EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatial–Frequency Response Aware Synergy for Small-Object Detection in UAV Aerial Imagery

Dejie Luan, Chunlong Yang, Chunjie Zhang, Peng Li

Algorithms · 21.08.2026 · 19 (8) · 699

DOI: 10.3390/a19080699 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 21.08.2026. Verfasst von Dejie Luan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-altitude UAV aerial imagery often has complex backgrounds with densely distributed small objects, posing challenges to accurate small-object detection. To address these problems, we propose a spatial–frequency response aware synergistic network for small-object detection in low-altitude UAV aerial imagery. A Frequency-Response-Aware Enhancement Module (FRAEM) is designed to effectively extract discriminative features. The module employs a deterministic stage-aware filtering strategy: Scharr-based edge-sensitive filtering is used in the shallow stage, whereas Gaussian smoothing is used in deeper stages, enabling complementary enhancement of hierarchical representations. A Detail Feature Fusion module (DFFusion) is then developed to improve the efficiency of multi-scale feature fusion. The existing Content-Aware Reassembly of Features (CARAFE) operator is employed for content-aware upsampling and feature alignment, after which DFFusion uses learnable scalar weighting to integrate high-resolution detail information with low-resolution contextual information. A Lightweight Adaptive Decoupled Head (LADH) is also designed to reduce complexity. LADH asymmetrically allocates computational capacity across the prediction tasks: the confidence branch retains stronger spatial processing, whereas the classification and regression branches use lightweight projections; depthwise separable convolution serves as an efficiency-oriented implementation choice. Experiments on the VisDrone2019 and DOTA-v2.0 datasets demonstrate that the proposed method can achieve balance between detection performance and model complexity over mainstream detection methods. Ablation experiments also prove the effectiveness of the proposed components.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Luan, D., Yang, C., Zhang, C., & Li, P. (2026). Spatial–Frequency Response Aware Synergy for Small-Object Detection in UAV Aerial Imagery. Algorithms, 19(8), 699. https://doi.org/10.3390/a19080699

Vancouver

Luan D, Yang C, Zhang C, Li P. Spatial–Frequency Response Aware Synergy for Small-Object Detection in UAV Aerial Imagery. Algorithms. 2026;19(8):699. doi:10.3390/a19080699

BibTeX
@article{Luan2026,
  author = {Luan, Dejie and Yang, Chunlong and Zhang, Chunjie and Li, Peng},
  title = {Spatial–Frequency Response Aware Synergy for Small-Object Detection in UAV Aerial Imagery},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {8},
  pages = {699},
  doi = {10.3390/a19080699}
}
Kostenlos starten →