您好，欢迎访问新疆畜牧科学院 机构知识库！

Sleeping and Eating Behavior Recognition of Horses Based on an Improved SlowFast Network

文献类型： 外文期刊

作者： Liu, Yanhong 1 ; Zhou, Fang 5 ; Zheng, Wenxin 6 ; Bai, Tao 1 ; Chen, Xinwen 6 ; Guo, Leifeng 2 ;

作者机构： 1.Xinjiang Agr Univ, Coll Comp & Informat Engn, Urumqi 830052, Peoples R China

2.Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100080, Peoples R China

3.Xinjiang Agr Informatizat Engn Technol Res Ctr, Urumqi 830052, Peoples R China

4.Minist Educ, Engn Res Ctr Intelligent Agr, Urumqi 830052, Peoples R China

5.Shihezi Univ, Coll Informat Sci & Technol, Shihezi 832000, Peoples R China

6.Xinjiang Acad Anim Sci, Inst Anim Husb Qual Stand, Urumqi 830011, Peoples R China

关键词： horse; computer vision; body posture detection; behavior recognition; improved SlowFast network

期刊名称：SENSORS （ 影响因子：3.5； 五年影响因子：3.7 ）

ISSN：

年卷期： 2024 年 24 卷 23 期

页码：

收录情况： SCI

摘要： The sleeping and eating behaviors of horses are important indicators of their health. With the development of the modern equine industry, timely monitoring and analysis of these behaviors can provide valuable data for assessing the physiological state of horses. To recognize horse behaviors in stalls, this study builds on the SlowFast algorithm, introducing a novel loss function to address data imbalance and integrating an SE attention module in the SlowFast algorithm's slow pathway to enhance behavior recognition accuracy. Additionally, YOLOX is employed to replace the original target detection algorithm in the SlowFast network, reducing recognition time during the video analysis phase and improving detection efficiency. The improved SlowFast algorithm achieves automatic recognition of horse behaviors in stalls. The accuracy in identifying three postures-standing, sternal recumbency, and lateral recumbency-is 92.73%, 91.87%, and 92.58%, respectively. It also shows high accuracy in recognizing two behaviors-sleeping and eating-achieving 93.56% and 98.77%. The model's best overall accuracy reaches 93.90%. Experiments show that the horse behavior recognition method based on the improved SlowFast algorithm proposed in this study is capable of accurately identifying horse behaviors in video data sequences, achieving recognition of multiple horses' sleeping and eating behaviors. Additionally, this research provides data support for livestock managers in evaluating horse health conditions, contributing to advancements in modern intelligent horse breeding practices.

  • 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：新疆畜牧科学院

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