|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Agrossilvipastoril. Para informações adicionais entre em contato com cpamt.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital; Embrapa Agrossilvipastoril. |
Data corrente: |
18/02/2021 |
Data da última atualização: |
02/12/2021 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
KAMCHEN, S. G.; SANTOS, E. F. dos; LOPES, L. B.; VENDRUSCULO, L. G.; CONDOTTA, I. C. F. S. |
Afiliação: |
SCHEILA GEIELE KAMCHEN, UFMT, Cuiaba-MT; ELTON FERNANDES DOS SANTOS, UFMT, Sinop-MT; LUCIANO BASTOS LOPES, CPAMT; LAURIMAR GONCALVES VENDRUSCULO, CNPTIA; ISABELLA C. F. S. CONDOTTA, University of Illinois. |
Título: |
Application of depth sensor to estimate body mass and morphometric assessment in Nellore heifers. |
Ano de publicação: |
2021 |
Fonte/Imprenta: |
Livestock Science, v. 245, 104442, 2021. |
ISSN: |
1871-1413 |
DOI: |
https://doi.org/10.1016/j.livsci.2021.104442 |
Idioma: |
Inglês |
Conteúdo: |
Abstract. The potential of an RGB-D sensor as a tool to estimate Nellore heifers´ body mass and morphometric measurements through image analysis was evaluated. An Intel RealSense D435i depth sensor was used to acquire dorsal images of 260 animals aged between 8 and 18 months. Images were acquired from March to December 2019 in six-time points. The best quality images were selected using a multi-layer perceptron neural network (nn = 547). The images were then manually associated with each animal's electronic ear tag. Morphometric measurements were manually acquired using a hipometer and measured on the images using the OpenCV library's graphical interface. These values were acquired in pixels converted to meters. The adjusted linear regression analysis between body mass measured with a scale and estimated body volume presented a high coefficient of determination of R² = 0.97. The mean absolute percentage error was 3.13%, the absolute error was ± 8.85 kg, and the mean squared error was 10.07 kg. The mean absolute error, mean squared error and mean absolute percentage error between manually acquired and digitally acquired morphometric measurements were: 4.23 cm, 5.34 cm, and 18% for chest width (R² = 0.56); 4.4 cm, 5.1 cm, and 13.9% for croup width (R² = 0.86); 6.0 cm, 8.0 cm, and 19.3% for croup length (R² = 0.75); 4.7 cm, 6.6 cm, and 3.8% for croup height (R² = 0.9); and 3.5 cm, 5.1 cm, and 2.9% for withers height (R² = 0.92). This study showed that it is possible to estimate body mass in Nellore heifers using a depth sensor and has good potential for application on morphometric evaluations. MenosAbstract. The potential of an RGB-D sensor as a tool to estimate Nellore heifers´ body mass and morphometric measurements through image analysis was evaluated. An Intel RealSense D435i depth sensor was used to acquire dorsal images of 260 animals aged between 8 and 18 months. Images were acquired from March to December 2019 in six-time points. The best quality images were selected using a multi-layer perceptron neural network (nn = 547). The images were then manually associated with each animal's electronic ear tag. Morphometric measurements were manually acquired using a hipometer and measured on the images using the OpenCV library's graphical interface. These values were acquired in pixels converted to meters. The adjusted linear regression analysis between body mass measured with a scale and estimated body volume presented a high coefficient of determination of R² = 0.97. The mean absolute percentage error was 3.13%, the absolute error was ± 8.85 kg, and the mean squared error was 10.07 kg. The mean absolute error, mean squared error and mean absolute percentage error between manually acquired and digitally acquired morphometric measurements were: 4.23 cm, 5.34 cm, and 18% for chest width (R² = 0.56); 4.4 cm, 5.1 cm, and 13.9% for croup width (R² = 0.86); 6.0 cm, 8.0 cm, and 19.3% for croup length (R² = 0.75); 4.7 cm, 6.6 cm, and 3.8% for croup height (R² = 0.9); and 3.5 cm, 5.1 cm, and 2.9% for withers height (R² = 0.92). This study showed that it is possible to estimate... Mostrar Tudo |
Palavras-Chave: |
Análise de imagem; Massa corporal; Nellore heifers´ body mass; Novilhas Nelore; Pecuária de precisão; Precision livestock farming; RealSense D435i; Sensor RGB-D. |
Thesagro: |
Gado; Gado Nelore. |
Thesaurus Nal: |
Body mass index; Cattle; Heifers; Image analysis. |
Categoria do assunto: |
-- X Pesquisa, Tecnologia e Engenharia |
Marc: |
LEADER 02682naa a2200361 a 4500 001 2136987 005 2021-12-02 008 2021 bl uuuu u00u1 u #d 022 $a1871-1413 024 7 $ahttps://doi.org/10.1016/j.livsci.2021.104442$2DOI 100 1 $aKAMCHEN, S. G. 245 $aApplication of depth sensor to estimate body mass and morphometric assessment in Nellore heifers.$h[electronic resource] 260 $c2021 520 $aAbstract. The potential of an RGB-D sensor as a tool to estimate Nellore heifers´ body mass and morphometric measurements through image analysis was evaluated. An Intel RealSense D435i depth sensor was used to acquire dorsal images of 260 animals aged between 8 and 18 months. Images were acquired from March to December 2019 in six-time points. The best quality images were selected using a multi-layer perceptron neural network (nn = 547). The images were then manually associated with each animal's electronic ear tag. Morphometric measurements were manually acquired using a hipometer and measured on the images using the OpenCV library's graphical interface. These values were acquired in pixels converted to meters. The adjusted linear regression analysis between body mass measured with a scale and estimated body volume presented a high coefficient of determination of R² = 0.97. The mean absolute percentage error was 3.13%, the absolute error was ± 8.85 kg, and the mean squared error was 10.07 kg. The mean absolute error, mean squared error and mean absolute percentage error between manually acquired and digitally acquired morphometric measurements were: 4.23 cm, 5.34 cm, and 18% for chest width (R² = 0.56); 4.4 cm, 5.1 cm, and 13.9% for croup width (R² = 0.86); 6.0 cm, 8.0 cm, and 19.3% for croup length (R² = 0.75); 4.7 cm, 6.6 cm, and 3.8% for croup height (R² = 0.9); and 3.5 cm, 5.1 cm, and 2.9% for withers height (R² = 0.92). This study showed that it is possible to estimate body mass in Nellore heifers using a depth sensor and has good potential for application on morphometric evaluations. 650 $aBody mass index 650 $aCattle 650 $aHeifers 650 $aImage analysis 650 $aGado 650 $aGado Nelore 653 $aAnálise de imagem 653 $aMassa corporal 653 $aNellore heifers´ body mass 653 $aNovilhas Nelore 653 $aPecuária de precisão 653 $aPrecision livestock farming 653 $aRealSense D435i 653 $aSensor RGB-D 700 1 $aSANTOS, E. F. dos 700 1 $aLOPES, L. B. 700 1 $aVENDRUSCULO, L. G. 700 1 $aCONDOTTA, I. C. F. S 773 $tLivestock Science$gv. 245, 104442, 2021.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agrossilvipastoril (CPAMT) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registros recuperados : 83 | |
11. | | ROCHA, K. C. G.; SILVA, R. A. da; MICHELOTTO, M. D.; BUSOLI, A. C. Aspectos biológicos, morfológicos e comportamentais de Aspidiotus nerii Bouché, 1833 (Hemiptera: Diaspididae). Ciência Rural, Santa Maria, v. 36, n. 2, p. 363-368, mar./abr. 2006.Tipo: Artigo em Periódico Indexado | Circulação/Nível: Nacional - B |
Biblioteca(s): Embrapa Amapá. |
| |
14. | | JANINI, J. C.; BOIÇA JÚNIOR, A. L.; GODOY, I. J.; MICHELOTTO, M. D.; FAVERO, A. P. Comparação de desenvolvimento de plantas de espécies silvestres de Arachis, sob o ataque de Enneothrips flavens e Stegasta bosquella com e sem controle químico. In: CONGRESSO BRASILEIRO DE ENTOMOLOGIA, 23., 2010, Natal. Anais... Natal: SBE, 2010Tipo: Resumo em Anais de Congresso |
Biblioteca(s): Embrapa Recursos Genéticos e Biotecnologia. |
| |
15. | | JANINI, J. C.; BOIÇA JÚNIOR, A. L.; GODOY, I. J.; MICHELOTTO, M. D.; FAVERO, A. P. Comparação de desenvolvimento de plantas de espécies silvestres de Arachis, sob o ataque de Enneothrips flavens e Stegasta bosquella com e sem controle químico. In: CONGRESSO BRASILEIRO DE ENTOMOLOGIA, 23., 2010, Natal. Anais... Natal: SBE, 2010Tipo: Resumo em Anais de Congresso |
Biblioteca(s): Embrapa Pecuária Sudeste. |
| |
16. | | MICHELOTTO, M. D.; GODOY, I. J. de; FAVERO, A. P.; CARREGA, W. C.; FINOTO, E. L. Ocurrence of enneothrips flavens moulton and stegasta bosquella (chambers) and its effects on agronomic traits of wild arachis accessions. Bioscience Journal, Uberlândia, v. 29, n. 1, p. 115-124, mar./apr. 2013.Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 2 |
Biblioteca(s): Embrapa Pecuária Sudeste. |
| |
19. | | CHAGAS FILHO, N. R.; MICHELOTTO, M. D.; SILVA, R. A. da; BUSOLI, A. C. Desenvolvimento ninfal de Myzus persicae (Sulzer, 1776) (Hemiptera: Aphididae) sobre berinjela em diferentes temperaturas. Bragantia, Campinas, v. 64, n. 2, p. 257-262, 2005.Biblioteca(s): Embrapa Amapá. |
| |
20. | | SILVA, R. A. da; GUERREIRO, J. C.; MICHELOTTO, M. D.; BUSOLI, A. C. Desenvolvimento e comportamento de predação de Coccidophilus citricola Brèthes, 1905 (Coleoptera: Coccinellidae) sobre Aspodiotus nerri Bouché, 1833 (Hemiptera: Diaspididae). Boletín de Sanidad Vegetal, Madrid, v. 29, n. 1, p. 9-15, 2003.Tipo: Artigo em Periódico Indexado | Circulação/Nível: Internacional - B |
Biblioteca(s): Embrapa Amapá. |
| |
Registros recuperados : 83 | |
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|