Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
26/11/2021 |
Data da última atualização: |
13/12/2023 |
Tipo da produção científica: |
Artigo em Anais de Congresso |
Autoria: |
SANTOS, T. T.; GEBLER, L. |
Afiliação: |
THIAGO TEIXEIRA SANTOS, CNPTIA; LUCIANO GEBLER, CNPUV. |
Título: |
A methodology for detection and localization of fruits in apples orchards from aerial images. |
Ano de publicação: |
2021 |
Fonte/Imprenta: |
In: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA, 13., 2021, Bagé. Anais [...]. Bagé: Unipampa, 2021. |
Páginas: |
p. 1-9. |
ISBN: |
978-65-00-34526-1 |
ISSN: |
2177-9724 |
Idioma: |
Inglês |
Notas: |
Organizado por Ana Paula Lüdtke Ferreira. SBIAgro 2021. |
Conteúdo: |
Abstract. Computer vision methods based on convolutional neural networks (CNNs) have presented promising results on image-based fruit detection at ground-level for different crops. However, the integration of the detections found in different images, allowing accurate fruit counting and yield prediction, have received less attention. This work presents a methodology for automated fruit counting employing aerial-images. It includes algorithms based on multiple view geometry to perform fruits tracking, not just avoiding double counting but also locating the fruits in the 3-D space. Preliminary assessments show correlations above 0.8 between fruit counting and true yield for apples. The annotated dataset employed on CNN training is publicly available. |
Palavras-Chave: |
Contagem automática de frutas; Convolutional neural networks; Detecção de maçãs; Fruit detection; Redes neurais. |
Thesagro: |
Maçã. |
Thesaurus Nal: |
Apples; Neural networks. |
Categoria do assunto: |
-- |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/228160/1/PL-Methodology-detection-localization-SBIAgro-2021.pdf
|
Marc: |
LEADER 01630nam a2200265 a 4500 001 2136667 005 2023-12-13 008 2021 bl uuuu u00u1 u #d 020 $a978-65-00-34526-1 022 $a2177-9724 100 1 $aSANTOS, T. T. 245 $aA methodology for detection and localization of fruits in apples orchards from aerial images.$h[electronic resource] 260 $aIn: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA, 13., 2021, Bagé. Anais [...]. Bagé: Unipampa$c2021 300 $ap. 1-9. 500 $aOrganizado por Ana Paula Lüdtke Ferreira. SBIAgro 2021. 520 $aAbstract. Computer vision methods based on convolutional neural networks (CNNs) have presented promising results on image-based fruit detection at ground-level for different crops. However, the integration of the detections found in different images, allowing accurate fruit counting and yield prediction, have received less attention. This work presents a methodology for automated fruit counting employing aerial-images. It includes algorithms based on multiple view geometry to perform fruits tracking, not just avoiding double counting but also locating the fruits in the 3-D space. Preliminary assessments show correlations above 0.8 between fruit counting and true yield for apples. The annotated dataset employed on CNN training is publicly available. 650 $aApples 650 $aNeural networks 650 $aMaçã 653 $aContagem automática de frutas 653 $aConvolutional neural networks 653 $aDetecção de maçãs 653 $aFruit detection 653 $aRedes neurais 700 1 $aGEBLER, L.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |