EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structure-Aware Heterogeneous Dual-Stream Network with Wavelet-Guided Fusion for UAV Infrared–Visible Object Detection

Weijian Jia, Fenghua Wang, Haiwen Zheng, Penglei Hu, Xiaobing Wang, Yao Zhao, Pengdong Zhang, Yufei Gao

Drones · 11.08.2026 · 10 (8) · 614

DOI: 10.3390/drones10080614 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 11.08.2026. Verfasst von Weijian Jia und 7 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: research grants from the People’s Republic of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the susceptibility of single-modality approaches to illumination variations and imaging conditions in low-altitude unmanned aerial vehicle (UAV) detection, this study proposes a structure-aware heterogeneous dual-stream detection network based on infrared and visible-light fusion. First, a multimodal UAV detection dataset oriented toward complex low-altitude scenarios is constructed, providing a data foundation for cross-modal detection research. Then, a structure-aware heterogeneous dual-stream feature extraction framework is designed to enable collaborative modeling of visible-light and infrared features through modality-specific encoding. In the visible-light branch, a Structure-Aware Gated Enhancement Block (SAGE Block) is introduced to enhance the representation of fine-grained structural and edge information. In the cross-modal fusion stage, a Bidirectional Wavelet-Guided Fusion Module (BWFM) is proposed to decouple structural semantics and detailed information in the frequency domain. Adaptive fusion is further achieved through low-frequency cross-modal interaction and high-frequency detail-preservation strategies. Finally, the proposed method is experimentally validated on the proposed Multispectral UAV Detection Dataset (MUDD) and the Multi-scenario Multi-Modality Fusion Dataset (M3FD).. The experimental results show that the proposed method achieves an mAP@0.5 of 0.9680 and an mAP@0.5:0.95 of 0.6794 on the proposed MUDD, as well as an mAP@0.5:0.95 of 0.6072 on the M3FD dataset, demonstrating competitive detection accuracy and generalization capability. Ablation experiments further indicate that the SAGE Block, BWFM, and the low-frequency cross-modal fusion and high-frequency detail-preservation strategies within BWFM all contribute positively to performance improvement.

Förderung

  • research grants from the People’s Republic of China

Zitieren

APA

Jia, W., Wang, F., Zheng, H., Hu, P., Wang, X., Zhao, Y., Zhang, P., & Gao, Y. (2026). Structure-Aware Heterogeneous Dual-Stream Network with Wavelet-Guided Fusion for UAV Infrared–Visible Object Detection. Drones, 10(8), 614. https://doi.org/10.3390/drones10080614

Vancouver

Jia W, Wang F, Zheng H, Hu P, Wang X, Zhao Y, et al. Structure-Aware Heterogeneous Dual-Stream Network with Wavelet-Guided Fusion for UAV Infrared–Visible Object Detection. Drones. 2026;10(8):614. doi:10.3390/drones10080614

BibTeX
@article{Jia2026,
  author = {Jia, Weijian and Wang, Fenghua and Zheng, Haiwen and Hu, Penglei and Wang, Xiaobing and Zhao, Yao and Zhang, Pengdong and Gao, Yufei},
  title = {Structure-Aware Heterogeneous Dual-Stream Network with Wavelet-Guided Fusion for UAV Infrared–Visible Object Detection},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {8},
  pages = {614},
  doi = {10.3390/drones10080614}
}
Kostenlos starten →