Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms

In modern agriculture, visual recognition systems based on deep learning are arising to allow autonomous machines to execute field operations in crops. However, for obtaining high performances, these methods need high amounts of data, which are usually scarce in agriculture. The main reason is that...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nikos Mylonas, Ioannis Malounas, Sofia Mouseti, Eleanna Vali, Borja Espejo-Garcia, Spyros Fountas
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Open-data Dataset Precision agriculture Deep learning Computer vision Robotics Agriculture (General) S1-972 Agricultural industries HD9000-9495
Acceso en línea:	https://doaj.org/article/538b7cb068d9449b9d4e0b673a6acaa6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:538b7cb068d9449b9d4e0b673a6acaa6
record_format	dspace
spelling	oai:doaj.org-article:538b7cb068d9449b9d4e0b673a6acaa62021-11-28T04:40:11ZEden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms2772-375510.1016/j.atech.2021.100028https://doaj.org/article/538b7cb068d9449b9d4e0b673a6acaa62022-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2772375521000289https://doaj.org/toc/2772-3755In modern agriculture, visual recognition systems based on deep learning are arising to allow autonomous machines to execute field operations in crops. However, for obtaining high performances, these methods need high amounts of data, which are usually scarce in agriculture. The main reason is that building an agricultural dataset covering exhaustively a specific problem is challenging, as visual characteristics of the symptoms may change, and there is a high dependency on environmental factors, such as temperature, humidity and light conditions. Therefore, an efficient methodology is necessary to consistently cover the entire workflow for creating an agricultural dataset, from the image acquisition to its online publication. This paper presents the Eden Library, a platform for contributing to this existing gap in open access crop/plant databases covering proximal and aerial images. The complete workflow on the design and deployment of the platform is also explained and discussed. This workflow is relevant because the provided datasets are thought to be maintained and enriched along the time, and they do not just remain as a static research output covering only specific species, growth stages, and conditions. The image annotations of plants and symptoms are provided, saving users from manually annotating images. Currently, the Eden Library covers 15 different crops, 9 weeds and 30 disorders (pests, diseases and nutrient deficiencies). Eden Library aspires to close this gap by providing a large and diversified image collection of plants, organized in a consistent manner, in order to boost further vision-based and AI-enabled field applications.Nikos MylonasIoannis MalounasSofia MousetiEleanna ValiBorja Espejo-GarciaSpyros FountasElsevierarticleOpen-dataDatasetPrecision agricultureDeep learningComputer visionRoboticsAgriculture (General)S1-972Agricultural industriesHD9000-9495ENSmart Agricultural Technology, Vol 2, Iss , Pp 100028- (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Open-data Dataset Precision agriculture Deep learning Computer vision Robotics Agriculture (General) S1-972 Agricultural industries HD9000-9495
spellingShingle	Open-data Dataset Precision agriculture Deep learning Computer vision Robotics Agriculture (General) S1-972 Agricultural industries HD9000-9495 Nikos Mylonas Ioannis Malounas Sofia Mouseti Eleanna Vali Borja Espejo-Garcia Spyros Fountas Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
description	In modern agriculture, visual recognition systems based on deep learning are arising to allow autonomous machines to execute field operations in crops. However, for obtaining high performances, these methods need high amounts of data, which are usually scarce in agriculture. The main reason is that building an agricultural dataset covering exhaustively a specific problem is challenging, as visual characteristics of the symptoms may change, and there is a high dependency on environmental factors, such as temperature, humidity and light conditions. Therefore, an efficient methodology is necessary to consistently cover the entire workflow for creating an agricultural dataset, from the image acquisition to its online publication. This paper presents the Eden Library, a platform for contributing to this existing gap in open access crop/plant databases covering proximal and aerial images. The complete workflow on the design and deployment of the platform is also explained and discussed. This workflow is relevant because the provided datasets are thought to be maintained and enriched along the time, and they do not just remain as a static research output covering only specific species, growth stages, and conditions. The image annotations of plants and symptoms are provided, saving users from manually annotating images. Currently, the Eden Library covers 15 different crops, 9 weeds and 30 disorders (pests, diseases and nutrient deficiencies). Eden Library aspires to close this gap by providing a large and diversified image collection of plants, organized in a consistent manner, in order to boost further vision-based and AI-enabled field applications.
format	article
author	Nikos Mylonas Ioannis Malounas Sofia Mouseti Eleanna Vali Borja Espejo-Garcia Spyros Fountas
author_facet	Nikos Mylonas Ioannis Malounas Sofia Mouseti Eleanna Vali Borja Espejo-Garcia Spyros Fountas
author_sort	Nikos Mylonas
title	Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
title_short	Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
title_full	Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
title_fullStr	Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
title_full_unstemmed	Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms
title_sort	eden library: a long-term database for storing agricultural multi-sensor datasets from uav and proximal platforms
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/538b7cb068d9449b9d4e0b673a6acaa6
work_keys_str_mv	AT nikosmylonas edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms AT ioannismalounas edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms AT sofiamouseti edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms AT eleannavali edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms AT borjaespejogarcia edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms AT spyrosfountas edenlibraryalongtermdatabaseforstoringagriculturalmultisensordatasetsfromuavandproximalplatforms
_version_	1718408257752530944

Eden Library: A long-term database for storing agricultural multi-sensor datasets from UAV and proximal platforms

Ejemplares similares