Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals

G A Miller, JJ Hyslop, DW Ross, David Barclay, Andrew Edwards, Willie Thomson, SM Troy, C-A Duthie

Research output: Contribution to conferenceAbstract

Abstract

The performance of beef cattle is currently evaluated through visual assessment or by weighing through a crush. Video imaging analysis (VIA) is increasingly used in abattoirs to grade carcasses and there is potential for 3D imaging to be used on farm to predict carcass characteristics of live animals. The objectives of this study were to validate the use of a water trough system with automated weighing platform and 3D camera technology to track growth and predict carcass characteristics of live animals using artificial neural networks (ANNs). A variety of breeds (steers and heifers) were placed behind systems on five finishing units for 1-3 months pre slaughter. Images and weights were passively collected each time an animal came to the trough and cattle were tracked through the abattoir at slaughter. An abattoir trial was also conducted where live animals were weighed and 3D images taken in the lairage immediately pre-slaughter. Cold carcass weight (CCW) was provided by the abattoir. Saleable meat yield (SMY) and fat and conformation grades were determined by VIA of carcass images. The relationship between weights measured in a crush and the average of weights measured in the crate on the same day had an R2 of 0.99. ANN prediction performance was assessed by regression for liveweight (R2 = 0.72), CCW (R2 = 0.91) and SMY (R2 = 0.80). ANNs predicted EUROP fat and conformation grades with 63% and 69% accuracy, respectively. Performance of individual animals can be tracked through accurate, daily weights obtained without the need for manual handling. Carcass characteristics can be predicted for live animals on farm using 3D imaging technology. This system presents an opportunity to reduce a considerable inefficiency in beef production enterprises through marketing of animals at the optimal time.
Original languageEnglish
Publication statusPrint publication - 2018
EventEAAP 69th Annual Meeting: Conventional and traditional livestock production systems - new challenges - Dubrovnik, Croatia
Duration: 27 Aug 201831 Aug 2018

Conference

ConferenceEAAP 69th Annual Meeting
CountryCroatia
CityDubrovnik
Period27/08/1831/08/18

Fingerprint

carcass characteristics
beef cattle
beef
monitoring
slaughterhouses
animals
image analysis
neural networks
slaughter
carcass weight
meat
water troughs
lairage
farms
crates
lipids
cameras
marketing
heifers
finishing

Cite this

Miller, G. A., Hyslop, JJ., Ross, DW., Barclay, D., Edwards, A., Thomson, W., ... Duthie, C-A. (2018). Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals. Abstract from EAAP 69th Annual Meeting, Dubrovnik, Croatia.
Miller, G A ; Hyslop, JJ ; Ross, DW ; Barclay, David ; Edwards, Andrew ; Thomson, Willie ; Troy, SM ; Duthie, C-A. / Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals. Abstract from EAAP 69th Annual Meeting, Dubrovnik, Croatia.
@conference{c78b75e68a3349f69bc1071f2d855430,
title = "Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals",
abstract = "The performance of beef cattle is currently evaluated through visual assessment or by weighing through a crush. Video imaging analysis (VIA) is increasingly used in abattoirs to grade carcasses and there is potential for 3D imaging to be used on farm to predict carcass characteristics of live animals. The objectives of this study were to validate the use of a water trough system with automated weighing platform and 3D camera technology to track growth and predict carcass characteristics of live animals using artificial neural networks (ANNs). A variety of breeds (steers and heifers) were placed behind systems on five finishing units for 1-3 months pre slaughter. Images and weights were passively collected each time an animal came to the trough and cattle were tracked through the abattoir at slaughter. An abattoir trial was also conducted where live animals were weighed and 3D images taken in the lairage immediately pre-slaughter. Cold carcass weight (CCW) was provided by the abattoir. Saleable meat yield (SMY) and fat and conformation grades were determined by VIA of carcass images. The relationship between weights measured in a crush and the average of weights measured in the crate on the same day had an R2 of 0.99. ANN prediction performance was assessed by regression for liveweight (R2 = 0.72), CCW (R2 = 0.91) and SMY (R2 = 0.80). ANNs predicted EUROP fat and conformation grades with 63{\%} and 69{\%} accuracy, respectively. Performance of individual animals can be tracked through accurate, daily weights obtained without the need for manual handling. Carcass characteristics can be predicted for live animals on farm using 3D imaging technology. This system presents an opportunity to reduce a considerable inefficiency in beef production enterprises through marketing of animals at the optimal time.",
author = "Miller, {G A} and JJ Hyslop and DW Ross and David Barclay and Andrew Edwards and Willie Thomson and SM Troy and C-A Duthie",
year = "2018",
language = "English",
note = "EAAP 69th Annual Meeting : Conventional and traditional livestock production systems - new challenges ; Conference date: 27-08-2018 Through 31-08-2018",

}

Miller, GA, Hyslop, JJ, Ross, DW, Barclay, D, Edwards, A, Thomson, W, Troy, SM & Duthie, C-A 2018, 'Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals' EAAP 69th Annual Meeting, Dubrovnik, Croatia, 27/08/18 - 31/08/18, .

Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals. / Miller, G A; Hyslop, JJ; Ross, DW; Barclay, David; Edwards, Andrew; Thomson, Willie; Troy, SM; Duthie, C-A.

2018. Abstract from EAAP 69th Annual Meeting, Dubrovnik, Croatia.

Research output: Contribution to conferenceAbstract

TY - CONF

T1 - Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals

AU - Miller, G A

AU - Hyslop, JJ

AU - Ross, DW

AU - Barclay, David

AU - Edwards, Andrew

AU - Thomson, Willie

AU - Troy, SM

AU - Duthie, C-A

PY - 2018

Y1 - 2018

N2 - The performance of beef cattle is currently evaluated through visual assessment or by weighing through a crush. Video imaging analysis (VIA) is increasingly used in abattoirs to grade carcasses and there is potential for 3D imaging to be used on farm to predict carcass characteristics of live animals. The objectives of this study were to validate the use of a water trough system with automated weighing platform and 3D camera technology to track growth and predict carcass characteristics of live animals using artificial neural networks (ANNs). A variety of breeds (steers and heifers) were placed behind systems on five finishing units for 1-3 months pre slaughter. Images and weights were passively collected each time an animal came to the trough and cattle were tracked through the abattoir at slaughter. An abattoir trial was also conducted where live animals were weighed and 3D images taken in the lairage immediately pre-slaughter. Cold carcass weight (CCW) was provided by the abattoir. Saleable meat yield (SMY) and fat and conformation grades were determined by VIA of carcass images. The relationship between weights measured in a crush and the average of weights measured in the crate on the same day had an R2 of 0.99. ANN prediction performance was assessed by regression for liveweight (R2 = 0.72), CCW (R2 = 0.91) and SMY (R2 = 0.80). ANNs predicted EUROP fat and conformation grades with 63% and 69% accuracy, respectively. Performance of individual animals can be tracked through accurate, daily weights obtained without the need for manual handling. Carcass characteristics can be predicted for live animals on farm using 3D imaging technology. This system presents an opportunity to reduce a considerable inefficiency in beef production enterprises through marketing of animals at the optimal time.

AB - The performance of beef cattle is currently evaluated through visual assessment or by weighing through a crush. Video imaging analysis (VIA) is increasingly used in abattoirs to grade carcasses and there is potential for 3D imaging to be used on farm to predict carcass characteristics of live animals. The objectives of this study were to validate the use of a water trough system with automated weighing platform and 3D camera technology to track growth and predict carcass characteristics of live animals using artificial neural networks (ANNs). A variety of breeds (steers and heifers) were placed behind systems on five finishing units for 1-3 months pre slaughter. Images and weights were passively collected each time an animal came to the trough and cattle were tracked through the abattoir at slaughter. An abattoir trial was also conducted where live animals were weighed and 3D images taken in the lairage immediately pre-slaughter. Cold carcass weight (CCW) was provided by the abattoir. Saleable meat yield (SMY) and fat and conformation grades were determined by VIA of carcass images. The relationship between weights measured in a crush and the average of weights measured in the crate on the same day had an R2 of 0.99. ANN prediction performance was assessed by regression for liveweight (R2 = 0.72), CCW (R2 = 0.91) and SMY (R2 = 0.80). ANNs predicted EUROP fat and conformation grades with 63% and 69% accuracy, respectively. Performance of individual animals can be tracked through accurate, daily weights obtained without the need for manual handling. Carcass characteristics can be predicted for live animals on farm using 3D imaging technology. This system presents an opportunity to reduce a considerable inefficiency in beef production enterprises through marketing of animals at the optimal time.

M3 - Abstract

ER -

Miller GA, Hyslop JJ, Ross DW, Barclay D, Edwards A, Thomson W et al. Beef Monitor: tracking beef cattle growth and predicting carcass characteristics of live animals. 2018. Abstract from EAAP 69th Annual Meeting, Dubrovnik, Croatia.