EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OIL: A Closed-Loop Periodic Batch Adaptation Framework for Object Detection on Industrial Variable-Speed Conveyor Lines

Xiang Liu iD, Jing Fang iD, Haiqiao Liu iD, Zichao Gong iD, Zhiling Peng iD, Jing Dong iD

Sensors · 27.08.2026 · 26 (17) · 5423

DOI: 10.3390/s26175423 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.08.2026. Verfasst von Xiang Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Hunan Institute of Engineering, Xiangtan 410014, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Natural Science Foundation of Hunan Province, Scientific Research Foundation of Hunan Provincial Department of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address motion blur and the degradation of object detection performance caused by variations in industrial conveyor-belt speed, this paper proposes OIL, a closed-loop periodic batch adaptation framework. First, the framework employs a YOLOv8 detector incorporating the Global Attention Mechanism (GAM) and uses the Classification Index Weight (CIW), which consists of detection confidence and the temporal consistency of predicted bounding boxes between adjacent frames. Second, the detection results are divided into three intervals according to the CIW and its constituent metrics: interval A, with a CIW below 0.3; interval B, with a CIW between 0.3 and 0.5; and interval C, with a CIW above 0.5. Results in interval A are treated as negative samples, those in interval B as ambiguous samples, and those in interval C as positive samples. Positive samples are used to train the candidate model, ambiguous samples are stored in a buffer and re-evaluated in subsequent cycles, and negative samples are excluded from the current model update. Finally, when the accumulated number of positive samples reaches a predefined threshold, the system trains a candidate model using the baseline data and newly collected samples. The candidate model is then compared with the currently deployed model on a fixed manually annotated evaluation set. The candidate model is deployed only when its overall performance improves; otherwise, a rollback is performed. Experiments on a coal conveyor line demonstrate that, at 25× speed, incorporating OIL into YOLOv8 + GAM improves Recall by 34.3 percentage points compared with the same detector without OIL. In the variable-speed experiments ranging from 5× to 25×, Recall remained above 64.3%, indicating that the proposed framework can effectively suppress missed detections under high-speed operating conditions.

Schlagwörter

Stichwörter der Autor:innen

detection accuracymotion blurobject detectionperiodic batch adaptationvariable-speed conveyor line

Autor:innen und Institutionen

  • School of Electrical and Information Engineering, Hunan Institute of Engineering, Xiangtan 410014, China.
  • Hunan Provincial Third Surveying and Mapping Institute, Changsha 410008, China.
  • Aerospace Technology Research Institute, Central South University, Changsha 410008, China.

ORCID-Profile: Xiang Liu, Jing Fang, Haiqiao Liu, Zichao Gong, Zhiling Peng, Jing Dong

Förderung

  • National Natural Science Foundation of China
  • National Natural Science Foundation of Hunan Province
  • Scientific Research Foundation of Hunan Provincial Department of Education
  • Open Project of Hunan Geospatial Information Engineering and Technology Research Center

Zitieren

APA

Liu, X., Fang, J., Liu, H., Gong, Z., Peng, Z., & Dong, J. (2026). OIL: A Closed-Loop Periodic Batch Adaptation Framework for Object Detection on Industrial Variable-Speed Conveyor Lines. Sensors, 26(17), 5423. https://doi.org/10.3390/s26175423

Vancouver

Liu X, Fang J, Liu H, Gong Z, Peng Z, Dong J. OIL: A Closed-Loop Periodic Batch Adaptation Framework for Object Detection on Industrial Variable-Speed Conveyor Lines. Sensors. 2026;26(17):5423. doi:10.3390/s26175423

BibTeX
@article{Liu2026,
  author = {Liu, Xiang and Fang, Jing and Liu, Haiqiao and Gong, Zichao and Peng, Zhiling and Dong, Jing},
  title = {OIL: A Closed-Loop Periodic Batch Adaptation Framework for Object Detection on Industrial Variable-Speed Conveyor Lines},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {17},
  pages = {5423},
  doi = {10.3390/s26175423}
}
Kostenlos starten →