您好，欢迎访问广东省农业科学院 机构知识库！
广东省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Automatic Recognition and Quantification Feeding Behaviors of Nursery Pigs Using Improved YOLOV5 and Feeding Functional Area Proposals

文献类型： 外文期刊

作者： Luo, Yizhi 1 ; Xia, Jinjin 3 ; Lu, Huazhong 2 ; Luo, Haowen 1 ; Lv, Enli 2 ; Zeng, Zhixiong 3 ; Li, Bin 2 ; Meng, Fanming 2 ; Yang, Aqing 5 ;

作者机构： 1.Guangdong Acad Agr Sci, Inst Facil Agr, Guangzhou 510640, Peoples R China

2.State Key Lab Swine & Poultry Breeding Ind, Guangzhou 510645, Peoples R China

3.South China Agr Univ, Coll Engn, Guangzhou 510642, Peoples R China

4.Guangdong Acad Agr Sci, Inst Anim Sci, Guangzhou 510645, Peoples R China

5.Guangdong Polytech Normal Univ, Coll Comp Sci, Guangzhou 510665, Peoples R China

关键词： nursery pigs; feeding behavior recognition; functional area proposals; behavioral quantification; transformer

期刊名称：ANIMALS （ 影响因子：3.0； 五年影响因子：3.2 ）

ISSN： 2076-2615

年卷期： 2024 年 14 卷 4 期

页码：

收录情况： SCI

摘要： Simple Summary In commercial-intensive pig farms, the identification and quantification of piglet feeding behavior is an important indicator for daily inspections. However, the model often judges pigs resting in the feeding area as the feeding behavior. Considering the functional characteristics of the pig house feeding area, we present a novel method based on the improved YOLOV5 and feeding functional area suggestions to identify the feeding and non-feeding behaviors of nursery piglets. In addition, four advanced models and ablation experiments are adopted for a comparative evaluation of the robustness of the model. This article proposes a model that can help the management team adjust piglet feeding patterns and save more manpower and feed.Abstract A novel method is proposed based on the improved YOLOV5 and feeding functional area proposals to identify the feeding behaviors of nursery piglets in a complex light and different posture environment. The method consists of three steps: first, the corner coordinates of the feeding functional area were set up by using the shape characteristics of the trough proposals and the ratio of the corner point to the image width and height to separate the irregular feeding area; second, a transformer module model was introduced based on YOLOV5 for highly accurate head detection; and third, the feeding behavior was recognized and counted by calculating the proportion of the head in the located feeding area. The pig head dataset was constructed, including 5040 training sets with 54,670 piglet head boxes, and 1200 test sets, and 25,330 piglet head boxes. The improved model achieves a 5.8% increase in the mAP and a 4.7% increase in the F1 score compared with the YOLOV5s model. The model is also applied to analyze the feeding pattern of group-housed nursery pigs in 24 h continuous monitoring and finds that nursing pigs have different feeding rhythms for the day and night, with peak feeding periods at 7:00-9:00 and 15:00-17:00 and decreased feeding periods at 12:00-14:00 and 0:00-6:00. The model provides a solution for identifying and quantifying pig feeding behaviors and offers a data basis for adjusting the farm feeding scheme.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：广东省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台