FSA-DETR: A Frequency-Aware and Structure-Aligned DETR for Small-Object Detection in UAV Aerial Imagery
Electronics · 19.08.2026 · 15 (16) · 3701
DOI: 10.3390/electronics15163701 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 19.08.2026. Verfasst von Hong Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Shuguang Plan Project, Shanghai Rising-Star Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Small objects in unmanned aerial vehicle (UAV) imagery often occupy only a few pixels, making their responses vulnerable to downsampling, cluttered backgrounds, and cross-scale feature misalignment. Most detector improvements handle backbone representation, encoder context modeling, and neck fusion as separate design choices, so the frequency structure of tiny targets and the geometric consistency of multi-scale features remain underused. FSA-DETR addresses this gap with a frequency-aware and structure-aligned design built on Real-Time Detection Transformer (RT-DETR). Its central idea is to treat UAV small-object detection as a frequency–structure representation problem: high-frequency target cues are enhanced in the backbone and encoder, while local structural orientation is aligned during cross-scale fusion. The design combines a Cross-stage Spectral-Aware Multi-scale Block, a Wavelet-enhanced Intra-scale Transformer Encoder, and a Spectral Orientation-Aligned Fusion module. On VisDrone2019, FSA-DETR achieves 21.5% AP and 37.5% AP50, improving the RT-DETR baseline by 1.6% and 2.4%, respectively, while reducing the computational cost to 48.8 GFLOPs and the parameter count to 15.04 M. The small-object metric APs increases by 1.3%, and the broader size-stratified gains indicate improved sensitivity to aerial targets across multiple scales. On AI-TOD, FSA-DETR obtains 22.5% AP and 51.9% AP50, suggesting that the same frequency–structure design transfers to extremely tiny objects. Under the reported benchmark protocol, explicitly coupling frequency-sensitive perception with structure-aligned fusion improves UAV small-object detection while keeping the complete model smaller than the RT-DETR baseline used in this study; this suggests that separating spectral discrimination from geometric alignment is a useful design pattern for UAV detectors.
Förderung
- Shanghai Shuguang Plan Project
- Shanghai Rising-Star Program
- National Natural Science Foundation of China
- Shanghai Gas Turbine Union Innovation Center Project
Zitieren
APA
Liu, H., Ling, Z., Yang, W., Wang, Y., & Xia, L. (2026). FSA-DETR: A Frequency-Aware and Structure-Aligned DETR for Small-Object Detection in UAV Aerial Imagery. Electronics, 15(16), 3701. https://doi.org/10.3390/electronics15163701
Vancouver
Liu H, Ling Z, Yang W, Wang Y, Xia L. FSA-DETR: A Frequency-Aware and Structure-Aligned DETR for Small-Object Detection in UAV Aerial Imagery. Electronics. 2026;15(16):3701. doi:10.3390/electronics15163701
BibTeX
@article{Liu2026,
author = {Liu, Hong and Ling, Zihui and Yang, Wenxian and Wang, Yefan and Xia, Linqing},
title = {FSA-DETR: A Frequency-Aware and Structure-Aligned DETR for Small-Object Detection in UAV Aerial Imagery},
journal = {Electronics},
year = {2026},
volume = {15},
number = {16},
pages = {3701},
doi = {10.3390/electronics15163701}
}
EUVIMED