Enhanced Methodology and Experimental Research for Caged Chicken Counting Based on YOLOv8

文献类型： 外文期刊

第一作者： Wu, Zhenlong

作者： Wu, Zhenlong;Yang, Jikang;Zhang, Hengyuan;Fang, Cheng;Wu, Zhenlong;Yang, Jikang;Zhang, Hengyuan;Fang, Cheng

作者机构：

关键词： chicken counting; layered cage farming; object detection; poultry; precision livestock farming

期刊名称：ANIMALS （ 影响因子：2.7； 五年影响因子：3.2 ）

ISSN： 2076-2615

年卷期： 2025 年 15 卷 6 期

页码：

收录情况： SCI

摘要： Accurately counting chickens in densely packed cages is a major challenge in large-scale poultry farms. Traditional manual counting methods are labor-intensive, costly, and prone to errors due to worker fatigue. Furthermore, current deep learning models often struggle with accuracy in caged environments because they are not well-equipped to handle occlusions. In response, we propose the You Only Look Once-Chicken Counting Algorithm (YOLO-CCA). YOLO-CCA improves the YOLOv8-small model by integrating the CoordAttention mechanism and the Reversible Column Networks backbone. This enhancement improved the YOLOv8-small model's F1 score to 96.7% (+3%) and average precision50:95 to 80.6% (+2.8%). Additionally, we developed a threshold-based continuous frame inspection method that records the maximum number of chickens per cage with corresponding timestamps. The data are stored in a cloud database for reliable tracking during robotic inspections. The experiments were conducted in an actual poultry farming environment, involving 80 cages with a total of 493 chickens, and showed that YOLO-CCA raised the chicken recognition rate to 90.9% (+13.2%). When deployed on a Jetson AGX Orin industrial computer using TensorRT, the detection speed increased to 90.9 FPS (+57.6 FPS), although the recognition rate slightly decreased to 93.2% (-2.9%). In summary, YOLO-CCA reduces labor costs, improves counting efficiency, and supports intelligent poultry farming transformation.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序