Lean meat yield estimation using a prototype 3D imaging approach

Alen Alempijevic; Teresa Vidal-Calleja; Raphael Falque; Phillip Quin; Edwina Toohey; Brad Walmsley; Malcolm McPhee

doi:10.1016/j.meatsci.2021.108470

Lean meat yield estimation using a prototype 3D imaging approach

Meat Sci. 2021 Nov:181:108470. doi: 10.1016/j.meatsci.2021.108470. Epub 2021 Feb 19.

Authors

Alen Alempijevic¹, Teresa Vidal-Calleja², Raphael Falque³, Phillip Quin⁴, Edwina Toohey⁵, Brad Walmsley⁶, Malcolm McPhee⁷

Affiliations

¹ Center for Autonomous Systems, University of Technology Sydney, P.O. Box 123, Broadway, NSW 2007, Australia. Electronic address: alen.alempijevic@uts.edu.au.
² Center for Autonomous Systems, University of Technology Sydney, P.O. Box 123, Broadway, NSW 2007, Australia. Electronic address: teresa.vidalcalleja@uts.edu.au.
³ Center for Autonomous Systems, University of Technology Sydney, P.O. Box 123, Broadway, NSW 2007, Australia. Electronic address: raphael.guenot-falque@uts.edu.au.
⁴ Center for Autonomous Systems, University of Technology Sydney, P.O. Box 123, Broadway, NSW 2007, Australia. Electronic address: phillip.quin@uts.edu.au.
⁵ NSW Department of Primary Industries, Centre for Sheep Meat Development, P.O. Box 129, Cowra, NSW 2794, Australia. Electronic address: edwina.toohey@dpi.nsw.gov.au.
⁶ NSW Department of Primary Industries, Animal Genetics and Breeding Unit (AGBU: AGBU is a joint venture of NSW Department of Primary Industries and University of New England), Armidale, NSW 2351, Australia. Electronic address: brad.walmsley@dpi.nsw.gov.au.
⁷ NSW Department of Primary Industries, Livestock Industries Centre, Armidale, NSW 2351, Australia. Electronic address: malcolm.mcphee@dpi.nsw.gov.au.

PMID: 33642037
DOI: 10.1016/j.meatsci.2021.108470

Abstract

Lean Meat Yield (LMY, %) of carcass is an important industry trait, which currently is not routinely measured in Australian beef abattoirs. Objective on-line technology to determine LMY is key for wider adoption. This paper presents a proof-of-concept approach for estimating the LMY of beef carcasses from the 3D information provided by RGB-D cameras. Moreover, a specifically designed on-line data acquisition system for abattoir applications is presented, consisting of three cameras moving on a scanning rig to generate 3D carcass side reconstructions. The hindquarter is then segmented consistently across all the 3D models to extract curvature information and LMY estimated via non-linear regression based on Gaussian Process models. Sides from 119 carcasses at two different commercial abattoirs were used to evaluate this approach. Results from this preliminary study (RMSE = 3.91%, R² = 0.69) using curvature, P8 fat and HSCW indicate that 3D imaging of beef carcasses is a viable and relatively accurate technology to estimate LMY.

Keywords: Beef; Carcass grading; Computer vision; Lean meat yield.

MeSH terms

Abattoirs
Animals
Body Composition*
Cattle
Female
Imaging, Three-Dimensional / methods
Imaging, Three-Dimensional / veterinary*
Male
Red Meat / analysis*