Lean meat yield estimation using a prototype 3D imaging approach

被引：14

作者：

Alempijevic, Alen ^{[1
]}

Vidal-Calleja, Teresa ^{[1
]}

Falque, Raphael ^{[1
]}

Quin, Phillip ^{[1
]}

Toohey, Edwina ^{[4
]}

Walmsley, Brad ^{[3
]}

McPhee, Malcolm ^{[2
]}

机构：

[1] Univ Technol Sydney, Ctr Autonomous Syst, POB 123,Broadwy, Sydney, NSW 2007, Australia

[2] Livestock Ind Ctr, NSW Dept Primary Ind, Armidale, NSW 2351, Australia

[3] Anim Genet & Breeding Unit, NSW Dept Primary Ind, Armidale, NSW 2351, Australia

[4] Ctr Sheep Meat Dev, NSW Dept Primary Ind, POB 129, Cowra, NSW 2794, Australia

来源：

MEAT SCIENCE | 2021年 / 181卷

关键词：

Lean meat yield; Beef; Carcass grading; Computer vision; LAMB; CLASSIFICATION; ACCURACY; INDUSTRY; MUSCLE; SHAPE; FAT;

D O I：

10.1016/j.meatsci.2021.108470

中图分类号：

TS2 [食品工业];

学科分类号：

0832 ;

摘要：

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.

引用

页数：9

共 26 条

[1]

Allen P, 2009, WOODHEAD PUBL FOOD S, P479, DOI 10.1533/9781845695439.4.479

[2] Intramuscular fat in lamb muscle and the impact of selection for improved carcass lean meat yield [J].

Anderson, F. ;

Pannier, L. ;

Pethick, D. W. ;

Gardner, G. E. .

ANIMAL, 2015, 9 (06) :1081-1090

[3]

Biddle R., 2016, AUSTR BEEF LANGUAGE

[4] In-line image analysis in the slaughter industry, illustrated by Beef Carcass Classification [J].

Borggaard, C ;

Madsen, NT ;

Thodberg, HH .

MEAT SCIENCE, 1996, 43 :S151-S163

[5] The relationship between video image analysis (VIA), visual classification, and saleable meat yield of sirloin and fillet cuts of beef carcasses differing in breed and gender [J].

Craigie, C. R. ;

Ross, D. W. ;

Maltin, C. A. ;

Purchas, R. W. ;

Buenger, L. ;

Roehe, R. ;

Morris, S. T. .

LIVESTOCK SCIENCE, 2013, 158 (1-3) :169-178

[6] A review of the development and use of video image analysis (VIA) for beef carcass evaluation as an alternative to the current EUROP system and other subjective systems [J].

Craigie, C. R. ;

Navajas, E. A. ;

Purchas, R. W. ;

Maltin, C. A. ;

Buenger, L. ;

Hoskin, S. O. ;

Ross, D. W. ;

Morris, S. T. ;

Roehe, R. .

MEAT SCIENCE, 2012, 92 (04) :307-318

[7] Calibration of an on-line dual energy X-ray absorptiometer for estimating carcase composition in lamb at abattoir chain-speed [J].

Gardner, G. E. ;

Starling, S. ;

Charnley, J. ;

Hocking-Edwards, J. ;

Peterse, J. ;

Williams, A. .

MEAT SCIENCE, 2018, 144 :91-99

[8] Video image analysis in the Australian meat industry - precision and accuracy of predicting lean meat yield in lamb carcasses [J].

Hopkins, DL ;

Safari, E ;

Thompson, JM ;

Smith, CR .

MEAT SCIENCE, 2004, 67 (02) :269-274

[9] Screened Poisson Surface Reconstruction [J].

Kazhdan, Michael ;

Hoppe, Hugues .

ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (03)

[10] Prediction of fat, muscle and value in Norwegian lamb carcasses using EUROP classification, carcass shape and length measurements, visible light reflectance and computer tomography (CT) [J].

Kongsro, J. ;

Roe, M. ;

Kvaal, K. ;

Aastveit, A. H. ;

Egelandsdal, B. .

MEAT SCIENCE, 2009, 81 (01) :102-107

← 1 2 3 →