| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Gado de Leite. |
|
Data corrente: |
23/09/2021 |
|
Data da última atualização: |
12/10/2021 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
OLIVEIRA, D. A. B.; PEREIRA, L. G. R.; BRESOLIN, T.; FERREIRA, R. E. P.; DREA, J. R. R. |
|
Afiliação: |
DARIO AUGUSTO BORGES OLIVEIRA, University of Wisconsin; LUIZ GUSTAVO RIBEIRO PEREIRA, CNPGL; TIAGO BRESOLIN, University of Wisconsin; RAFAEL ENRICH PONTES FERREIRA, University of Wisconsin; JOO RICARDO REBOUAS DREA, University of Wisconsin. |
|
Título: |
A review of deep learning algorithms for computer vision systems in livestock. |
|
Ano de publicação: |
2021 |
|
Fonte/Imprenta: |
Livestock Science, v. 253, 104700, 2021. |
|
Idioma: |
Inglês |
|
Conteúdo: |
In livestock operations, systematically monitoring animal body weight, bio-metric body measurements, animal behavior, feed bunk, and other difficult-to-measure phenotypes is manually unfeasible due to labor, costs, and animal stress. Applications of computer vision are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. However, the development of a computer vision system requires sophisticated statistical and computational approaches for efficient data management and appropriate data mining, as it involves mas-sive datasets. This article aims to provide an overview of how deep learning has been implemented in computer vision systems used in livestock, and how such implementation can be an effective tool to predict animal phe-notypes and to accelerate the development of predictive modeling for precise management decisions. First, we reviewed the most recent milestones achieved with computer vision systems and its respective deep learning algorithms implemented in Animal Science studies. Second, we reviewed the published research studies in Animal Science, which used deep learning algorithms as the primary analytical strategy for image classification, object detection, object segmentation, and feature extraction. The great number of reviewed articles published in the last few years demonstrates the high interest and rapid development of deep learning algorithms in computer vision systems across livestock species. Deep learning algorithms for computer vision systems, such as Mask R-CNN, Faster R-CNN, YOLO (v3 and v4), DeepLab v3, U-Net and others have been used in Animal Science research studies. Additionally, network architectures such as ResNet, Inception, Xception, and VGG16 have been implemented in several studies across livestock species. The great performance of these deep learning algorithms suggests an33improved predictive ability in livestock applications and a faster inference.34However, only a few articles fully described the deep learning algorithms and its implementation. Thus, information regarding hyperparameter tuning, pre-trained weights, deep learning backbone, and hierarchical data structure were missed. We summarized peer-reviewed articles by computer vision tasks38(image classification, object detection, and object segmentation), deep learn-39ing algorithms, species, and phenotypes including animal identification and behavior, feed intake, animal body weight, and many others. Understanding the principles of computer vision and the algorithms used for each application is crucial to develop efficient systems in livestock operations. Such development will potentially have a major impact on the livestock industry by predicting real-time and accurate phenotypes, which could be used in the future to improve farm management decisions, breeding programs through high-throughput phenotyping, and optimized data-driven interventions. MenosIn livestock operations, systematically monitoring animal body weight, bio-metric body measurements, animal behavior, feed bunk, and other difficult-to-measure phenotypes is manually unfeasible due to labor, costs, and animal stress. Applications of computer vision are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. However, the development of a computer vision system requires sophisticated statistical and computational approaches for efficient data management and appropriate data mining, as it involves mas-sive datasets. This article aims to provide an overview of how deep learning has been implemented in computer vision systems used in livestock, and how such implementation can be an effective tool to predict animal phe-notypes and to accelerate the development of predictive modeling for precise management decisions. First, we reviewed the most recent milestones achieved with computer vision systems and its respective deep learning algorithms implemented in Animal Science studies. Second, we reviewed the published research studies in Animal Science, which used deep learning algorithms as the primary analytical strategy for image classification, object detection, object segmentation, and feature extraction. The great number of reviewed articles published in the last few years demonstrates the high interest and rapid development of deep learning algorithms in computer vision systems a... Mostrar Tudo |
|
Palavras-Chave: |
Inteligência artificial; Machine learning. |
|
Thesagro: |
Agricultura de Precisão; Gado; Suíno. |
|
Thesaurus Nal: |
Artificial intelligence. |
|
Categoria do assunto: |
L Ciência Animal e Produtos de Origem Animal |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/226878/1/Review-deep.pdf
|
|
Marc: |
LEADER 03678naa a2200241 a 4500
001 2134741
005 2021-10-12
008 2021 bl uuuu u00u1 u #d
100 1 $aOLIVEIRA, D. A. B.
245 $aA review of deep learning algorithms for computer vision systems in livestock.$h[electronic resource]
260 $c2021
520 $aIn livestock operations, systematically monitoring animal body weight, bio-metric body measurements, animal behavior, feed bunk, and other difficult-to-measure phenotypes is manually unfeasible due to labor, costs, and animal stress. Applications of computer vision are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. However, the development of a computer vision system requires sophisticated statistical and computational approaches for efficient data management and appropriate data mining, as it involves mas-sive datasets. This article aims to provide an overview of how deep learning has been implemented in computer vision systems used in livestock, and how such implementation can be an effective tool to predict animal phe-notypes and to accelerate the development of predictive modeling for precise management decisions. First, we reviewed the most recent milestones achieved with computer vision systems and its respective deep learning algorithms implemented in Animal Science studies. Second, we reviewed the published research studies in Animal Science, which used deep learning algorithms as the primary analytical strategy for image classification, object detection, object segmentation, and feature extraction. The great number of reviewed articles published in the last few years demonstrates the high interest and rapid development of deep learning algorithms in computer vision systems across livestock species. Deep learning algorithms for computer vision systems, such as Mask R-CNN, Faster R-CNN, YOLO (v3 and v4), DeepLab v3, U-Net and others have been used in Animal Science research studies. Additionally, network architectures such as ResNet, Inception, Xception, and VGG16 have been implemented in several studies across livestock species. The great performance of these deep learning algorithms suggests an33improved predictive ability in livestock applications and a faster inference.34However, only a few articles fully described the deep learning algorithms and its implementation. Thus, information regarding hyperparameter tuning, pre-trained weights, deep learning backbone, and hierarchical data structure were missed. We summarized peer-reviewed articles by computer vision tasks38(image classification, object detection, and object segmentation), deep learn-39ing algorithms, species, and phenotypes including animal identification and behavior, feed intake, animal body weight, and many others. Understanding the principles of computer vision and the algorithms used for each application is crucial to develop efficient systems in livestock operations. Such development will potentially have a major impact on the livestock industry by predicting real-time and accurate phenotypes, which could be used in the future to improve farm management decisions, breeding programs through high-throughput phenotyping, and optimized data-driven interventions.
650 $aArtificial intelligence
650 $aAgricultura de Precisão
650 $aGado
650 $aSuíno
653 $aInteligência artificial
653 $aMachine learning
700 1 $aPEREIRA, L. G. R.
700 1 $aBRESOLIN, T.
700 1 $aFERREIRA, R. E. P.
700 1 $aDREA, J. R. R.
773 $tLivestock Science$gv. 253, 104700, 2021.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Gado de Leite (CNPGL) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Gado de Corte. |
|
Data corrente: |
16/10/2012 |
|
Data da última atualização: |
16/10/2012 |
|
Tipo da produção científica: |
Resumo em Anais de Congresso |
|
Autoria: |
QUEIROZ, C. A.; LOBO JUNIOR, M.; FERNANDES, C. D.; VALLE, C. B.; JANK, L.; BATISTA, M. V.; CHERMOUTH, K. S.; MALLMANN, G.; CARVALHO, C.; FERNANDES, E. T.; SILVA, M. J.; QUETEZ, F. A. |
|
Afiliação: |
C. A. QUEIROZ, mestranda UEMS; MURILLO LOBO JUNIOR, CNPAF; CELSO DORNELAS FERNANDES, CNPGC; CACILDA BORGES DO VALLE, CNPGC; LIANA JANK, CNPGC; MARGARETH VIEIRA BATISTA, CNPGC; K. S. CHERMOUTH; G. MALLMANN; C. CARVALHO; E. T. FERNANDES; M. J. SILVA; F. A. Q. |
|
Título: |
Efeito de gramíneas forrageiras sobre a germinação carpogênica de Sclerotinia sclerotiorum e atividade microbiana no solo. |
|
Ano de publicação: |
2012 |
|
Fonte/Imprenta: |
Summa Phytopathologica, São Paulo, v. 38, fev. 2012. Suplemento, ref. 124. Edição dos Resumos do XXXV Congresso Paulista de Fitopatologia, Jaguariúna, fev. 2012. |
|
Descrição Física: |
1 CD-ROM. |
|
Idioma: |
Português |
|
Conteúdo: |
Estudaram-se o efeito do cultivo de Brachiaria spp. (B. ruziziensis, B. brizantha cv. Piatã, B. humidicola cv. Tupi, acessos B4, B6 e H1), Panicum maximum (P. maximum cvs. Tanzânia e Massai, acessos PM32, PM36, PM45 e PM46), milheto e pousio sobre a germinação carpogênica de Sclerotinia sclerotiorum e a atividade microbiana no solo. |
|
Palavras-Chave: |
Germinação carpogênica. |
|
Categoria do assunto: |
-- |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/67337/1/ResumoCPF-124.pdf
|
|
Marc: |
LEADER 01279naa a2200277 a 4500
001 1936786
005 2012-10-16
008 2012 bl uuuu u00u1 u #d
100 1 $aQUEIROZ, C. A.
245 $aEfeito de gramíneas forrageiras sobre a germinação carpogênica de Sclerotinia sclerotiorum e atividade microbiana no solo.$h[electronic resource]
260 $c2012
300 $c1 CD-ROM.
520 $aEstudaram-se o efeito do cultivo de Brachiaria spp. (B. ruziziensis, B. brizantha cv. Piatã, B. humidicola cv. Tupi, acessos B4, B6 e H1), Panicum maximum (P. maximum cvs. Tanzânia e Massai, acessos PM32, PM36, PM45 e PM46), milheto e pousio sobre a germinação carpogênica de Sclerotinia sclerotiorum e a atividade microbiana no solo.
653 $aGerminação carpogênica
700 1 $aLOBO JUNIOR, M.
700 1 $aFERNANDES, C. D.
700 1 $aVALLE, C. B.
700 1 $aJANK, L.
700 1 $aBATISTA, M. V.
700 1 $aCHERMOUTH, K. S.
700 1 $aMALLMANN, G.
700 1 $aCARVALHO, C.
700 1 $aFERNANDES, E. T.
700 1 $aSILVA, M. J.
700 1 $aQUETEZ, F. A.
773 $tSumma Phytopathologica, São Paulo$gv. 38, fev. 2012. Suplemento, ref. 124. Edição dos Resumos do XXXV Congresso Paulista de Fitopatologia, Jaguariúna, fev. 2012.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Gado de Corte (CNPGC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
