Images analysis in prediction of swine weight

• Grant number: 15/07254-3
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: August 01, 2015
• End date: November 30, 2015
• Field of knowledge: Agronomical Sciences - Agronomy
• Principal Investigator: Késia Oliveira da Silva Miranda
• Grantee: Isabella Cardoso Ferreira da Silva Condotta
• Supervisor: Tami Brown-Brandl
• Host Institution: Escola Superior de Agricultura Luiz de Queiroz (ESALQ). Universidade de São Paulo (USP). Piracicaba , SP, Brazil
• Institution abroad: U.S. Meat Animal Research Center (MARC), United States
• Associated to the scholarship: 14/18458-6 - Predicting growing -finishing swine’s weight with image analysis, BP.IC

Abstract

Food production increasingly requires products deriving from animals created by respecting the welfare precepts. The intensive farming system has several sources of stress, making necessary the search for alternatives that promote the improvement of these conditions. The human influence on animal management activities, in addition to increasing production costs, becomes another source of stress through the production cycle. In order to eliminate this problem, the development of methods to monitoring the animal's physical conditions from distance and in real time becomes an alternative. Thus, the quality of the data obtained and the levels of carcass quality and feed conversion are improved, enabling the opening of new markets and fortifying the production and export of pork in Brazil. The pigs' weighing requires the displacement to the scales, making this procedure stressful for both animals and managers. Several researchers have successfully demonstrated that pig dimensions extracted from digital images (2D) can be used to predict the weight with approximately 5% error. However, the automation of this approach is hampered due to problems with clear differentiation between animals and environment colors. Alternatively, it presents the use of a 3D camera, which eliminates this problem. Thus, this project aims to determine the growth profile (size and animal weights) of 3 commercial genetic lines of pigs (Duroc, Landrace and Yorkshire) and develop a weight prediction method using a low cost 3D camera. (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)

CONDOTTA, ISABELLA C. F. S.; BROWN-BRANDL, TAMI M.; SILVA-MIRANDA, KESIA O.; STINN, JOHN P.. Evaluation of a depth sensor for mass estimation of growing and finishing pigs. BIOSYSTEMS ENGINEERING, v. 173, p. 8-pg., 2018-09-01. (15/07254-3)

CONDOTTA, ISABELLA C. F. S.; BROWN-BRANDL, TAMI M.; SILVA-MIRANDA, KESIA O.; STINN, JOHN P.. Evaluation of a depth sensor for mass estimation of growing and finishing pigs. BIOSYSTEMS ENGINEERING, v. 173, n. SI, p. 11-18, SEP 2018. (15/07254-3)