| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Agricultura Digital; Embrapa Pecuária Sudeste. |
|
Data corrente: |
10/12/2019 |
|
Data da última atualização: |
07/11/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
BARBEDO, J. G. A.; KOENIGKAN, L. V.; SANTOS, T. T.; SANTOS, P. M. |
|
Afiliação: |
JAYME GARCIA ARNAL BARBEDO, CNPTIA; LUCIANO VIEIRA KOENIGKAN, CNPTIA; THIAGO TEIXEIRA SANTOS, CNPTIA; PATRICIA MENEZES SANTOS, CPPSE. |
|
Título: |
A study on the detection of cattle in UAV images using deep learning. |
|
Ano de publicação: |
2019 |
|
Fonte/Imprenta: |
Sensors, v. 19, n. 24, 5436, Dec. 2019. |
|
Páginas: |
14 p. |
|
DOI: |
10.3390/s19245436 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Abstract: Unmanned aerial vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and convolutional neural networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: (1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (Bos taurus indicus); (2) to determine the ideal ground sample distance (GSD) for animal detection; (3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1853 images containing 8629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures 3 spacial resolutions 2 datasets 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring. MenosAbstract: Unmanned aerial vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and convolutional neural networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: (1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (Bos taurus indicus); (2) to determine the ideal ground sample distance (GSD) for animal detection; (3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1853 images containing 8629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures 3 spacial resolutions 2 datasets 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN arch... Mostrar Tudo |
|
Palavras-Chave: |
Aprendizado profundo; Canchim breed; Convolutional neural networks; Deep learning; Drone; Nelore breed; Redes neurais; Veículo aéreo não tripulado. |
|
Thesagro: |
Gado Canchim; Gado de Corte; Gado Nelore. |
|
Thesaurus Nal: |
Cattle; Unmanned aerial vehicles. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/206564/1/AP-sensors-UAV.pdf
|
|
Marc: |
LEADER 02605naa a2200337 a 4500
001 2116449
005 2023-11-07
008 2019 bl uuuu u00u1 u #d
024 7 $a10.3390/s19245436$2DOI
100 1 $aBARBEDO, J. G. A.
245 $aA study on the detection of cattle in UAV images using deep learning.$h[electronic resource]
260 $c2019
300 $a14 p.
520 $aAbstract: Unmanned aerial vehicles (UAVs) are being increasingly viewed as valuable tools to aid the management of farms. This kind of technology can be particularly useful in the context of extensive cattle farming, as production areas tend to be expansive and animals tend to be more loosely monitored. With the advent of deep learning, and convolutional neural networks (CNNs) in particular, extracting relevant information from aerial images has become more effective. Despite the technological advancements in drone, imaging and machine learning technologies, the application of UAVs for cattle monitoring is far from being thoroughly studied, with many research gaps still remaining. In this context, the objectives of this study were threefold: (1) to determine the highest possible accuracy that could be achieved in the detection of animals of the Canchim breed, which is visually similar to the Nelore breed (Bos taurus indicus); (2) to determine the ideal ground sample distance (GSD) for animal detection; (3) to determine the most accurate CNN architecture for this specific problem. The experiments involved 1853 images containing 8629 samples of animals, and 15 different CNN architectures were tested. A total of 900 models were trained (15 CNN architectures 3 spacial resolutions 2 datasets 10-fold cross validation), allowing for a deep analysis of the several aspects that impact the detection of cattle using aerial images captured using UAVs. Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring.
650 $aCattle
650 $aUnmanned aerial vehicles
650 $aGado Canchim
650 $aGado de Corte
650 $aGado Nelore
653 $aAprendizado profundo
653 $aCanchim breed
653 $aConvolutional neural networks
653 $aDeep learning
653 $aDrone
653 $aNelore breed
653 $aRedes neurais
653 $aVeículo aéreo não tripulado
700 1 $aKOENIGKAN, L. V.
700 1 $aSANTOS, T. T.
700 1 $aSANTOS, P. M.
773 $tSensors$gv. 19, n. 24, 5436, Dec. 2019.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 69 | |
| Registros recuperados : 69 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
