Automatic body condition scoring system for dairy cows based on depth-image analysis
作者机构：College of Agricultural Equipment EngineeringHenan University of Science and TechnologyLuoyang 471023China Key Laboratory of Equipment and Informatization in Environment Controlled AgricultureMinistry of Agriculture andRural AffairsHangzhou 310058China College of Biosystems Engineering and Food ScienceZhejiang UniversityHangzhou 310058China Department of Electrical EngineeringUniversity of KentuckyLexington 40546USA Department of Animal and Food SciencesUniversity of KentuckyLexington 40546USA Alltech Inc.Nicholasville 40356USA
出 版 物：《International Journal of Agricultural and Biological Engineering》 (国际农业与生物工程学报（英文）)
年 卷 期：2020年第13卷第4期
页 面：45-54页
核心收录：
学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：The work was sponsored by the Key R&D and Promotion Projects in Henan Province(Science and Technology Development,No.192102110089) Open Funding Project of Key Laboratory of Equipment and Informatization in Environment Controlled Agriculture,Ministry of Agriculture and Rural Affairs,P.R.China(No.2011NYZD1804) Key Scientific Research Project Plan of Colleges and Universities in Henan Province(No.19A416003)
主 题：body condition score depth-image processing curvature analysis machine learning precision dairy farming
摘 要：Body condition score(BCS)is an important management tool in the modern dairy industry,and one of the basic techniques for animal welfare and precision dairy *** objective of this study was to use a vision system to evaluate the fat cover on the back of cows and to automatically determine BCS.A 3D camera was used to capture the depth images of the back of cows twice a day as each cow passed beneath the *** background subtraction,the back area of the cow was extracted from the depth *** thurl,sacral ligament,hook bone,and pin bone were located via depth image analysis and evaluated by calculating their visibility and curvature,and those four anatomical features were used to measure fatness.A dataset containing 4820 depth images of cows with 7 BCS levels was built,among which 952 images were used as training *** four anatomical features as input and BCS as output,decision tree learning,linear regression,and BP network were calibrated on the training dataset and tested on the entire *** average,the BP network model scored each cow within 0.25 BCS points compared to their manual scores during the study *** measured values of visibility and curvature used in this study have strong correlations with BCS and can be used to automatically assess BCS with high *** study demonstrates that the automatic body condition scoring system has the possibility of being more accurate than human scoring.
维普期刊数据库