|
|
Registros recuperados : 1 | |
Registros recuperados : 1 | |
|
|
Registro Completo
Biblioteca(s): |
Embrapa Agricultura Digital; Embrapa Pecuária Sudeste. |
Data corrente: |
15/04/2020 |
Data da última atualização: |
17/04/2020 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Circulação/Nível: |
A - 1 |
Autoria: |
BARBEDO, J. G. A.; KOENIGKAN, L. V.; SANTOS, P. M.; RIBEIRO, A. R. B. |
Afiliação: |
JAYME GARCIA ARNAL BARBEDO, CNPTIA; LUCIANO VIEIRA KOENIGKAN, CNPTIA; PATRICIA MENEZES SANTOS, CPPSE; ANDREA ROBERTO BUENO RIBEIRO, UNISA; UNIP. |
Título: |
Counting cattle in UAV images: dealing with clustered animals and animal/background contrast changes. |
Ano de publicação: |
2020 |
Fonte/Imprenta: |
Sensors, v. 20, n. 7, p. 1-14, Apr. 2020. |
DOI: |
10.3390/s20072126 |
Idioma: |
Inglês |
Notas: |
Article number: 2126. |
Conteúdo: |
Abstract: The management of livestock in extensive production systems may be challenging, especially in large areas. Using Unmanned Aerial Vehicles (UAVs) to collect images from the area of interest is quickly becoming a viable alternative, but suitable algorithms for extraction of relevant information from the images are still rare. This article proposes a method for counting cattle which combines a deep learning model for rough animal location, color space manipulation to increase contrast between animals and background, mathematical morphology to isolate the animals and infer the number of individuals in clustered groups, and image matching to take into account image overlap. Using Nelore and Canchim breeds as a case study, the proposed approach yields accuracies over 90% under a wide variety of conditions and backgrounds. |
Palavras-Chave: |
Canchim breed; Convolutional neural networks; Deep learning mode; Mathematical morphology; Nelore breed; Rede neural convolucional; Redes neurais; Veículo aéreo não tripulado. |
Thesagro: |
Gado Canchim; Gado de Corte; Gado Nelore. |
Thesaurus NAL: |
Neural networks; Unmanned aerial vehicles. |
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/212350/1/AP-Couting-cattle.pdf
|
Marc: |
LEADER 01863naa a2200337 a 4500 001 2121664 005 2020-04-17 008 2020 bl uuuu u00u1 u #d 024 7 $a10.3390/s20072126$2DOI 100 1 $aBARBEDO, J. G. A. 245 $aCounting cattle in UAV images$bdealing with clustered animals and animal/background contrast changes.$h[electronic resource] 260 $c2020 500 $aArticle number: 2126. 520 $aAbstract: The management of livestock in extensive production systems may be challenging, especially in large areas. Using Unmanned Aerial Vehicles (UAVs) to collect images from the area of interest is quickly becoming a viable alternative, but suitable algorithms for extraction of relevant information from the images are still rare. This article proposes a method for counting cattle which combines a deep learning model for rough animal location, color space manipulation to increase contrast between animals and background, mathematical morphology to isolate the animals and infer the number of individuals in clustered groups, and image matching to take into account image overlap. Using Nelore and Canchim breeds as a case study, the proposed approach yields accuracies over 90% under a wide variety of conditions and backgrounds. 650 $aNeural networks 650 $aUnmanned aerial vehicles 650 $aGado Canchim 650 $aGado de Corte 650 $aGado Nelore 653 $aCanchim breed 653 $aConvolutional neural networks 653 $aDeep learning mode 653 $aMathematical morphology 653 $aNelore breed 653 $aRede neural convolucional 653 $aRedes neurais 653 $aVeículo aéreo não tripulado 700 1 $aKOENIGKAN, L. V. 700 1 $aSANTOS, P. M. 700 1 $aRIBEIRO, A. R. B. 773 $tSensors$gv. 20, n. 7, p. 1-14, Apr. 2020.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|