EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EnhancedMulti-Scenario Pig Behavior Recognition Based on YOLOv8n

Panqi Pu iD, Junge Wang, Geqi Yan, Hongchao Jiao, Hao Li, Hai Lin

Animals · 09.10.2025 · 15 (19) · 2927

DOI: 10.3390/ani15192927 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 09.10.2025. Verfasst von Panqi Pu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Efficient Utilization of Non-Grain Feed Resources (Co-Construction by Ministry and Province), Ministry of Agriculture and Rural Aff…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Project of China, the National Key R&D Project of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advances in smart animal husbandry necessitate efficient pig behavior monitoring, yet traditional approaches suffer from operational inefficiency and animal stress. We address these limitations through a lightweight YOLOv8n architecture enhanced with SPD-Conv for feature preservation during downsampling, LSKBlock attention for contextual feature fusion, and a dedicated small-target detection head. Experimental validation demonstrates superior performance: the optimized model achieves a 92.4% mean average precision (mAP@0.5) and 87.4% recall, significantly outperforming baseline YOLOv8n by 3.7% in AP while maintaining minimal parameter growth (3.34M). Controlled illumination tests confirm enhanced robustness under strong and warm lighting conditions, with performance gains of 1.5% and 0.7% in AP, respectively. This high-precision framework enables real-time recognition of standing, prone lying, lateral lying, and feeding behaviors in commercial piggeries, supporting early health anomaly detection through non-invasive monitoring.

Schlagwörter

Stichwörter der Autor:innen

YOLObehavior recognitionmulti-scene detectionpigprecision livestock farming

Autor:innen und Institutionen

  • Key Laboratory of Efficient Utilization of Non-Grain Feed Resources (Co-Construction by Ministry and Province), Ministry of Agriculture and Rural Affairs, Shandong Provincial Key Laboratory of Animal Nutrition and Effic…
  • College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100193, China.

ORCID-Profile: Panqi Pu

Förderung

  • the National Key R&D Project of China
  • the National Key R&D Project of China

Zitieren

APA

Pu, P., Wang, J., Yan, G., Jiao, H., Li, H., & Lin, H. (2025). EnhancedMulti-Scenario Pig Behavior Recognition Based on YOLOv8n. Animals, 15(19), 2927. https://doi.org/10.3390/ani15192927

Vancouver

Pu P, Wang J, Yan G, Jiao H, Li H, Lin H. EnhancedMulti-Scenario Pig Behavior Recognition Based on YOLOv8n. Animals. 2025;15(19):2927. doi:10.3390/ani15192927

BibTeX
@article{Pu2025,
  author = {Pu, Panqi and Wang, Junge and Yan, Geqi and Jiao, Hongchao and Li, Hao and Lin, Hai},
  title = {EnhancedMulti-Scenario Pig Behavior Recognition Based on YOLOv8n},
  journal = {Animals},
  year = {2025},
  volume = {15},
  number = {19},
  pages = {2927},
  doi = {10.3390/ani15192927}
}
Kostenlos starten →