Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFU |
Texto Completo: | https://repositorio.ufu.br/handle/123456789/31012 http://doi.org/10.14393/ufu.di.2020.736 |
Resumo: | In recent years, UAVs (Unmanned Aerial Vehicles) have become increasingly popular in the agricultural sector, promoting and enabling the application of aerial image monitoring in both scientific and business contexts. Images captured by UAVs are fundamental for precision farming practices, as they allow activities that deal with low and medium altitude images. After the effective sowing, the scenario of the planted area may change drastically over time due to the appearance of erosion, gaps, death and drying of part of the crop, animal interventions, etc. Thus, the process of detecting the crop rows is strongly important for planning the harvest, estimating the use of inputs, control of costs of production, plant stand counts, early correction of sowing failures, more-efficient watering, etc. In addition, the geolocation information of the detected lines allows the use of autonomous machinery and a better application of inputs, reducing financial costs and the aggression to the environment. In this work we address the problem of detection and segmentation of sugarcane crop lines using UAV imagery. First, we experimented an approach based on \ac{GA} associated with Otsu method to produce binarized images. Then, due to some reasons including the recent relevance of Semantic Segmentation in the literature, its levels of abstraction, and the non-feasible results of Otsu associated with \ac{GA}, we proposed a new approach based on \ac{SSN} divided in two steps. First, we use a Convolutional Neural Network (CNN) to automatically segment the images, classifying their regions as crop lines or as non-planted soil. Then, we use the Radon transform to reconstruct and improve the already segmented lines, making them more uniform or grouping fragments of lines and loose plants belonging to the same planting line. We compare our results with segmentation performed manually by experts and the results demonstrate the efficiency and feasibility of our approach to the proposed task. |
id |
UFU_9f0a1cea0924472e42ff2f9ba6b359d7 |
---|---|
oai_identifier_str |
oai:repositorio.ufu.br:123456789/31012 |
network_acronym_str |
UFU |
network_name_str |
Repositório Institucional da UFU |
repository_id_str |
|
spelling |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon TransformDetecção de linha de plantio de cana de açúcar a partir de imagens de VANT usando Segmentação Semântica e Transformada de RadonCrop-rowSugarcaneSegmentationCNNUAVRadon TransformLinhas de PlantioCana-de-açúcarSegmentaçãoVANTTransformada de RadonComputaçãoCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOComputaçãoIn recent years, UAVs (Unmanned Aerial Vehicles) have become increasingly popular in the agricultural sector, promoting and enabling the application of aerial image monitoring in both scientific and business contexts. Images captured by UAVs are fundamental for precision farming practices, as they allow activities that deal with low and medium altitude images. After the effective sowing, the scenario of the planted area may change drastically over time due to the appearance of erosion, gaps, death and drying of part of the crop, animal interventions, etc. Thus, the process of detecting the crop rows is strongly important for planning the harvest, estimating the use of inputs, control of costs of production, plant stand counts, early correction of sowing failures, more-efficient watering, etc. In addition, the geolocation information of the detected lines allows the use of autonomous machinery and a better application of inputs, reducing financial costs and the aggression to the environment. In this work we address the problem of detection and segmentation of sugarcane crop lines using UAV imagery. First, we experimented an approach based on \ac{GA} associated with Otsu method to produce binarized images. Then, due to some reasons including the recent relevance of Semantic Segmentation in the literature, its levels of abstraction, and the non-feasible results of Otsu associated with \ac{GA}, we proposed a new approach based on \ac{SSN} divided in two steps. First, we use a Convolutional Neural Network (CNN) to automatically segment the images, classifying their regions as crop lines or as non-planted soil. Then, we use the Radon transform to reconstruct and improve the already segmented lines, making them more uniform or grouping fragments of lines and loose plants belonging to the same planting line. We compare our results with segmentation performed manually by experts and the results demonstrate the efficiency and feasibility of our approach to the proposed task.Dissertação (Mestrado)Nos últimos anos, os VANTs (Veículos Aéreos Não Tripulados) têm se tornado cada vez mais populares no setor agrícola, promovendo e possibilitando o monitoramento de imagens aéreas tanto no contexto científico, quanto no de negócios. Imagens capturadas por VANTs são fundamentais para práticas de agricultura de precisão, pois permitem a realização de atividades que lidam com imagens de baixa ou média altitude. O cenário da área plantada pode mudar drasticamente ao longo do tempo devido ao aparecimento de erosões, falhas de plantio, morte e ressecamento de parte da cultura, intervenções de animais, etc. Assim, o processo de detecção das linhas de plantio é de grande importância para o planejamento da colheita, controle de custos de produção, contagem de plantas, correção de falhas de semeadura, irrigação eficiente, entre outros. Além disso, a informação de geolocalização das linhas detectadas permite o uso de maquinários autônomos e um melhor planejamento de aplicação de insumos, reduzindo custos e a agressão ao meio ambiente. Neste trabalho, abordamos o problema de segmentação e detecção de linhas de plantio de cana-de-açúcar em imagens de VANTs. Primeiro, experimentamos uma abordagem baseada em Algoritmo Genético (AG) e Otsu para produzir imagens binarizadas. Posteriormente, devido a alguns motivos, incluindo a relevância recente da Segmentação Semântica, seus níveis de abstração e os resultados inviáveis obtidos com AG, estudamos e propusemos uma nova abordagem baseada em \ac{SSN} em duas etapas. Primeiro, usamos uma \ac{SSN} para segmentar as imagens, classificando suas regiões como linhas de plantio ou como solo não plantado. Em seguida, utilizamos a transformada de Radon para reconstruir e melhorar as linhas já segmentadas, tornando-as mais uniformes ou agrupando fragmentos de linhas e plantas soltas. Comparamos nossos resultados com segmentações feitas manualmente por especialistas e os resultados demonstram a eficiência e a viabilidade de nossa abordagem para a tarefa proposta.Universidade Federal de UberlândiaBrasilPrograma de Pós-graduação em Ciência da ComputaçãoEscarpinati, Mauricio Cunhahttp://lattes.cnpq.br/5939941255055989Backes, André Ricardohttp://lattes.cnpq.br/8590140337571249Nascimento, Marcelo Zanchetta dohttp://lattes.cnpq.br/5800175874658088Pistori, Hemersonhttp://lattes.cnpq.br/8684549377565696Silva, Renato Rodrigues da2021-01-12T20:47:31Z2021-01-12T20:47:31Z2020-12-07info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfSILVA, Renato Rodrigues da. Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform. 2020. 87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Uberlândia, Uberlândia, 2020. DOI http://doi.org/10.14393/ufu.di.2020.736.https://repositorio.ufu.br/handle/123456789/31012http://doi.org/10.14393/ufu.di.2020.736enghttp://creativecommons.org/licenses/by-nc-nd/3.0/us/info:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFUinstname:Universidade Federal de Uberlândia (UFU)instacron:UFU2021-01-13T06:18:23Zoai:repositorio.ufu.br:123456789/31012Repositório InstitucionalONGhttp://repositorio.ufu.br/oai/requestdiinf@dirbi.ufu.bropendoar:2021-01-13T06:18:23Repositório Institucional da UFU - Universidade Federal de Uberlândia (UFU)false |
dc.title.none.fl_str_mv |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform Detecção de linha de plantio de cana de açúcar a partir de imagens de VANT usando Segmentação Semântica e Transformada de Radon |
title |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
spellingShingle |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform Silva, Renato Rodrigues da Crop-row Sugarcane Segmentation CNN UAV Radon Transform Linhas de Plantio Cana-de-açúcar Segmentação VANT Transformada de Radon Computação CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Computação |
title_short |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
title_full |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
title_fullStr |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
title_full_unstemmed |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
title_sort |
Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform |
author |
Silva, Renato Rodrigues da |
author_facet |
Silva, Renato Rodrigues da |
author_role |
author |
dc.contributor.none.fl_str_mv |
Escarpinati, Mauricio Cunha http://lattes.cnpq.br/5939941255055989 Backes, André Ricardo http://lattes.cnpq.br/8590140337571249 Nascimento, Marcelo Zanchetta do http://lattes.cnpq.br/5800175874658088 Pistori, Hemerson http://lattes.cnpq.br/8684549377565696 |
dc.contributor.author.fl_str_mv |
Silva, Renato Rodrigues da |
dc.subject.por.fl_str_mv |
Crop-row Sugarcane Segmentation CNN UAV Radon Transform Linhas de Plantio Cana-de-açúcar Segmentação VANT Transformada de Radon Computação CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Computação |
topic |
Crop-row Sugarcane Segmentation CNN UAV Radon Transform Linhas de Plantio Cana-de-açúcar Segmentação VANT Transformada de Radon Computação CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Computação |
description |
In recent years, UAVs (Unmanned Aerial Vehicles) have become increasingly popular in the agricultural sector, promoting and enabling the application of aerial image monitoring in both scientific and business contexts. Images captured by UAVs are fundamental for precision farming practices, as they allow activities that deal with low and medium altitude images. After the effective sowing, the scenario of the planted area may change drastically over time due to the appearance of erosion, gaps, death and drying of part of the crop, animal interventions, etc. Thus, the process of detecting the crop rows is strongly important for planning the harvest, estimating the use of inputs, control of costs of production, plant stand counts, early correction of sowing failures, more-efficient watering, etc. In addition, the geolocation information of the detected lines allows the use of autonomous machinery and a better application of inputs, reducing financial costs and the aggression to the environment. In this work we address the problem of detection and segmentation of sugarcane crop lines using UAV imagery. First, we experimented an approach based on \ac{GA} associated with Otsu method to produce binarized images. Then, due to some reasons including the recent relevance of Semantic Segmentation in the literature, its levels of abstraction, and the non-feasible results of Otsu associated with \ac{GA}, we proposed a new approach based on \ac{SSN} divided in two steps. First, we use a Convolutional Neural Network (CNN) to automatically segment the images, classifying their regions as crop lines or as non-planted soil. Then, we use the Radon transform to reconstruct and improve the already segmented lines, making them more uniform or grouping fragments of lines and loose plants belonging to the same planting line. We compare our results with segmentation performed manually by experts and the results demonstrate the efficiency and feasibility of our approach to the proposed task. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-07 2021-01-12T20:47:31Z 2021-01-12T20:47:31Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
SILVA, Renato Rodrigues da. Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform. 2020. 87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Uberlândia, Uberlândia, 2020. DOI http://doi.org/10.14393/ufu.di.2020.736. https://repositorio.ufu.br/handle/123456789/31012 http://doi.org/10.14393/ufu.di.2020.736 |
identifier_str_mv |
SILVA, Renato Rodrigues da. Detection of Sugarcane Crop Rows From UAV Images Using Semantic Segmentation and Radon Transform. 2020. 87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Uberlândia, Uberlândia, 2020. DOI http://doi.org/10.14393/ufu.di.2020.736. |
url |
https://repositorio.ufu.br/handle/123456789/31012 http://doi.org/10.14393/ufu.di.2020.736 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/us/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/us/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Uberlândia Brasil Programa de Pós-graduação em Ciência da Computação |
publisher.none.fl_str_mv |
Universidade Federal de Uberlândia Brasil Programa de Pós-graduação em Ciência da Computação |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFU instname:Universidade Federal de Uberlândia (UFU) instacron:UFU |
instname_str |
Universidade Federal de Uberlândia (UFU) |
instacron_str |
UFU |
institution |
UFU |
reponame_str |
Repositório Institucional da UFU |
collection |
Repositório Institucional da UFU |
repository.name.fl_str_mv |
Repositório Institucional da UFU - Universidade Federal de Uberlândia (UFU) |
repository.mail.fl_str_mv |
diinf@dirbi.ufu.br |
_version_ |
1805569611080400896 |