EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Beef Cattle Body Condition Scoring Using EdgeBCS-YOLO: A Lightweight Framework for Edge Deployment

Zitian Liu, Zhi Weng iD, Zhiqiang Zheng iD, Caili Gong, Zhuangzhuang Wang iD, Jun Wang

Animals · 09.04.2026 · 16 (8) · 1143

DOI: 10.3390/ani16081143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 09.04.2026. Verfasst von Zitian Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information Engineering, Inner Mongolia University, Hohhot 010070, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Inner Mongolia Autonomous Region Graduate Research and Innovation Project, National Natural Science Foundation of China, Inner Mongolia Autonomous Region Higher Education Youth Science and Technology Talent Support Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and scalable body condition scoring (BCS) is important for health monitoring and productivity management in precision livestock farming. However, manual scoring is subjective, labor-intensive, and difficult to standardize, while many automated methods are too computationally demanding for edge deployment in real farm environments. This study proposes EdgeBCS-YOLO, a lightweight object detection framework for real-time beef cattle BCS in unstructured farming scenarios. Built on YOLO11n, it combines Position-Sensitive Feature Fusion (PSFF), a Texture-Aware Star Module (TASM), an Efficient Grouped Detection Head (EGDH), and a Focal and Global Knowledge Distillation (FGD)-based distillation strategy. On a dynamic blurring dataset, EdgeBCS-YOLO achieved 90.8% precision, 82.7% recall, and 88.9% mAP@50. On the NVIDIA Jetson Orin NX Super, it achieved a model size of 3.95 MB, a system FPS of 33.35, and an average inference latency of 13.26 ms. These results suggest that it is a practical and potentially efficient solution for automated BCS on edge devices.

Schlagwörter

Stichwörter der Autor:innen

beef cattlebody condition scoringedge computingfeature enhancementprecision livestock farming

Autor:innen und Institutionen

  • School of Electronic Information Engineering, Inner Mongolia University, Hohhot 010070, China.
  • State Key Laboratory of Reproductive Regulation & Breeding of Grassland Livestock, Hohhot 010030, China.
  • Full Mechanization Research Base of Dairy Farming Engineering and Equipment, Ministry of Agriculture and Rural Affairs of the People's Republic of China, Hohhot 010018, China.
  • Inner Mongolia Key Laboratory of Intelligent Communication and Sensing and Signal Processing, Hohhot 010070, China.

ORCID-Profile: Zhi Weng, Zhiqiang Zheng, Zhuangzhuang Wang

Förderung

  • Inner Mongolia Autonomous Region Graduate Research and Innovation Project
  • National Natural Science Foundation of China
  • Inner Mongolia Autonomous Region Higher Education Youth Science and Technology Talent Support Program
  • Foundation for the Central Government to Guide Local Science and Technology Development
  • Research Startup Project for Young Academic Talents of Inner Mongolia University
  • Natural Science Foundation of Inner Mongolia Autonomous Region
  • Inner Mongolia Science and Technology Breakthrough Project

Zitieren

APA

Liu, Z., Weng, Z., Zheng, Z., Gong, C., Wang, Z., & Wang, J. (2026). Real-Time Beef Cattle Body Condition Scoring Using EdgeBCS-YOLO: A Lightweight Framework for Edge Deployment. Animals, 16(8), 1143. https://doi.org/10.3390/ani16081143

Vancouver

Liu Z, Weng Z, Zheng Z, Gong C, Wang Z, Wang J. Real-Time Beef Cattle Body Condition Scoring Using EdgeBCS-YOLO: A Lightweight Framework for Edge Deployment. Animals. 2026;16(8):1143. doi:10.3390/ani16081143

BibTeX
@article{Liu2026,
  author = {Liu, Zitian and Weng, Zhi and Zheng, Zhiqiang and Gong, Caili and Wang, Zhuangzhuang and Wang, Jun},
  title = {Real-Time Beef Cattle Body Condition Scoring Using EdgeBCS-YOLO: A Lightweight Framework for Edge Deployment},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {8},
  pages = {1143},
  doi = {10.3390/ani16081143}
}
Kostenlos starten →