EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transmission Tower Structural Feature Localization Using Gated Contextual Fusion and Bidirectional Refinement

Ting Zeng, Yueqing Chen, Xiangmei Kong, Mingpeng Yuan, Xin Hu, Haoyu Chen, Ruifeng Liu

Electronics · 15.11.2026 · 15 (22) · 5309

DOI: 10.3390/electronics15225309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 15.11.2026. Verfasst von Ting Zeng und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study adapts RT-DETR for two-dimensional bounding-box localization of upper and lower structural connection regions on transmission towers. The architecture combines a C2f_SHSA_CGLU backbone, deformable encoder attention, and SBA_fused with a high-resolution P2 level. The private dataset contains 818 images and 12,541 boxes. The 655-image training split is paired with a 163-image validation split used for both checkpoint selection and performance reporting. There is no independent test partition for the private task. On this validation split, our seed 0 achieves an AP of 59.14% and a small-object AP of 52.06%, compared with 56.68% and 44.88% for RT-DETR-r18. The backbone controls show no consistent CGLU accuracy benefit. In a separate three-seed ablation, the P2 and SBA_fused configuration achieves an AP of 58.33 ± 0.79%, compared with 55.67 ± 0.69% when both are omitted. On the five-class public STN PLAD benchmark, our model achieves an AP of 37.53 ± 4.51% versus 44.18 ± 1.26% for RT-DETR-r18. The observed gains apply to the private validation setting. Generalization of the private labels to independent scenes remains unverified. The desktop file-input pipeline reaches 14.94 FPS on an NVIDIA GeForce RTX 3090 (NVIDIA Corporation, Santa Clara, CA, USA).

Zitieren

APA

Zeng, T., Chen, Y., Kong, X., Yuan, M., Hu, X., Chen, H., & Liu, R. (2026). Transmission Tower Structural Feature Localization Using Gated Contextual Fusion and Bidirectional Refinement. Electronics, 15(22), 5309. https://doi.org/10.3390/electronics15225309

Vancouver

Zeng T, Chen Y, Kong X, Yuan M, Hu X, Chen H, et al. Transmission Tower Structural Feature Localization Using Gated Contextual Fusion and Bidirectional Refinement. Electronics. 2026;15(22):5309. doi:10.3390/electronics15225309

BibTeX
@article{Zeng2026,
  author = {Zeng, Ting and Chen, Yueqing and Kong, Xiangmei and Yuan, Mingpeng and Hu, Xin and Chen, Haoyu and Liu, Ruifeng},
  title = {Transmission Tower Structural Feature Localization Using Gated Contextual Fusion and Bidirectional Refinement},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5309},
  doi = {10.3390/electronics15225309}
}
Kostenlos starten →