Prediction of body weight and hot carcass weight of Nellore cattle using digital images

• Grant number: 17/20812-0
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: November 01, 2017
• End date: April 30, 2018
• Field of knowledge: Agronomical Sciences - Animal Husbandry - Animal Production
• Principal Investigator: Otávio Rodrigues Machado Neto
• Grantee: Alexandre Cominotte
• Supervisor: Guilherme Jordão de Magalhães Rosa
• Host Institution: Faculdade de Ciências Agrárias e Veterinárias (FCAV). Universidade Estadual Paulista (UNESP). Campus de Jaboticabal. Jaboticabal , SP, Brazil
• Institution abroad: University of Wisconsin-Madison (UW-Madison), United States
• Associated to the scholarship: 17/02057-0 - Use of visual scores and biometric image in Nellore cattle, BP.MS

Abstract

The objective of this project is to evaluate the use of beef cattle images captured through infrared light depth sensors for the estimation of body weight and hot carcass weight of animals using linear regression analysis. The project will be divided into 2 phases: phase 1 conducted in Brazil and phase 2 will be conducted in USA. We analyzed 240 dorsal images of sixty Nellore cattle, which were obtained during different periods: weaning (231 days of age), growing phase at rainy season (354 days of age), feedlot initial phase (591 days of age) and finishing phase (711 days of age). Body weight was also collected at each period and hot carcass weight of each animal will be collected at the end of finishing phase. The hypothesis is that the dorsal images of beef cattle can be used to estimate body weight and hot carcass weight using linear regression. The following physical measurements were evaluated using the collected images: dorsal height, dorsal plane area, anterior width, rib width, posterior width and length. The phase 2 of the project will be conducted at the Department of Animal Sciences at the University of Wisconsin-Madison, USA, where will be developed equations of weight prediction through linear regression using the measurements taken in the dorsal images (phase 1). To evaluate the model a cross-validation procedure will be performed using the Model Evaluation System (MES) software, version 3.1.15 (Texas A & M University, College Station, TX). The prediction equations will be developed using the SAS. Pearson correlation will be performed using CORR procedure in SAS for a better understanding of the relationship between measurements. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

COMINOTTE, A.; FERNANDES, A. F. A.; DOREA, J. R. R.; ROSA, G. J. M.; LADEIRA, M. M.; VAN CLEEF, E. H. C. B.; PEREIRA, G. L.; BALDASSINI, W. A.; MACHADO NETO, O. R.. Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases. LIVESTOCK SCIENCE, v. 232, FEB 2020. (17/20812-0, 17/02057-0)

COMINOTTE, ALEXANDRE; FERNANDES, ARTHUR; DOREA, JOAO; ROSA, GUILHERME; TORRES, RODRIGO; PEREIRA, GUILHERME; BALDASSINI, WELDER; MACHADO NETO, OTAVIO. Use of Biometric Images to Predict Body Weight and Hot CarcassWeight of Nellore Cattle. ANIMALS, v. 13, n. 10, p. 12-pg., 2023-05-18. (21/07222-5, 17/02057-0, 17/20812-0)