Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.5935/1806-6690.20200102 http://hdl.handle.net/11449/207272 |
Resumo: | Digital agriculture contributes to agricultural efficiency through the use of such tools as computer vision, robotics, and precision agriculture. In this study, the objective was to develop a system capable of classifying images through the recognition of pre-established patterns. For this purpose, a geographically distributed system was created, based on the Raspberry Pi 3B+ computer, which captures images in the field and stores them in a database, where they are available to receive a pre-classification by a supervisor. Subsequently, classifiers are generated, evaluated, and sent to the remote device to conduct a classification in real time. For an evaluation of the system, 23 classes were defined and grouped into 3 superclasses, 36,979 images were captured, and 1,579 pre-classifications were conducted, which allowed the classification tests to be carried out by means of a cross-validation by randomly dividing into the equivalent number of classes. These tests revealed that the accuracy delivered by each classifier is different and directly proportional to the quantity and balance of the samples, with a variation of 11% to 79%, with 26 and 2,200 samples considered, respectively. The response time of the system was evaluated during 1,585 periods and was maintained within approximately 0.20 s, and under controlled speed of the vehicle, can be used for the dispersion of inputs in real time. |
id |
UNSP_2385e062852015d9dd568befe0684962 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/207272 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane cropsComputer VisionDigital AgricultureMachine LearningOpen sourceRaspberry PiDigital agriculture contributes to agricultural efficiency through the use of such tools as computer vision, robotics, and precision agriculture. In this study, the objective was to develop a system capable of classifying images through the recognition of pre-established patterns. For this purpose, a geographically distributed system was created, based on the Raspberry Pi 3B+ computer, which captures images in the field and stores them in a database, where they are available to receive a pre-classification by a supervisor. Subsequently, classifiers are generated, evaluated, and sent to the remote device to conduct a classification in real time. For an evaluation of the system, 23 classes were defined and grouped into 3 superclasses, 36,979 images were captured, and 1,579 pre-classifications were conducted, which allowed the classification tests to be carried out by means of a cross-validation by randomly dividing into the equivalent number of classes. These tests revealed that the accuracy delivered by each classifier is different and directly proportional to the quantity and balance of the samples, with a variation of 11% to 79%, with 26 and 2,200 samples considered, respectively. The response time of the system was evaluated during 1,585 periods and was maintained within approximately 0.20 s, and under controlled speed of the vehicle, can be used for the dispersion of inputs in real time.Instituto Federal de Educação Ciência e Tecnologia de São Paulo/IFSP, Avenida C-Um, 250, Residencial Ide Daher Barretos-SPDepartamento de Engenharia e Ciências Exatas Faculdade de Ciências Agrárias e Veterinárias/FCAV Universidade Estadual Paulista/UNESPDepartamento de Engenharia e Ciências Exatas Faculdade de Ciências Agrárias e Veterinárias/FCAV Universidade Estadual Paulista/UNESPCiência e Tecnologia de São Paulo/IFSPUniversidade Estadual Paulista (Unesp)Cardoso, José Ricardo FerreiraFurlani, Carlos Eduardo Angeli [UNESP]Turco, José Eduardo Pitelli [UNESP]Zerbato, Cristiano [UNESP]Carneiro, Franciele Morlin [UNESP]de Lima Estevam, Francisca Nivanda [UNESP]2021-06-25T10:52:18Z2021-06-25T10:52:18Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article5-15http://dx.doi.org/10.5935/1806-6690.20200102Revista Ciencia Agronomica, v. 51, n. 5, p. 5-15, 2020.1806-66900045-6888http://hdl.handle.net/11449/20727210.5935/1806-6690.202001022-s2.0-85100777151Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRevista Ciencia Agronomicainfo:eu-repo/semantics/openAccess2021-10-23T16:43:32Zoai:repositorio.unesp.br:11449/207272Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T16:43:32Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
title |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
spellingShingle |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops Cardoso, José Ricardo Ferreira Computer Vision Digital Agriculture Machine Learning Open source Raspberry Pi |
title_short |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
title_full |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
title_fullStr |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
title_full_unstemmed |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
title_sort |
Development of a robotic structure for acquisition and classification of images (ERACI) in sugarcane crops |
author |
Cardoso, José Ricardo Ferreira |
author_facet |
Cardoso, José Ricardo Ferreira Furlani, Carlos Eduardo Angeli [UNESP] Turco, José Eduardo Pitelli [UNESP] Zerbato, Cristiano [UNESP] Carneiro, Franciele Morlin [UNESP] de Lima Estevam, Francisca Nivanda [UNESP] |
author_role |
author |
author2 |
Furlani, Carlos Eduardo Angeli [UNESP] Turco, José Eduardo Pitelli [UNESP] Zerbato, Cristiano [UNESP] Carneiro, Franciele Morlin [UNESP] de Lima Estevam, Francisca Nivanda [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Ciência e Tecnologia de São Paulo/IFSP Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Cardoso, José Ricardo Ferreira Furlani, Carlos Eduardo Angeli [UNESP] Turco, José Eduardo Pitelli [UNESP] Zerbato, Cristiano [UNESP] Carneiro, Franciele Morlin [UNESP] de Lima Estevam, Francisca Nivanda [UNESP] |
dc.subject.por.fl_str_mv |
Computer Vision Digital Agriculture Machine Learning Open source Raspberry Pi |
topic |
Computer Vision Digital Agriculture Machine Learning Open source Raspberry Pi |
description |
Digital agriculture contributes to agricultural efficiency through the use of such tools as computer vision, robotics, and precision agriculture. In this study, the objective was to develop a system capable of classifying images through the recognition of pre-established patterns. For this purpose, a geographically distributed system was created, based on the Raspberry Pi 3B+ computer, which captures images in the field and stores them in a database, where they are available to receive a pre-classification by a supervisor. Subsequently, classifiers are generated, evaluated, and sent to the remote device to conduct a classification in real time. For an evaluation of the system, 23 classes were defined and grouped into 3 superclasses, 36,979 images were captured, and 1,579 pre-classifications were conducted, which allowed the classification tests to be carried out by means of a cross-validation by randomly dividing into the equivalent number of classes. These tests revealed that the accuracy delivered by each classifier is different and directly proportional to the quantity and balance of the samples, with a variation of 11% to 79%, with 26 and 2,200 samples considered, respectively. The response time of the system was evaluated during 1,585 periods and was maintained within approximately 0.20 s, and under controlled speed of the vehicle, can be used for the dispersion of inputs in real time. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2021-06-25T10:52:18Z 2021-06-25T10:52:18Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.5935/1806-6690.20200102 Revista Ciencia Agronomica, v. 51, n. 5, p. 5-15, 2020. 1806-6690 0045-6888 http://hdl.handle.net/11449/207272 10.5935/1806-6690.20200102 2-s2.0-85100777151 |
url |
http://dx.doi.org/10.5935/1806-6690.20200102 http://hdl.handle.net/11449/207272 |
identifier_str_mv |
Revista Ciencia Agronomica, v. 51, n. 5, p. 5-15, 2020. 1806-6690 0045-6888 10.5935/1806-6690.20200102 2-s2.0-85100777151 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Revista Ciencia Agronomica |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
5-15 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799965744719462400 |