A novel approach based on a modified mask R-CNN for the weight prediction of live pigs

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY Artificial Intelligence in Agriculture Pub Date : 2024-03-04 DOI:10.1016/j.aiia.2024.03.001
Chuanqi Xie , Yuji Cang , Xizhong Lou , Hua Xiao , Xing Xu , Xiangjun Li , Weidong Zhou
{"title":"A novel approach based on a modified mask R-CNN for the weight prediction of live pigs","authors":"Chuanqi Xie ,&nbsp;Yuji Cang ,&nbsp;Xizhong Lou ,&nbsp;Hua Xiao ,&nbsp;Xing Xu ,&nbsp;Xiangjun Li ,&nbsp;Weidong Zhou","doi":"10.1016/j.aiia.2024.03.001","DOIUrl":null,"url":null,"abstract":"<div><p>Since determining the weight of pigs during large-scale breeding and production is challenging, using non-contact estimation methods is vital. This study proposed a novel pig weight prediction method based on a modified mask region-convolutional neural network (mask R-CNN). The modified approach used ResNeSt as the backbone feature extraction network to enhance the image feature extraction ability. The feature pyramid network (FPN) was added to the backbone feature extraction network for multi-scale feature fusion. The channel attention mechanism (CAM) and spatial attention mechanism (SAM) were introduced in the region proposal network (RPN) for the adaptive integration of local features and their global dependencies to capture global information, ultimately improving image segmentation accuracy. The modified network obtained a precision rate (P), recall rate (R), and mean average precision (MAP) of 90.33%, 89.85%, and 95.21%, respectively, effectively segmenting the pig regions in the images. Five image features, namely the back area (A), body length (L), body width (W), average depth (AD), and eccentricity (E), were investigated. The pig depth images were used to build five regression algorithms (ordinary least squares (OLS), AdaBoost, CatBoost, XGBoost, and random forest (RF)) for weight value prediction. AdaBoost achieved the best prediction result with a coefficient of determination (R<sup>2</sup>) of 0.987, a mean absolute error (MAE) of 2.96 kg, a mean square error (MSE) of 12.87 kg<sup>2</sup>, and a mean absolute percentage error (MAPE) of 8.45%. The results demonstrated that the machine learning models effectively predicted the weight values of the pigs, providing technical support for intelligent pig farm management.</p></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":null,"pages":null},"PeriodicalIF":8.2000,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589721724000047/pdfft?md5=43c515f8d95da29c768ed4d67f22ebc0&pid=1-s2.0-S2589721724000047-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Agriculture","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589721724000047","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Since determining the weight of pigs during large-scale breeding and production is challenging, using non-contact estimation methods is vital. This study proposed a novel pig weight prediction method based on a modified mask region-convolutional neural network (mask R-CNN). The modified approach used ResNeSt as the backbone feature extraction network to enhance the image feature extraction ability. The feature pyramid network (FPN) was added to the backbone feature extraction network for multi-scale feature fusion. The channel attention mechanism (CAM) and spatial attention mechanism (SAM) were introduced in the region proposal network (RPN) for the adaptive integration of local features and their global dependencies to capture global information, ultimately improving image segmentation accuracy. The modified network obtained a precision rate (P), recall rate (R), and mean average precision (MAP) of 90.33%, 89.85%, and 95.21%, respectively, effectively segmenting the pig regions in the images. Five image features, namely the back area (A), body length (L), body width (W), average depth (AD), and eccentricity (E), were investigated. The pig depth images were used to build five regression algorithms (ordinary least squares (OLS), AdaBoost, CatBoost, XGBoost, and random forest (RF)) for weight value prediction. AdaBoost achieved the best prediction result with a coefficient of determination (R2) of 0.987, a mean absolute error (MAE) of 2.96 kg, a mean square error (MSE) of 12.87 kg2, and a mean absolute percentage error (MAPE) of 8.45%. The results demonstrated that the machine learning models effectively predicted the weight values of the pigs, providing technical support for intelligent pig farm management.

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
基于改进型掩膜 R-CNN 的活猪体重预测新方法
由于在大规模育种和生产过程中确定猪的体重具有挑战性,因此使用非接触式估算方法至关重要。本研究提出了一种基于改进型掩膜区域卷积神经网络(掩膜 R-CNN)的新型猪体重预测方法。改进方法使用 ResNeSt 作为骨干特征提取网络,以增强图像特征提取能力。在骨干特征提取网络中加入了特征金字塔网络(FPN),用于多尺度特征融合。在区域建议网络(RPN)中引入了通道注意机制(CAM)和空间注意机制(SAM),用于自适应地整合局部特征及其全局依赖关系,以捕捉全局信息,最终提高图像分割精度。改进后的网络获得的精确率(P)、召回率(R)和平均精确率(MAP)分别为 90.33%、89.85% 和 95.21%,有效地分割了图像中的猪区域。研究了五个图像特征,即背部面积(A)、体长(L)、体宽(W)、平均深度(AD)和偏心率(E)。猪的深度图像被用于建立五种回归算法(普通最小二乘法(OLS)、AdaBoost、CatBoost、XGBoost 和随机森林(RF))来预测权重值。AdaBoost 的预测结果最好,其决定系数 (R2) 为 0.987,平均绝对误差 (MAE) 为 2.96 千克,平均平方误差 (MSE) 为 12.87 千克2,平均绝对百分比误差 (MAPE) 为 8.45%。结果表明,机器学习模型能有效预测猪的体重值,为猪场的智能化管理提供了技术支持。
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
Artificial Intelligence in Agriculture
Artificial Intelligence in Agriculture Engineering-Engineering (miscellaneous)
CiteScore
21.60
自引率
0.00%
发文量
18
审稿时长
12 weeks
期刊最新文献
A review of external quality inspection for fruit grading using CNN models Automatic location and recognition of horse freezing brand using rotational YOLOv5 deep learning network Prediction of spatial heterogeneity in nutrient-limited sub-tropical maize yield: Implications for precision management in the eastern Indo-Gangetic Plains UAV-based field watermelon detection and counting using YOLOv8s with image panorama stitching and overlap partitioning Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments
×
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