Sign in Subscribe
Agricultural industry

Robust Pig Detection and Counting in Complex Agricultural Environments

Strategic Insights

— 1 min read

Researchers at Fuyang Normal University in China have developed a new method for detecting and counting pigs in challenging agricultural environments. The method, called EAPC-YOLO, uses a combination of advanced detection optimizations and density-aware processing to achieve high accuracy and robustness. Experimental results on a comprehensive dataset demonstrate that EAPC-YOLO achieves 94.2% mean average precision (mAP) at 0.5 IoU and 96.8% counting accuracy, representing significant improvements over existing methods.

Key Takeaways:

  • The study highlights the importance of accurate pig counting for precision livestock farming, enabling optimized feeding management and health monitoring.
  • EAPC-YOLO is a robust architecture that integrates density-aware processing with advanced detection optimizations to address the challenges of complex agricultural environments.
  • The method consists of an enhanced YOLOv8 network and a density-aware post-processing module with intelligent NMS strategies.
  • Experimental results demonstrate that EAPC-YOLO achieves 94.2% mAP@0.5 for detection performance and 96.8% counting accuracy, representing 12.3% and 15.7% improvements compared to the strongest baseline, YOLOv11n.
  • The study suggests that EAPC-YOLO enables robust and accurate pig counting across challenging agricultural environments, supporting precision livestock management.
  • The research was supported by the Biological And Medical Sciences of Applied Summit Nurturing Disciplines in Anhui Province, Key Projects of Natural Science Research Projects in Anhui Universities, Scientific Research Project of Fuyang Normal University, and School-level Undergraduate Teaching Project of Fuyang Normal University.

Statistics:

  • 94.2% mAP@0.5 for detection performance
  • 96.8% counting accuracy
  • 12.3% improvement in mAP at 0.5 IoU compared to YOLOv11n
  • 15.7% improvement in counting accuracy compared to YOLOv11n

Sources:

  • Enhanced YOLOv8 for Robust Pig Detection and Counting in Complex Agricultural Environments. Animals, 2025,15(14):2149.
  • Biological And Medical Sciences of Applied Summit Nurturing Disciplines in Anhui Province
  • Key Projects of Natural Science Research Projects in Anhui Universities
  • Scientific Research Project of Fuyang Normal University
  • School-level Undergraduate Teaching Project of Fuyang Normal University

Read more