On-line weight estimation of broiler carcass and cuts by a computer vision system

ABSTRACT: In a broiler carcass production conveyor system, inspection, monitoring, and grading carcass and cuts based on computer vision techniques are challenging due to cuts segmentation and ambient light conditions issues. This study presents a depth image-based broiler carcass weight prediction...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Innocent Nyalala, Cedric Okinda, Nelson Makange, Tchalla Korohou, Qi Chao, Luke Nyalala, Zhang Jiayu, Zuo Yi, Khurram Yousaf, Liu Chao, Chen Kunjie
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/0e22200fdae54ef7808d4e754cb4966f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0e22200fdae54ef7808d4e754cb4966f
record_format dspace
spelling oai:doaj.org-article:0e22200fdae54ef7808d4e754cb4966f2021-11-24T04:21:54ZOn-line weight estimation of broiler carcass and cuts by a computer vision system0032-579110.1016/j.psj.2021.101474https://doaj.org/article/0e22200fdae54ef7808d4e754cb4966f2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S0032579121004971https://doaj.org/toc/0032-5791ABSTRACT: In a broiler carcass production conveyor system, inspection, monitoring, and grading carcass and cuts based on computer vision techniques are challenging due to cuts segmentation and ambient light conditions issues. This study presents a depth image-based broiler carcass weight prediction system. An Active Shape Model was developed to segment the carcass into 4 cuts (drumsticks, breasts, wings, and head and neck). Five regression models were developed based on the image features for each weight estimation (carcass and its cuts). The Bayesian-ANN model outperformed all other regression models at 0.9981 R2 and 0.9847 R2 in the whole carcass and head and neck weight estimation. The RBF-SVR model surpassed all the other drumstick, breast, and wings weight prediction models at 0.9129 R2, 0.9352 R2, and 0.9896 R2, respectively. This proposed technique can be applied as a nondestructive, nonintrusive, and accurate on-line broiler carcass production system in the automation of chicken carcass and cuts weight estimation.Innocent NyalalaCedric OkindaNelson MakangeTchalla KorohouQi ChaoLuke NyalalaZhang JiayuZuo YiKhurram YousafLiu ChaoChen KunjieElsevierarticlebroiler carcassescarcass weightcomputer vision systemregression modelingstatistical modelingAnimal cultureSF1-1100ENPoultry Science, Vol 100, Iss 12, Pp 101474- (2021)
institution DOAJ
collection DOAJ
language EN
topic broiler carcasses
carcass weight
computer vision system
regression modeling
statistical modeling
Animal culture
SF1-1100
spellingShingle broiler carcasses
carcass weight
computer vision system
regression modeling
statistical modeling
Animal culture
SF1-1100
Innocent Nyalala
Cedric Okinda
Nelson Makange
Tchalla Korohou
Qi Chao
Luke Nyalala
Zhang Jiayu
Zuo Yi
Khurram Yousaf
Liu Chao
Chen Kunjie
On-line weight estimation of broiler carcass and cuts by a computer vision system
description ABSTRACT: In a broiler carcass production conveyor system, inspection, monitoring, and grading carcass and cuts based on computer vision techniques are challenging due to cuts segmentation and ambient light conditions issues. This study presents a depth image-based broiler carcass weight prediction system. An Active Shape Model was developed to segment the carcass into 4 cuts (drumsticks, breasts, wings, and head and neck). Five regression models were developed based on the image features for each weight estimation (carcass and its cuts). The Bayesian-ANN model outperformed all other regression models at 0.9981 R2 and 0.9847 R2 in the whole carcass and head and neck weight estimation. The RBF-SVR model surpassed all the other drumstick, breast, and wings weight prediction models at 0.9129 R2, 0.9352 R2, and 0.9896 R2, respectively. This proposed technique can be applied as a nondestructive, nonintrusive, and accurate on-line broiler carcass production system in the automation of chicken carcass and cuts weight estimation.
format article
author Innocent Nyalala
Cedric Okinda
Nelson Makange
Tchalla Korohou
Qi Chao
Luke Nyalala
Zhang Jiayu
Zuo Yi
Khurram Yousaf
Liu Chao
Chen Kunjie
author_facet Innocent Nyalala
Cedric Okinda
Nelson Makange
Tchalla Korohou
Qi Chao
Luke Nyalala
Zhang Jiayu
Zuo Yi
Khurram Yousaf
Liu Chao
Chen Kunjie
author_sort Innocent Nyalala
title On-line weight estimation of broiler carcass and cuts by a computer vision system
title_short On-line weight estimation of broiler carcass and cuts by a computer vision system
title_full On-line weight estimation of broiler carcass and cuts by a computer vision system
title_fullStr On-line weight estimation of broiler carcass and cuts by a computer vision system
title_full_unstemmed On-line weight estimation of broiler carcass and cuts by a computer vision system
title_sort on-line weight estimation of broiler carcass and cuts by a computer vision system
publisher Elsevier
publishDate 2021
url https://doaj.org/article/0e22200fdae54ef7808d4e754cb4966f
work_keys_str_mv AT innocentnyalala onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT cedricokinda onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT nelsonmakange onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT tchallakorohou onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT qichao onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT lukenyalala onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT zhangjiayu onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT zuoyi onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT khurramyousaf onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT liuchao onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
AT chenkunjie onlineweightestimationofbroilercarcassandcutsbyacomputervisionsystem
_version_ 1718416018604294144