BiGRU-Attention Based Cow Behavior Classification Using Video Data for Precision Livestock Farming

IF 1.4 4区 农林科学 Q3 AGRICULTURAL ENGINEERING Transactions of the ASABE Pub Date : 2021-01-01 DOI:10.13031/trans.14658
Yangyang Guo, Yongliang Qiao, S. Sukkarieh, L. Chai, Dongjian He
{"title":"BiGRU-Attention Based Cow Behavior Classification Using Video Data for Precision Livestock Farming","authors":"Yangyang Guo, Yongliang Qiao, S. Sukkarieh, L. Chai, Dongjian He","doi":"10.13031/trans.14658","DOIUrl":null,"url":null,"abstract":"HighlightsBiGRU-attention based cow behavior classification was proposed.Key spatial-temporal features were captured for behavior representation.BiGRU-attention achieved >82% classification accuracy on calf and adult cow datasets.The proposed method could be used for similar animal behavior classification.Abstract. Animal behavior consists of time series activities, which can reflect animals’ health and welfare status. Monitoring and classifying animal behavior facilitates management decisions to optimize animal performance, welfare, and environmental outcomes. In recent years, deep learning methods have been applied to monitor animal behavior worldwide. To achieve high behavior classification accuracy, a BiGRU-attention based method is proposed in this article to classify some common behaviors, such as exploring, feeding, grooming, standing, and walking. In our work, (1) Inception-V3 was first applied to extract convolutional neural network (CNN) features for each image frame in videos, (2) bidirectional gated recurrent unit (BiGRU) was used to further extract spatial-temporal features, (3) an attention mechanism was deployed to allocate weights to each of the extracted spatial-temporal features according to feature similarity, and (4) the weighted spatial-temporal features were fed to a Softmax layer for behavior classification. Experiments were conducted on two datasets (i.e., calf and adult cow), and the proposed method achieved 82.35% and 82.26% classification accuracy on the calf and adult cow datasets, respectively. In addition, in comparison with other methods, the proposed BiGRU-attention method outperformed long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and BiGRU. Overall, the proposed BiGRU-attention method can capture key spatial-temporal features to significantly improve animal behavior classification, which is favorable for automatic behavior classification in precision livestock farming. Keywords: BiGRU, Cow behavior, Deep learning, LSTM, Precision livestock farming.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"178 1","pages":""},"PeriodicalIF":1.4000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of the ASABE","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.13031/trans.14658","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 11

Abstract

HighlightsBiGRU-attention based cow behavior classification was proposed.Key spatial-temporal features were captured for behavior representation.BiGRU-attention achieved >82% classification accuracy on calf and adult cow datasets.The proposed method could be used for similar animal behavior classification.Abstract. Animal behavior consists of time series activities, which can reflect animals’ health and welfare status. Monitoring and classifying animal behavior facilitates management decisions to optimize animal performance, welfare, and environmental outcomes. In recent years, deep learning methods have been applied to monitor animal behavior worldwide. To achieve high behavior classification accuracy, a BiGRU-attention based method is proposed in this article to classify some common behaviors, such as exploring, feeding, grooming, standing, and walking. In our work, (1) Inception-V3 was first applied to extract convolutional neural network (CNN) features for each image frame in videos, (2) bidirectional gated recurrent unit (BiGRU) was used to further extract spatial-temporal features, (3) an attention mechanism was deployed to allocate weights to each of the extracted spatial-temporal features according to feature similarity, and (4) the weighted spatial-temporal features were fed to a Softmax layer for behavior classification. Experiments were conducted on two datasets (i.e., calf and adult cow), and the proposed method achieved 82.35% and 82.26% classification accuracy on the calf and adult cow datasets, respectively. In addition, in comparison with other methods, the proposed BiGRU-attention method outperformed long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and BiGRU. Overall, the proposed BiGRU-attention method can capture key spatial-temporal features to significantly improve animal behavior classification, which is favorable for automatic behavior classification in precision livestock farming. Keywords: BiGRU, Cow behavior, Deep learning, LSTM, Precision livestock farming.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于视频数据的BiGRU-Attention - Based奶牛行为分类在精准畜牧业中的应用
提出了基于bigru -attention的奶牛行为分类方法。捕获关键的时空特征用于行为表征。BiGRU-attention在犊牛和成年牛数据集上的分类准确率均>82%。该方法可用于同类动物的行为分类。动物行为是由时间序列活动构成的,可以反映动物的健康和福利状况。监测和分类动物行为有助于管理决策,以优化动物性能,福利和环境结果。近年来,深度学习方法在全球范围内被应用于动物行为监测。为了获得较高的行为分类精度,本文提出了一种基于BiGRU-attention的方法对一些常见的行为进行分类,如探索、进食、梳理、站立和行走。在我们的工作中,(1)首先应用Inception-V3提取视频中每个图像帧的卷积神经网络(CNN)特征,(2)使用双向门控循环单元(BiGRU)进一步提取时空特征,(3)部署注意机制,根据特征相似度为每个提取的时空特征分配权重,(4)将加权的时空特征馈入Softmax层进行行为分类。在犊牛和成年牛两个数据集上进行了实验,该方法在犊牛和成年牛数据集上的分类准确率分别达到82.35%和82.26%。此外,与其他方法相比,所提出的BiGRU-attention方法优于长短期记忆(LSTM)、双向LSTM (BiLSTM)和BiGRU方法。总体而言,所提出的BiGRU-attention方法能够捕获关键时空特征,显著提高动物行为分类水平,有利于实现精准养殖中的自动行为分类。关键词:BiGRU,奶牛行为,深度学习,LSTM,精准畜牧
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Transactions of the ASABE
Transactions of the ASABE AGRICULTURAL ENGINEERING-
CiteScore
2.30
自引率
0.00%
发文量
0
审稿时长
6 months
期刊介绍: This peer-reviewed journal publishes research that advances the engineering of agricultural, food, and biological systems. Submissions must include original data, analysis or design, or synthesis of existing information; research information for the improvement of education, design, construction, or manufacturing practice; or significant and convincing evidence that confirms and strengthens the findings of others or that revises ideas or challenges accepted theory.
期刊最新文献
Effectiveness of Nutrient Management for Reducing Phosphorus Losses from Agricultural Areas. Effectiveness of Nutrient Management on Water Quality Improvement: A Synthesis on Nitrate-Nitrogen Loss from Subsurface Drainage. Comparison of Droplet Size, Coverage, and Drift Potential from UAV Application Methods and Ground Application Methods on Row Crops. Experimental Study on Critical Shear Stress of Cohesive Soils and Soil Mixtures Dynamics of Texture Change and in Vitro Starch Digestibility with High-Pressure, Freeze-Thaw Cycle, and Germination-Parboiling Treatments of Brown Rice
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1