A methodology for detection and localization of fruits in apples orchards from aerial images.

Vista sencilla de ítem
dc.contributorTHIAGO TEIXEIRA SANTOS, CNPTIA; LUCIANO GEBLER, CNPUV.
dc.creatorSANTOS, T. T.
dc.creatorGEBLER, L.
dc.date2021-11-26T12:00:39Z
dc.date2021-11-26T12:00:39Z
dc.date2021-11-26
dc.date2021
dc.date.accessioned2026-07-07T04:16:39Z
dc.descriptionAbstract. 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.
dc.descriptionOrganizado por Ana Paula Lüdtke Ferreira. SBIAgro 2021.
dc.formatp. 1-9.
dc.identifierIn: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA, 13., 2021, Bagé. Anais [...]. Bagé: Unipampa, 2021.
dc.identifier978-65-00-34526-1
dc.identifier2177-9724
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1136667
dc.identifier.urihttp://hdl.handle.net/123456789/456217
dc.languageeng
dc.rightsopenAccess
dc.subjectRedes neurais
dc.subjectContagem automática de frutas
dc.subjectDetecção de maçãs
dc.subjectConvolutional neural networks
dc.subjectFruit detection
dc.subjectMaçã
dc.subjectNeural networks
dc.subjectApples
dc.titleA methodology for detection and localization of fruits in apples orchards from aerial images.
dc.typeArtigo em anais e proceedings

Archivos

Colecciones

Embrapa Agricultura Digital (CNPTIA)