基于改进YOLOv8n的叠层笼养鸡只笼位采食量估测  

Estimation of chicken cage’s feed intake based on improved YOLOv8n in stacked-cage-raising system

作　　者：冀横溢 张哲 滕光辉 周振宇 刘慕霖 葛绍娟 刘健 JI Hengyi;ZHANG Zhe;TENG Guanghui;ZHOU Zhenyu;LIU Mulin;GE Shaojuan;LIU Jian(College of Water Resources and Civil Engineering,China Agricultural University,Beijing 100083,China;Key Laboratory of Agricultural Engineering in Structure and Environment of Ministry of Agriculture and Rural Affairs,Beijing 100083,China;Beijing Research Center for Livestock and Poultry Healthy Environmental Engineering Technology,Beijing 100083,China)

机构地区：[1]中国农业大学水利与土木工程学院,北京100083 [2]农业部设施农业工程重点实验室,北京100083 [3]北京市畜禽健康养殖环境工程技术研究中心,北京100083

出　　处：《农业工程学报》2024年第24期218-225,共8页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划(2023YFD2000805);山东省重点研发计划(2022TZXD0015)。

摘　　要：为了实现叠层笼养模式下鸡只笼位采食量的估测,该研究以笼养肉种鸡为研究对象,对YOLOv8n模型进行轻量化改进提出了YOLO-FSG模型以识别鸡只的采食行为;在此基础上,采用多元线性回归模型建立了以采食时长和采食次数为自变量,采食量为因变量的估测模型。YOLO-FSG模型通过以下3点改进实现模型轻量化:1)在主干网络部分,将高效多尺度注意力(efficient multi-scale attention,EMA)模块、Faster-NetBlock和C2F(CSPDarknet53 to 2-stage feature pyramid network)结合,构建了C2F-FEblock以增强特征提取能力和降低模型复杂度;2)在颈部网络部分,使用Slim-Neck设计方法,将GSConv(group shuffle convolution)和VovGSCSP(GSConv spatial cross stage partial)模块分别替换卷积和C2F模块优化特征融合与处理过程;3)在检测头部分,使用2个共享参数的分组卷积模块替换4个卷积模块以减少计算量。结果表明,YOLO-FSG模型识别采食行为的平均精度均值(mAP0.5)、参数量、浮点计算量和检测时间分别为97.1%、1.94 M、4 G和3.6 ms,优于YOLOv5n、YOLOv7n、YOLOv8n等常见目标检测模型。采食量估测模型在测试集上的决定系数和均方根误差分别为0.9和5.91 g,表明该模型具有较高的估测精度。该研究提出的方法可为叠层笼养模式下鸡只的精细化管理提供技术支撑,促进养鸡业的智能化和可持续发展。This study aims to estimate the feed intake of chickens in stacked-cage-raising systems.Meat-type breeder chickens were selected as the research object.An improved lightweight version of the YOLOv8n model,named YOLO-FSG,was developed to recognize chicken feeding behaviors.A multivariate linear regression model was established to estimate feed intake using feeding duration and frequency as variables.A dataset of 2043 images was constructed.The data augmentation was applied to the training and validation sets using random rotation,flipping,brightness alteration,and Gaussian blurring.The expanded training and validation set contained3268 and 408 images,respectively.Meanwhile,the test set contained 204 images.The YOLO-FSG model was achieved in the lightweight performance after three key modifications:1)In the backbone network,the efficient multi-scale attention(EMA)module,Faster-NetBlock,and C2F(CSPDarknet53 to two-stage feature pyramid network)were combined to create the C2F-FEblock,thus enhancing feature extraction while reducing model complexity.2)In the neck network,a Slim-Neck design strategy was employed to replace the convolutional layers and C2F modules with GSConv(group shuffle convolution)and VovGSCSP(GSConv spatial cross stage partial)modules,in order to optimize the feature fusion and processing.3)In the detection head,grouped convolutional modules with two shared parameters were replaced by four convolutional modules to reduce the computational load.The YOLO-FSG model achieved a 97.1%mean average precision at a 0.5 threshold(mAP0.5)and a 47.4%mean average precision across 0.5-0.95 thresholds(mAP0.5-0.95),with a model size of 1.94 M,4.0 G floating-point operations(FLOPs),and a detection time of 3.6 ms.Compared with YOLOv8n,the improved model was enhanced by 0.2 percentage points at mAP0.5-0.95 and maintained the same mAP0.5;There was a decrease in the number of parameters,where FLOPs were reduced by 35.3%and 50.6%,respectively;The detection time decreased by 0.2 ms,leading to the more portable model.The i

关 键 词：YOLOv8n 叠层笼养 采食量 鸡 多元线性回归 

分 类 号：S24[农业科学—农业电气化与自动化]