EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HARM-YOLO11n: A Lightweight Real-Time Object Detection Framework for Robust Classroom Behavior Monitoring

Zihang Zhang, Yonghua Mao iD, Yingcang Ma, Xiaolin Gui iD

Sensors · 27.07.2026 · 26 (15) · 4770

DOI: 10.3390/s26154770 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.07.2026. Verfasst von Zihang Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Xi'an Polytechnic University, Xi'an 710048, China. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Basic Research Program of Shaanxi Province, National Key Research and Development Project, Key Science and Technology Project of Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time classroom behavior monitoring is an important component of intelligent education systems, yet it remains challenging due to dense student layouts, frequent occlusions, and small-scale behavior targets. To address these challenges, this paper proposes Hierarchical Adaptive Re-parameterized Multi-scale YOLO11n (HARM-YOLO11n), a lightweight object detection framework based on YOLO11n for classroom behavior analysis. The proposed framework integrates structural re-parameterized feature enhancement (SRFE), a spatial-channel adaptive module (SCAM), position-adaptive multi-scale fusion (PAMSF), and IoU-adaptive soft weight (IASW) to improve feature representation, multi-scale interaction, and optimization behavior. SRFE enhances feature extraction through structural re-parameterization, the SCAM reduces redundant feature responses via selective spatial-channel computation, PAMSF performs adaptive multi-scale feature aggregation, and IASW introduces localization-aware sample weighting during training. Experiments on POCO-Dataset, SCB-Dataset3, and STBD-08 show that HARM-YOLO11n achieves improved detection performance compared with representative lightweight detectors while maintaining real-time inference efficiency. Multi-dataset evaluations further indicate stable performance under different data distributions. The results suggest that the proposed framework provides a practical approach for classroom behavior detection in resource-constrained educational environments.

Schlagwörter

Stichwörter der Autor:innen

class imbalanceclassroom behavior analysisfeature refinementlightweight modelsobject detectionposition-adaptive multi-scale fusion

Autor:innen und Institutionen

  • School of Computer Science, Xi'an Polytechnic University, Xi'an 710048, China.
  • School of Science, Xi'an Polytechnic University, Xi'an 710048, China.
  • School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China.

ORCID-Profile: Yonghua Mao, Xiaolin Gui

Förderung

  • Natural Science Basic Research Program of Shaanxi Province
  • National Key Research and Development Project
  • Key Science and Technology Project of Henan Province
  • Key Research and Development Program of Shaanxi Province
  • Provincial College Students’ Innovation and Entrepreneurship Training Program of Shaanxi Province

Zitieren

APA

Zhang, Z., Mao, Y., Ma, Y., & Gui, X. (2026). HARM-YOLO11n: A Lightweight Real-Time Object Detection Framework for Robust Classroom Behavior Monitoring. Sensors, 26(15), 4770. https://doi.org/10.3390/s26154770

Vancouver

Zhang Z, Mao Y, Ma Y, Gui X. HARM-YOLO11n: A Lightweight Real-Time Object Detection Framework for Robust Classroom Behavior Monitoring. Sensors. 2026;26(15):4770. doi:10.3390/s26154770

BibTeX
@article{Zhang2026,
  author = {Zhang, Zihang and Mao, Yonghua and Ma, Yingcang and Gui, Xiaolin},
  title = {HARM-YOLO11n: A Lightweight Real-Time Object Detection Framework for Robust Classroom Behavior Monitoring},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4770},
  doi = {10.3390/s26154770}
}
Kostenlos starten →