基于改进YOLO v5n的舍养绵羊行为识别方法  

Behavior Recognition of Domesticated Sheep Based on Improved YOLO v5n

作　　者：翟亚红[1] 王杰 徐龙艳[1] 祝岚 原红光 赵逸凡 ZHAI Yahong;WANG Jie;XU Longyan;ZHU Lan;YUAN Hongguang;ZHAO Yifan(School of Electrical and Information Engineering,Hubei University of Automotive Technology,Shiyan 442002,China;Qinyang Beisheng Pastoral Industry Co.,Ltd.,Qinyang 454550,China)

机构地区：[1]湖北汽车工业学院电气与信息工程学院,十堰442002 [2]沁阳市北盛牧业有限公司,沁阳454550

出　　处：《农业机械学报》2024年第4期231-240,共10页Transactions of the Chinese Society for Agricultural Machinery

基　　金：湖北省教育厅重点科研项目(D20211802);湖北省科技厅重点研发计划项目(2022BEC008)。

摘　　要：日常行为是家畜健康状况的重要体现,在传统的行为识别方法中,通常需要人工或者依赖工具对家畜进行观察。为解决以上问题,基于YOLO v5n模型,提出了一种高效的绵羊行为识别方法,利用目标识别算法从羊圈斜上方的视频序列中识别舍养绵羊的进食、躺卧以及站立行为。首先用摄像头采集养殖场中羊群的日常行为图像,构建绵羊行为数据集;其次在YOLO v5n的主干特征提取网络中引入SE注意力机制,增强全局信息交互能力和表达能力,提高检测性能;采用GIoU损失函数,减少训练模型时的计算开销并提升模型收敛速度;最后,在Backbone主干网络中引入GhostConv卷积,有效地减少了模型计算量和参数量。实验结果表明,本研究提出的GS-YOLO v5n目标检测方法参数量仅为1.52×10^(6),相较于原始模型YOLO v5n减少15%;浮点运算量为3.3×10^(9),相较于原始模型减少30%;且平均精度均值达到95.8%,相比于原始模型提高4.6个百分点。改进后模型与当前主流的YOLO系列目标检测模型相比,在大幅减少模型计算量和参数量的同时,检测精度均有较高提升。在边缘设备上进行部署,达到了实时检测要求,可准确快速地对绵羊进行定位并检测。Daily behavior is an important manifestation of the health status of livestock.In traditional behavior recognition methods,livestock usually need to be observed manually or rely on additional tools.In order to solve the above problems,an efficient sheep behavior recognition method was proposed based on the YOLO v5n model,which used the target recognition algorithm to recognize the feeding,lying and standing behaviors of domesticated sheep from the video sequence above the sheepflod.Firstly,the daily behavior images of sheep in the farm were collected by cameras,and the data set of sheep behavior was constructed.Secondly,SE attention mechanism was introduced into the Backbone feature extraction network of YOLO v5n to enhance the global information interaction and expression capability and improve the detection performance.The GIoU loss function was utilized to reduce the computational cost and improve the convergence speed of the model.Finally,GhostConv convolution was integrated into Backbone network,which effectively reduced the calculation and parameter number of the model.The experimental results showed that the parameter number of GS-YOLO v5n object detection method proposed was only 1.52×10^(6),which was reduced by 15% compared with the original model YOLO v5n.The FLOPs was 3.3×10^(9),which was 30% less than the original model.The average accuracy achieved 95.8%,which was 4.6 percentage points higher than that of the original model.Compared with the current mainstream YOLO series of object detection models,the improved model significantly reduced the computational and parameter complexity of the model,while also achieved higher detection accuracy.It was deployed on edge devices and met the standard of real-time detection.It can accurately and quickly locate and detect sheep,providing ideas and support for intelligent sheep breeding.

关 键 词：舍养绵羊 智慧养殖 行为识别 注意力机制 YOLO v5n 绵羊数据集 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] S828[自动化与计算机技术—计算机科学与技术]