages = {5556},
  doi = {10.3390/s25175556}
}
Kostenlos starten →