EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HAFusionNet: Visible-Thermal Image Fusion with Cross-Modal Interaction for High-Altitude Substation Defect Detection

Donghua Xiao, Linghao Zhang, Siyu Xiang, Hongli Liu, Junwei Kuang, Yongbin Yu, Xiangxiang Wang

Processes · 05.11.2026 · 14 (21) · 3575

DOI: 10.3390/pr14213575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 05.11.2026. Verfasst von Donghua Xiao und 6 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of State Grid Sichuan Electric Power Company.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Defect detection in high-altitude substations is severely complicated by harsh environmental conditions such as low oxygen, strong ultraviolet radiation, and extreme temperature variations, which markedly limit the reliability of traditional single-modal methods. To address these issues, we propose HAFusionNet, a multimodal defect detection network that fuses visible and thermal imagery for robust equipment inspection in extreme environments. The network is built around three complementary modules: a Gated Cross-Modal Interaction (GCMI) module that performs attention-based, gated feature exchange between the two modalities; an Edge-Guided Difference Gated Fusion (EDGF) module that emphasises modality-complementary differences and boundary cues; and a lightweight Attention-guided Spatial Reweighting (ASR) module for efficient spatial feature refinement. These modules are embedded in a dual-stream backbone with enhanced multi-scale fusion. On a self-constructed high-altitude substation defect dataset, HAFusionNet attains an mAP50 of 0.956, and an mAP50:95 of 0.742, outperforming existing multimodal detectors while remaining efficient. This work offers an effective and robust solution for intelligent defect detection of power equipment in extreme high-altitude environments.

Förderung

  • Science and Technology Project of State Grid Sichuan Electric Power Company

Zitieren

APA

Xiao, D., Zhang, L., Xiang, S., Liu, H., Kuang, J., Yu, Y., & Wang, X. (2026). HAFusionNet: Visible-Thermal Image Fusion with Cross-Modal Interaction for High-Altitude Substation Defect Detection. Processes, 14(21), 3575. https://doi.org/10.3390/pr14213575

Vancouver

Xiao D, Zhang L, Xiang S, Liu H, Kuang J, Yu Y, et al. HAFusionNet: Visible-Thermal Image Fusion with Cross-Modal Interaction for High-Altitude Substation Defect Detection. Processes. 2026;14(21):3575. doi:10.3390/pr14213575

BibTeX
@article{Xiao2026,
  author = {Xiao, Donghua and Zhang, Linghao and Xiang, Siyu and Liu, Hongli and Kuang, Junwei and Yu, Yongbin and Wang, Xiangxiang},
  title = {HAFusionNet: Visible-Thermal Image Fusion with Cross-Modal Interaction for High-Altitude Substation Defect Detection},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {21},
  pages = {3575},
  doi = {10.3390/pr14213575}
}
Kostenlos starten →