EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Refined Deformable-DETR for Electric Pylon Detection Based on Optical Satellite Image

Jun Yang iD, Yu Sun, Yingjun Zhao, Donghua Lu, Yuxi Hao, Xianglin Liu

Sensors · 31.05.2026 · 26 (11) · 3467

DOI: 10.3390/s26113467 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 31.05.2026. Verfasst von Jun Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Research Institute of Uranium Geology, Beijing 100029, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China National Nuclear Corporation, National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing, National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic detection of electric pylons in optical remote sensing imagery is important for large-scale powerline monitoring, but remains challenging due to complex backgrounds, small target appearances, and large variations in pylon-shadow structures. This paper proposes a Refined Deformable-DETR framework with a Spatial Context-aware Query Modulation (SCQM) module to enhance object query representations. SCQM aggregates image-level contextual information from encoder memory and generates channel-wise modulation vectors to recalibrate object queries before deformable cross-attention, thereby providing image-conditioned channel priors for subsequent query-feature interaction. Experiments on the self-constructed Electric Pylon Remote Sensing Dataset (EPRD) show that the proposed method improves AP from 72.7% to 74.1% and APs from 47.2% to 50.9% compared with the baseline Deformable-DETR. Evaluations on the public Electric Pylon Dataset (EPD) further demonstrate its generalization capability. These results indicate that context-aware query modulation is effective for Transformer-based electric pylon detection in complex remote sensing scenarios.

Schlagwörter

Stichwörter der Autor:innen

electric pylon detectionoptical satellite imagequery modulationrefined deformable-DETR

Autor:innen und Institutionen

  • Beijing Research Institute of Uranium Geology, Beijing 100029, China.
  • National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing, Beijing 100029, China.

ORCID-Profile: Jun Yang

Förderung

  • China National Nuclear Corporation
  • National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing
  • National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing Fund
  • China National Nuclear Corporation Research and Development Platform Stable Support Scientific Research Project

Zitieren

APA

Yang, J., Sun, Y., Zhao, Y., Lu, D., Hao, Y., & Liu, X. (2026). Refined Deformable-DETR for Electric Pylon Detection Based on Optical Satellite Image. Sensors, 26(11), 3467. https://doi.org/10.3390/s26113467

Vancouver

Yang J, Sun Y, Zhao Y, Lu D, Hao Y, Liu X. Refined Deformable-DETR for Electric Pylon Detection Based on Optical Satellite Image. Sensors. 2026;26(11):3467. doi:10.3390/s26113467

BibTeX
@article{Yang2026,
  author = {Yang, Jun and Sun, Yu and Zhao, Yingjun and Lu, Donghua and Hao, Yuxi and Liu, Xianglin},
  title = {Refined Deformable-DETR for Electric Pylon Detection Based on Optical Satellite Image},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3467},
  doi = {10.3390/s26113467}
}
Kostenlos starten →