EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Asymmetric Spatial–Frequency Fusion Network for Infrared and Visible Object Detection

Jing Liu, Jing Gao, Xiaoyong Liu, Junjie Tao, Jun Ma, Chaoping Guo, Peijun Shi, Pan Li

Symmetry · 17.12.2025 · 17 (12) · 2174

DOI: 10.3390/sym17122174 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 17.12.2025. Verfasst von Jing Liu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared and visible image fusion-based object detection is critical for robust environmental perception under adverse conditions, yet existing methods still suffer from insufficient modeling of modality discrepancies and limited adaptivity in their fusion mechanisms. This work proposes an asymmetric spatial–frequency fusion network, AsyFusionNet. The network adopts an asymmetric dual-branch backbone that extends the RGB branch to P5 while truncating the infrared branch at P4, thereby better aligning with the physical characteristics of the two modalities, enhancing feature complementarity, and enabling fine-grained modeling of modality differences. On top of this backbone, a local–global attention fusion (LGAF) module is introduced to model local and global attention in parallel and reorganize them through lightweight convolutions, achieving joint spatial–channel selective enhancement. Modality-specific feature enhancement is further realized via a hierarchical attention module (HAM) in the RGB branch, which employs dynamic kernel selection to emphasize multi-level texture details, and a fourier spatial spectral modulation (FS2M) module in the infrared branch, which more effectively captures global thermal radiation patterns. Extensive experiments on the M3FD and VEDAI datasets demonstrate that AsyFusionNet attains 86.3% and 54.1%mAP50, respectively, surpassing the baseline by 8.8 and 6.4 points (approximately 11.4% and 13.4% relative gains) while maintaining real-time inference speed.

Zitieren

APA

Liu, J., Gao, J., Liu, X., Tao, J., Ma, J., Guo, C., Shi, P., & Li, P. (2025). Asymmetric Spatial–Frequency Fusion Network for Infrared and Visible Object Detection. Symmetry, 17(12), 2174. https://doi.org/10.3390/sym17122174

Vancouver

Liu J, Gao J, Liu X, Tao J, Ma J, Guo C, et al. Asymmetric Spatial–Frequency Fusion Network for Infrared and Visible Object Detection. Symmetry. 2025;17(12):2174. doi:10.3390/sym17122174

BibTeX
@article{Liu2025,
  author = {Liu, Jing and Gao, Jing and Liu, Xiaoyong and Tao, Junjie and Ma, Jun and Guo, Chaoping and Shi, Peijun and Li, Pan},
  title = {Asymmetric Spatial–Frequency Fusion Network for Infrared and Visible Object Detection},
  journal = {Symmetry},
  year = {2025},
  volume = {17},
  number = {12},
  pages = {2174},
  doi = {10.3390/sym17122174}
}
Kostenlos starten →