EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SIRI-YOLO: A Foreign Object Detection Method for Belt Conveyors in High-Entropy Underground Scenes

Yi Liu, Yi Liu, Rengang Xue, Zixian Zhao, Jinping Xiao

Entropy · 11.06.2026 · 28 (6) · 673

DOI: 10.3390/e28060673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 11.06.2026. Verfasst von Yi Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing 100083, China. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development and Technology Transfer Program Project of Inner Mongolia Autonomous Region, Inner Mongolia Autonomous Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the poor detection performance in low-light underground coal mine belt conveyors caused by information entropy degradation and high background noise, as well as the difficulty in multi-scale target extraction due to uneven entropy distribution, this paper proposes an efficient foreign object detection model named SIRI-YOLO based on an improved YOLOv11n architecture. First, a Self-Calibrating Illumination Network (SCINet) is introduced to restore image information entropy and enhance low-light adaptability. Second, the C2PSA module is enhanced to C2PSA-IRMB by incorporating an Inverted Residual Mobile Block (IRMB), improving multi-scale feature utilization and reducing ineffective entropy increase. Third, an improved Reparameterized Generalized Feature Pyramid Network (RepGFPN) is adopted to strengthen the fusion of high-level semantics and low-level spatial features, reducing information entropy loss during feature pyramid transfer. Finally, the Inner-MPDIoU loss function is introduced to replace CIoU, achieving more accurate entropy minimization from a KL divergence perspective. Experimental results on a dataset containing large coal chunks and anchor rods show that SIRI-YOLO achieves 92.8% mAP@50, 59.4% mAP@50:95, 89.5% precision, and 87.2% recall, with only 2.92M parameters and 70.01 FPS, outperforming mainstream YOLO models. Furthermore, on the public ExDark low-light dataset, SIRI-YOLO improves mAP@50 by 4.2% over YOLOv11n, demonstrating strong generalization across different low-light and complex scenarios. The proposed method effectively handles uneven illumination, scale variation, and complex backgrounds, offering a practical solution for coal mine safety through system entropy reduction.

Schlagwörter

Stichwörter der Autor:innen

belt conveyorboundary box regressionforeign object detectioninformation entropymulti-scale target

Autor:innen und Institutionen

  • School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing 100083, China.
  • School of Mechanical and Electrical Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China.
  • Beijing Aerospace Changfeng ScienceTechnology Industry Group Co., Ltd., Beijing 100854, China.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development and Technology Transfer Program Project of Inner Mongolia Autonomous Region
  • Inner Mongolia Autonomous Region

Zitieren

APA

Liu, Y., Liu, Y., Xue, R., Zhao, Z., & Xiao, J. (2026). SIRI-YOLO: A Foreign Object Detection Method for Belt Conveyors in High-Entropy Underground Scenes. Entropy, 28(6), 673. https://doi.org/10.3390/e28060673

Vancouver

Liu Y, Liu Y, Xue R, Zhao Z, Xiao J. SIRI-YOLO: A Foreign Object Detection Method for Belt Conveyors in High-Entropy Underground Scenes. Entropy. 2026;28(6):673. doi:10.3390/e28060673

BibTeX
@article{Liu2026,
  author = {Liu, Yi and Liu, Yi and Xue, Rengang and Zhao, Zixian and Xiao, Jinping},
  title = {SIRI-YOLO: A Foreign Object Detection Method for Belt Conveyors in High-Entropy Underground Scenes},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {6},
  pages = {673},
  doi = {10.3390/e28060673}
}
Kostenlos starten →