摘要
针对人工和接触式监测牛日常行为的局限性,提出了一种基于特征部位空间关系的牛日常行为识别方法。首先,用YOLOv5(You only look once,v5)目标检测模型定位图像中牛特征部位的位置,并根据特征部位的位置信息构建牛特征部位的空间关系向量。然后,利用全连接神经网络对空间关系向量进行分类,实现牛的站立、卧躺和采食行为的识别。最后,通过统计一段视频中各行为的时长验证该方法的可行性。实验结果表明,该方法对牛的站立、卧躺和采食行为具有较高的识别准确率,对视频中各行为时长统计的相对误差较低,满足牛日常行为监测的需求。
Considering the limitation of manual and contact monitoring of cattle’s daily behavior,this paper proposes a recognition method of the cattle daily behavior based on the spatial relationship of feature parts.First,YOLOv5(You only look once,v5)target detection model is used to locate the position of the cattle feature parts in the image,and the spatial relation vector of the cattle feature parts is constructed based on the position information of the feature parts.Thereafter,the fully connected neural network is used to classify the spatial relation vector to recognize the cattle’s standing,lying,and feeding behaviors.Finally,the method’s feasibility is demonstrated by counting the duration of each behavior in a video.The experimental results show that the method has a high recognition accuracy for the standing,lying,and feeding behaviors of cattle,and the relative error of each behavior duration in the statistical video is low,meeting the needs of daily behavior monitoring of cattle.
作者
薛芳芳
王月明
李琦
Xue Fangfang;Wang Yueming;Li Qi(School of Ilnformation Elngineering,Inner Mongolia University of Science and Technology,Baotou,Imner Mongolia 014010,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第22期398-406,共9页
Laser & Optoelectronics Progress
基金
内蒙古自治区科技重大专项(2019ZD025)。
关键词
机器视觉
目标检测
特征部位
全连接神经网络
牛行为
machine vision
target detection
feature parts
fully connected neural network
cattle behavior