文献类型： 外文期刊

作者： Gao Ronghua ¹ ; Gu JingQiu ¹ ; Liang Jubao ¹ ;

作者机构： 1.Beijing Acad Agr & Forestry Sci, Beijing Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China

3.Minist Agr, Key Lab Informat Technol Agr, Beijing 100097, Peoples R China

4.Beijing Res Ctr Agr IOT Engn Technol, Beijing 100097, Peoples R China

关键词： object segmentation;image entropy;image moment;intelligent analysis

期刊名称：2017 INTERNATIONAL CONFERENCE ON SMART GRID AND ELECTRICAL AUTOMATION (ICSGEA)

ISSN：

年卷期： 2017 年

页码：

收录情况： SCI

摘要： The application of internet of things in dairy cattle large-scale breeding accumulates many video surveillance data. How to explore the value of dairy cow health reproductive behavior is important to scientifically formulate large-scale feeding measures and can also improve the economic benefits of dairy breeding. A cow behavioral recognition method using dynamic analysis is raised in this paper. The method focuses on the cow behavioral identification problem such as estrus and hoof disease under complex background. The abnormal behaviors that affect the healthy reproduction of dairy cows are captured based on behavior image characteristic analysis. The results show that the new method could improve the accuracy of the characteristic behavior identification, save the time of breeding staff, and improve the management efficiency of large-scale breeding.