基于尾巴特征和注意机制的奶牛体况评分模型。

IF 2.3 2区 农林科学 Q2 VETERINARY SCIENCES
Fan Liu, Yongan Zhang, Yanqiu Liu, Jia Li, Meian Li, Jianping Yao
{"title":"基于尾巴特征和注意机制的奶牛体况评分模型。","authors":"Fan Liu, Yongan Zhang, Yanqiu Liu, Jia Li, Meian Li, Jianping Yao","doi":"10.3390/vetsci12090906","DOIUrl":null,"url":null,"abstract":"<p><p>The Body Condition Score (BCS) is a key indicator of dairy cattle's health, production efficiency, and environmental impact. Manual BCS assessment is subjective and time-consuming, limiting its scalability in precision agriculture. This study utilizes computer vision to automatically assess cattle body condition by analyzing tail features, categorizing BCS into five levels (3.25, 3.50, 3.75, 4.0, 4.25). SE attention improves feature selection by adjusting channel importance, while spatial attention enhances spatial information processing by focusing on key image regions. EfficientNet-B0, enhanced by SE and spatial attention mechanisms, improves feature extraction and localization. To facilitate edge device deployment, model distillation reduces the size from 23.8 MB to 8.7 MB, improving inference speed and storage efficiency. After distillation, the model achieved 91.10% accuracy, 91.14% precision, 91.10% recall, and 91.10% F1 score. The accuracy increased to 97.57% for ±0.25 BCS error and 99.72% for ±0.5 error. This model saves space and meets real-time monitoring requirements, making it suitable for edge devices with limited resources. This research provides an efficient, scalable method for automated livestock health monitoring, supporting intelligent animal husbandry development.</p>","PeriodicalId":23694,"journal":{"name":"Veterinary Sciences","volume":"12 9","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12474389/pdf/","citationCount":"0","resultStr":"{\"title\":\"A Novel Lightweight Dairy Cattle Body Condition Scoring Model for Edge Devices Based on Tail Features and Attention Mechanisms.\",\"authors\":\"Fan Liu, Yongan Zhang, Yanqiu Liu, Jia Li, Meian Li, Jianping Yao\",\"doi\":\"10.3390/vetsci12090906\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The Body Condition Score (BCS) is a key indicator of dairy cattle's health, production efficiency, and environmental impact. Manual BCS assessment is subjective and time-consuming, limiting its scalability in precision agriculture. This study utilizes computer vision to automatically assess cattle body condition by analyzing tail features, categorizing BCS into five levels (3.25, 3.50, 3.75, 4.0, 4.25). SE attention improves feature selection by adjusting channel importance, while spatial attention enhances spatial information processing by focusing on key image regions. EfficientNet-B0, enhanced by SE and spatial attention mechanisms, improves feature extraction and localization. To facilitate edge device deployment, model distillation reduces the size from 23.8 MB to 8.7 MB, improving inference speed and storage efficiency. After distillation, the model achieved 91.10% accuracy, 91.14% precision, 91.10% recall, and 91.10% F1 score. The accuracy increased to 97.57% for ±0.25 BCS error and 99.72% for ±0.5 error. This model saves space and meets real-time monitoring requirements, making it suitable for edge devices with limited resources. This research provides an efficient, scalable method for automated livestock health monitoring, supporting intelligent animal husbandry development.</p>\",\"PeriodicalId\":23694,\"journal\":{\"name\":\"Veterinary Sciences\",\"volume\":\"12 9\",\"pages\":\"\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12474389/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Veterinary Sciences\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.3390/vetsci12090906\",\"RegionNum\":2,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"VETERINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Veterinary Sciences","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.3390/vetsci12090906","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"VETERINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

体况评分(BCS)是衡量奶牛健康、生产效率和环境影响的关键指标。人工BCS评估主观且耗时,限制了其在精准农业中的可扩展性。本研究利用计算机视觉技术,通过分析牛尾特征,将BCS分为5个等级(3.25、3.50、3.75、4.0、4.25),对牛体况进行自动评估。SE注意通过调整通道重要性来提高特征选择,而空间注意通过聚焦关键图像区域来增强空间信息处理。effentnet - b0通过SE和空间注意机制增强,改进了特征提取和定位。为了方便边缘设备部署,模型蒸馏将大小从23.8 MB减小到8.7 MB,提高了推理速度和存储效率。经精馏后,模型准确率达到91.10%,精密度达到91.14%,召回率达到91.10%,F1得分达到91.10%。在±0.25 BCS误差下,准确度提高到97.57%;在±0.5 BCS误差下,准确度提高到99.72%。该模型节省空间,满足实时监控需求,适用于资源有限的边缘设备。本研究为家畜健康自动化监测提供了一种高效、可扩展的方法,支持智能化畜牧业的发展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Novel Lightweight Dairy Cattle Body Condition Scoring Model for Edge Devices Based on Tail Features and Attention Mechanisms.

The Body Condition Score (BCS) is a key indicator of dairy cattle's health, production efficiency, and environmental impact. Manual BCS assessment is subjective and time-consuming, limiting its scalability in precision agriculture. This study utilizes computer vision to automatically assess cattle body condition by analyzing tail features, categorizing BCS into five levels (3.25, 3.50, 3.75, 4.0, 4.25). SE attention improves feature selection by adjusting channel importance, while spatial attention enhances spatial information processing by focusing on key image regions. EfficientNet-B0, enhanced by SE and spatial attention mechanisms, improves feature extraction and localization. To facilitate edge device deployment, model distillation reduces the size from 23.8 MB to 8.7 MB, improving inference speed and storage efficiency. After distillation, the model achieved 91.10% accuracy, 91.14% precision, 91.10% recall, and 91.10% F1 score. The accuracy increased to 97.57% for ±0.25 BCS error and 99.72% for ±0.5 error. This model saves space and meets real-time monitoring requirements, making it suitable for edge devices with limited resources. This research provides an efficient, scalable method for automated livestock health monitoring, supporting intelligent animal husbandry development.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Veterinary Sciences
Veterinary Sciences VETERINARY SCIENCES-
CiteScore
2.90
自引率
8.30%
发文量
612
审稿时长
6 weeks
期刊介绍: Veterinary Sciences is an international and interdisciplinary scholarly open access journal. It publishes original that are relevant to any field of veterinary sciences, including prevention, diagnosis and treatment of disease, disorder and injury in animals. This journal covers almost all topics related to animal health and veterinary medicine. Research fields of interest include but are not limited to: anaesthesiology anatomy bacteriology biochemistry cardiology dentistry dermatology embryology endocrinology epidemiology genetics histology immunology microbiology molecular biology mycology neurobiology oncology ophthalmology parasitology pathology pharmacology physiology radiology surgery theriogenology toxicology virology.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信