FDR-YOLO: Feature-Degradation-Aware Feature-Flow Reconstruction for Infrared Tiny UAV Detection
Technologies · 30.07.2026 · 14 (8) · 467
DOI: 10.3390/technologies14080467 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technologies, online erschienen am 30.07.2026. Verfasst von Meiyu He und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Foundation of Shanxi Key Laboratory of Machine Vision and Virtual Reality, Applied Basic Research Program of Shanxi Province.
Abstract (Originalsprache)
Infrared (IR) video target detection is important for long-range target perception in anti-UAV systems under complex lighting and background conditions. However, long-range tiny unmanned aerial vehicles (UAVs) usually occupy only a few pixels, exhibit weak thermal contrast, and are easily disturbed by cluttered backgrounds such as clouds, buildings, vegetation, feature edges, and thermal noise. Although YOLO-style detectors provide high real-time performance, their feature flow is prone to weak target response attenuation during downsampling, contextual ambiguity in deep feature representation, and background clutter propagation during cross-scale fusion. To address these degradation problems, this paper proposes FDR-YOLO, a feature-degradation-aware feature-flow reconstruction network based on YOLOv26. Specifically, LAE-based response-preserving downsampling (LAE-RPD) preserves weak but discriminative target responses during spatial compression; lightweight U-shaped dilated context aggregation (UCDC-Lite) enhances deep contextual discrimination between tiny UAV targets and cluttered backgrounds; and high-frequency prior-guided semantic injection fusion (HPG-SIF) uses shallow high-frequency priors to constrain the injection of deep semantic features. Experiments on multiple datasets show that FDR-YOLO improves detection accuracy while retaining lightweight and low-latency characteristics. On the Anti-UAV dataset, FDR-YOLO improves mAP50 and mAP50–95 by 3.0 and 3.3 percentage points, respectively, over YOLOv26s. Additional experiments on InfraredUAV and the RGB-based UAVSwarm dataset demonstrate the applicability of the proposed design to another infrared benchmark and to visible-light UAV detection under dataset-specific training.
Förderung
- Foundation of Shanxi Key Laboratory of Machine Vision and Virtual Reality
- Applied Basic Research Program of Shanxi Province
Zitieren
APA
He, M., Li, Y., Tian, E., Yang, F., & Han, H. (2026). FDR-YOLO: Feature-Degradation-Aware Feature-Flow Reconstruction for Infrared Tiny UAV Detection. Technologies, 14(8), 467. https://doi.org/10.3390/technologies14080467
Vancouver
He M, Li Y, Tian E, Yang F, Han H. FDR-YOLO: Feature-Degradation-Aware Feature-Flow Reconstruction for Infrared Tiny UAV Detection. Technologies. 2026;14(8):467. doi:10.3390/technologies14080467
BibTeX
@article{He2026,
author = {He, Meiyu and Li, Yufeng and Tian, Erming and Yang, Fuhe and Han, Huiyan},
title = {FDR-YOLO: Feature-Degradation-Aware Feature-Flow Reconstruction for Infrared Tiny UAV Detection},
journal = {Technologies},
year = {2026},
volume = {14},
number = {8},
pages = {467},
doi = {10.3390/technologies14080467}
}
EUVIMED