EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HCLOD-Net: Hierarchical Contrastive Learning Guided Object Detection Network for Low-Light UAV Conditions

You Wang, Jiayi Xu, Mengting Lin, Lu Dong, Gui Fu, Keye Yan

Drones · 02.08.2026 · 10 (8) · 592

DOI: 10.3390/drones10080592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 02.08.2026. Verfasst von You Wang und 5 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program Project of Xizang Autonomous Region, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the performance degradation of UAV object detection under low-light conditions, we develop an end-to-end object detection network. This proposed method integrates contrastive learning into the detection framework and establishes feature consistency constraints between low-light and normal-light images through a hierarchical contrastive selection encoder. Since the encoder is required only during training and removed during inference, the proposed framework improves feature robustness without introducing additional inference cost. To further improve object detection accuracy, Frequency Guided Dynamic Attention (FGDA) is introduced into the object detection network, focusing on resolving the issue of redundant interference during feature transmission and enhancing feature representation capability. To improve multi-level spatial feature fusion, an Adaptive Gated Dual-Spatial Fusion (AGDSF) module is further developed, which adaptively strengthens target-relevant responses while weakening background noise. According to the experiments on the VisDrone (dark) dataset and a self-collected nighttime UAV-dark dataset illustrate that the proposed method ensures heightened detection accuracy with low computational overhead, complying with the real-time and robustness requirements of UAV perception in low-light contexts.

Förderung

  • Key Research and Development Program Project of Xizang Autonomous Region
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Wang, Y., Xu, J., Lin, M., Dong, L., Fu, G., & Yan, K. (2026). HCLOD-Net: Hierarchical Contrastive Learning Guided Object Detection Network for Low-Light UAV Conditions. Drones, 10(8), 592. https://doi.org/10.3390/drones10080592

Vancouver

Wang Y, Xu J, Lin M, Dong L, Fu G, Yan K. HCLOD-Net: Hierarchical Contrastive Learning Guided Object Detection Network for Low-Light UAV Conditions. Drones. 2026;10(8):592. doi:10.3390/drones10080592

BibTeX
@article{Wang2026,
  author = {Wang, You and Xu, Jiayi and Lin, Mengting and Dong, Lu and Fu, Gui and Yan, Keye},
  title = {HCLOD-Net: Hierarchical Contrastive Learning Guided Object Detection Network for Low-Light UAV Conditions},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {8},
  pages = {592},
  doi = {10.3390/drones10080592}
}
Kostenlos starten →