摘要
精准养殖是一种实时监控奶牛信息并分析反馈的信息技术,其目的是保证奶牛福利。计算机视觉技术能够解决接触式方法带来的应激性与成本高问题。综述了奶牛精准养殖技术的发展现状,重点围绕人工智能技术和计算机视觉技术,针对个体身份识别、行为感知两个核心问题,从经典方法和深度学习方法两个方向,着重阐述对比应用对象、应用场景以及算法性能等。研究发现,个体身份识别和行为感知主要以图像分类算法为主;深度学习方法具有更好鲁棒性。最后总结了个体身份识别和行为感知方法的难点,展望了身份识别和行为感知未来发展方向。
Precision livestock farming is a kind of information technology for monitoring and analyzing dairy cattle.It’s aimed at ensuring the welfare of cattle.Computer vision could solve the stress and high-cost problems of contact method.The development of dairy precision livestock farming was summarized.Artificial intelligence and computer vision were focused on.The core problems were listed about individual identification and behavior perception.From classical method to deep learning,the application objects,application scenarios and algorithm performance were compared.In conclusion,the image classification algorithm is the main method of individual identification and behavior perception;deep learning method has better robustness.Finally,the difficulties of individual identification and behavior perception were summarized.The future research direction of identity recognition and behavior perception was prospected.
作者
游学杭
马钦
郭浩
王勤
YOU Xuehang;MA Qin;GUO Hao;WANG Qin(College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;College of Land Science and Technology,China Agricultural University,Beijing 100193,China;College of Animal Science and Technology,China Agricultural University,Beijing 100193,China)
出处
《计算机应用》
CSCD
北大核心
2021年第S01期216-224,共9页
journal of Computer Applications
基金
国家科技重大专项(2014ZX0801203B)
国家自然科学基金资助项目(42071449)。
关键词
奶牛
计算机视觉
精准养殖
身份识别
行为识别
dairy cattle
computer vision
precision livestock farming
identification
behavior recognition