Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases

Detalhes bibliográficos
Autor(a) principal: Cominotte, A.
Data de Publicação: 2020
Outros Autores: Fernandes, A. F. A., Dorea, J. R. R., Rosa, G. J. M., Ladeira, M. M., van Cleef, E. H. C. B., Pereira, G. L. [UNESP], Baldassini, W. A. [UNESP], Machado Neto, O. R. [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1016/j.livsci.2019.103904
http://hdl.handle.net/11449/195235
Resumo: Frequent measurements of body weight (BW) in livestock systems are very important because they allow assessing growth. However, real-time monitoring of animal growth through traditional weighing scales is stressful for animals, costly and labor-intensive. Thus, the objectives of this study were to: 1) assess the predictive quality of an automated computer vision system used to predict BW and average daily gain (ADG) in beef cattle; and 2) compare different predictive approaches, including Multiple Linear Regression (MLR), Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), and Artificial Neutral Networks (ANN). A total of 234 images of Nellore beef cattle were collected during the weaning, stocker and feedlot phases. First, biometric body measurements of each animal, such as body volume, area, length, and others, were performed using three-dimensional images captured with the Kinecto (R) sensor, and their respective BW were acquired using an electronic scale. Next, the biometric measurements were used as explanatory variables in the four predictive approaches (MLR, LASSO, PLS, and ANN). To evaluate prediction quality, a leave-one-out cross-validation was adopted. The ANN was the best prediction approach in terms of Root Mean Square Error of Prediction (RMSEP) and squared predictive correlation (r(2)). The results for Weaning were RMSEP = 8.6 kg and r(2) = 0.91; for Stocker phase, RMSEP = 11.4 kg and r(2) = 0.79; and for Beginning of feedlot, RMSEP = 7.7 kg and r(2) = 0.92. The ANN was also the best method for prediction of ADG, with RMSEP = 0.02 kg/d and r(2) = 0.67 for the period between Weaning and Stocker, RMSEP = 0.02 kg/d and r(2) = 0.85 for the Weaning and Beginning of Feedlot phase, RMSEP = 0.03 kg/d and r(2) = 0.80 for Weaning and Final of Feedlot phase, RMSEP = 0.10 kg/d and r(2) = 0.51 for Stocker and Beginning of feedlot phase, and RMSEP = 0.09 kg/d and r(2) = 0.82 for the Beginning and Final of feedlot phase. Overall, the results indicate that the proposed automated computer vision system can be successfully used to predict BW and ADG in real-time in beef cattle.
id UNSP_49ce836b2265c6ba84fbe0e81636435c
oai_identifier_str oai:repositorio.unesp.br:11449/195235
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phasesBeef cattleComputer visionImage analysisKinect (R)Frequent measurements of body weight (BW) in livestock systems are very important because they allow assessing growth. However, real-time monitoring of animal growth through traditional weighing scales is stressful for animals, costly and labor-intensive. Thus, the objectives of this study were to: 1) assess the predictive quality of an automated computer vision system used to predict BW and average daily gain (ADG) in beef cattle; and 2) compare different predictive approaches, including Multiple Linear Regression (MLR), Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), and Artificial Neutral Networks (ANN). A total of 234 images of Nellore beef cattle were collected during the weaning, stocker and feedlot phases. First, biometric body measurements of each animal, such as body volume, area, length, and others, were performed using three-dimensional images captured with the Kinecto (R) sensor, and their respective BW were acquired using an electronic scale. Next, the biometric measurements were used as explanatory variables in the four predictive approaches (MLR, LASSO, PLS, and ANN). To evaluate prediction quality, a leave-one-out cross-validation was adopted. The ANN was the best prediction approach in terms of Root Mean Square Error of Prediction (RMSEP) and squared predictive correlation (r(2)). The results for Weaning were RMSEP = 8.6 kg and r(2) = 0.91; for Stocker phase, RMSEP = 11.4 kg and r(2) = 0.79; and for Beginning of feedlot, RMSEP = 7.7 kg and r(2) = 0.92. The ANN was also the best method for prediction of ADG, with RMSEP = 0.02 kg/d and r(2) = 0.67 for the period between Weaning and Stocker, RMSEP = 0.02 kg/d and r(2) = 0.85 for the Weaning and Beginning of Feedlot phase, RMSEP = 0.03 kg/d and r(2) = 0.80 for Weaning and Final of Feedlot phase, RMSEP = 0.10 kg/d and r(2) = 0.51 for Stocker and Beginning of feedlot phase, and RMSEP = 0.09 kg/d and r(2) = 0.82 for the Beginning and Final of feedlot phase. Overall, the results indicate that the proposed automated computer vision system can be successfully used to predict BW and ADG in real-time in beef cattle.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Univ Wisconsin, Dept Anim Sci, Madison, WI 53706 USAUniv Wisconsin, Dept Biostat & Med Informat, Madison, WI 53706 USASao Paulo State Univ, Sch Vet Med & Anim Sci, BR-18618681 Botucatu, SP, BrazilSao Paulo State Univ, Sch Agr & Veterinarian Sci, BR-14884900 Jaboticabal, BrazilUniv Fed Lavras, Anim Sci Dept, BR-3720000 Lavras, MG, BrazilUniv Fed Triangulo Mineiro, BR-38280000 Iturama, MG, BrazilSao Paulo State Univ, Sch Vet Med & Anim Sci, BR-18618681 Botucatu, SP, BrazilSao Paulo State Univ, Sch Agr & Veterinarian Sci, BR-14884900 Jaboticabal, BrazilFAPESP: 2017/20812-0FAPESP: 2017/02057-0CAPES: 001Elsevier B.V.Univ WisconsinUniversidade Estadual Paulista (Unesp)Universidade Federal de Lavras (UFLA)Univ Fed Triangulo MineiroCominotte, 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. [UNESP]Baldassini, W. A. [UNESP]Machado Neto, O. R. [UNESP]2020-12-10T17:27:52Z2020-12-10T17:27:52Z2020-02-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article10http://dx.doi.org/10.1016/j.livsci.2019.103904Livestock Science. Amsterdam: Elsevier, v. 232, 10 p., 2020.1871-1413http://hdl.handle.net/11449/19523510.1016/j.livsci.2019.103904WOS:000518489400005Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengLivestock Scienceinfo:eu-repo/semantics/openAccess2021-10-23T07:00:34Zoai:repositorio.unesp.br:11449/195235Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:01:35.015780Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
title Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
spellingShingle Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
Cominotte, A.
Beef cattle
Computer vision
Image analysis
Kinect (R)
title_short Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
title_full Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
title_fullStr Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
title_full_unstemmed Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
title_sort Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases
author Cominotte, A.
author_facet 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. [UNESP]
Baldassini, W. A. [UNESP]
Machado Neto, O. R. [UNESP]
author_role author
author2 Fernandes, A. F. A.
Dorea, J. R. R.
Rosa, G. J. M.
Ladeira, M. M.
van Cleef, E. H. C. B.
Pereira, G. L. [UNESP]
Baldassini, W. A. [UNESP]
Machado Neto, O. R. [UNESP]
author2_role author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Univ Wisconsin
Universidade Estadual Paulista (Unesp)
Universidade Federal de Lavras (UFLA)
Univ Fed Triangulo Mineiro
dc.contributor.author.fl_str_mv 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. [UNESP]
Baldassini, W. A. [UNESP]
Machado Neto, O. R. [UNESP]
dc.subject.por.fl_str_mv Beef cattle
Computer vision
Image analysis
Kinect (R)
topic Beef cattle
Computer vision
Image analysis
Kinect (R)
description Frequent measurements of body weight (BW) in livestock systems are very important because they allow assessing growth. However, real-time monitoring of animal growth through traditional weighing scales is stressful for animals, costly and labor-intensive. Thus, the objectives of this study were to: 1) assess the predictive quality of an automated computer vision system used to predict BW and average daily gain (ADG) in beef cattle; and 2) compare different predictive approaches, including Multiple Linear Regression (MLR), Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), and Artificial Neutral Networks (ANN). A total of 234 images of Nellore beef cattle were collected during the weaning, stocker and feedlot phases. First, biometric body measurements of each animal, such as body volume, area, length, and others, were performed using three-dimensional images captured with the Kinecto (R) sensor, and their respective BW were acquired using an electronic scale. Next, the biometric measurements were used as explanatory variables in the four predictive approaches (MLR, LASSO, PLS, and ANN). To evaluate prediction quality, a leave-one-out cross-validation was adopted. The ANN was the best prediction approach in terms of Root Mean Square Error of Prediction (RMSEP) and squared predictive correlation (r(2)). The results for Weaning were RMSEP = 8.6 kg and r(2) = 0.91; for Stocker phase, RMSEP = 11.4 kg and r(2) = 0.79; and for Beginning of feedlot, RMSEP = 7.7 kg and r(2) = 0.92. The ANN was also the best method for prediction of ADG, with RMSEP = 0.02 kg/d and r(2) = 0.67 for the period between Weaning and Stocker, RMSEP = 0.02 kg/d and r(2) = 0.85 for the Weaning and Beginning of Feedlot phase, RMSEP = 0.03 kg/d and r(2) = 0.80 for Weaning and Final of Feedlot phase, RMSEP = 0.10 kg/d and r(2) = 0.51 for Stocker and Beginning of feedlot phase, and RMSEP = 0.09 kg/d and r(2) = 0.82 for the Beginning and Final of feedlot phase. Overall, the results indicate that the proposed automated computer vision system can be successfully used to predict BW and ADG in real-time in beef cattle.
publishDate 2020
dc.date.none.fl_str_mv 2020-12-10T17:27:52Z
2020-12-10T17:27:52Z
2020-02-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1016/j.livsci.2019.103904
Livestock Science. Amsterdam: Elsevier, v. 232, 10 p., 2020.
1871-1413
http://hdl.handle.net/11449/195235
10.1016/j.livsci.2019.103904
WOS:000518489400005
url http://dx.doi.org/10.1016/j.livsci.2019.103904
http://hdl.handle.net/11449/195235
identifier_str_mv Livestock Science. Amsterdam: Elsevier, v. 232, 10 p., 2020.
1871-1413
10.1016/j.livsci.2019.103904
WOS:000518489400005
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Livestock Science
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 10
dc.publisher.none.fl_str_mv Elsevier B.V.
publisher.none.fl_str_mv Elsevier B.V.
dc.source.none.fl_str_mv Web of Science
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808128740773855232