TAF-YOLO: A Small-Object Detection Network for UAV Aerial Imagery via Visible and Infrared Adaptive Fusion
Remote Sensing · 05.12.2025 · 17 (24) · 3936
DOI: 10.3390/rs17243936 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 05.12.2025. Verfasst von Zhanhong Zhuo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key R&D Program of Shaanxi Province, Shannxi Sanqin Elite Special Support Program.
Abstract (Originalsprache)
Detecting small objects from UAV-captured aerial imagery is a critical yet challenging task, hindered by factors such as small object size, complex backgrounds, and subtle inter-class differences. Single-modal methods lack the robustness for all-weather operation, while existing multimodal solutions are often too computationally expensive for deployment on resource-constrained UAVs. To this end, we propose TAF-YOLO, a lightweight and efficient multimodal detection framework designed to balance accuracy and efficiency. First, we propose an early fusion module, the Two-branch Adaptive Fusion Network (TAFNet), which adaptively integrates visible and infrared information at both pixel and channel levels before the feature extractor, maximizing complementary data while minimizing redundancy. Second, we propose a Large Adaptive Selective Kernel (LASK) module that dynamically expands the receptive field using multi-scale convolutions and spatial attention, preserving crucial details of small objects during downsampling. Finally, we present an optimized feature neck architecture that replaces PANet’s bidirectional path with a more efficient top-down pathway. This is enhanced by a Dual-Stream Attention Bridge (DSAB) that injects high-level semantics into low-level features, improving localization without significant computational overhead. On the VEDAI benchmark, TAF-YOLO achieves 67.2% mAP50, outperforming the CFT model by 2.7% and demonstrating superior performance against seven other YOLO variants. Our work presents a practical and powerful solution that enables real-time, all-weather object detection on resource-constrained UAVs.
Förderung
- National Natural Science Foundation of China
- Key R&D Program of Shaanxi Province
- Shannxi Sanqin Elite Special Support Program
Zitieren
APA
Zhuo, Z., Lu, R., Yao, Y., Wang, S., Zheng, Z., Zhang, J., & Yang, X. (2025). TAF-YOLO: A Small-Object Detection Network for UAV Aerial Imagery via Visible and Infrared Adaptive Fusion. Remote Sensing, 17(24), 3936. https://doi.org/10.3390/rs17243936
Vancouver
Zhuo Z, Lu R, Yao Y, Wang S, Zheng Z, Zhang J, et al. TAF-YOLO: A Small-Object Detection Network for UAV Aerial Imagery via Visible and Infrared Adaptive Fusion. Remote Sensing. 2025;17(24):3936. doi:10.3390/rs17243936
BibTeX
@article{Zhuo2025,
author = {Zhuo, Zhanhong and Lu, Ruitao and Yao, Yongxiang and Wang, Siyu and Zheng, Zhi and Zhang, Jing and Yang, Xiaogang},
title = {TAF-YOLO: A Small-Object Detection Network for UAV Aerial Imagery via Visible and Infrared Adaptive Fusion},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {24},
pages = {3936},
doi = {10.3390/rs17243936}
}
EUVIMED