Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística
Autor(a) principal: | |
---|---|
Data de Publicação: | 2010 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | LOCUS Repositório Institucional da UFV |
Texto Completo: | http://locus.ufv.br/handle/123456789/690 |
Resumo: | The objective of this study was to map weed percent coverage using techniques of digital image processing and geostatistics in row crops. Two experiments were performed. The first was conducted in a 0.8 hectare experimental area belonging to the Universidade Federal de Viçosa (UFV) in the city of Coimbra, MG, Brazil, whose area was irrigated with a central pivot system. The area was planted with common beans, Ouro Vermelho cultivar, where half of the area was crop in tillage system and the other half in no-tillage. The second experiment was conducted on a private property of approximately 1.2 hectares cultivated with sunflower, with no irrigation system, located in Aguilar de Bureba, Burgos province, Spain. In the first study, a machine vision system was built, with two digital cameras and a DGPS(Trimble Pathfinder Pro XRS) set up on the central pivot structure. The central pivot moved to sample the entire area of study. One camera acquired color images in the visible bands (RGB), and the other acquired images in the near infrared band (NIR). These cameras captured images simultaneously of the same scene. The scene coordinates were acquired by the DGPS, and it was assumed to be in the center of the common area of the two images. These images were acquired in a grid pattern.The images were processed for the percentage of weed cover estimation. Once it was acquired all the georeferenced weed percentage values, it was possible to construct maps using geostatistical techniques. The system performance was access for the two cameras and for the two tillage systems. The maps generated by using color images were more reliable than those using NIR images for weed infestation detection in both tillage systems since they presented a better contrast between plants and background. In the second experiment, the system used two different digital color cameras, with different image resolutions, and a GPS. All equipments were set on a tractor, simulating height of a central pivot. The two cameras captured color imagesof the same scene and at the same height, but with different spatial resolutions. It was again assumed that the GPS coordinates referred to the image center. Sample images of the area were acquired in a grid pattern at camera heights of 3 and 4 m, and at 37 and 46 days after planting (DAP). The images were processed for weeds infestation estimation for each position. Thus, maps for camera, height and date were built by the developed system. The higher resolution camera was presented better performance to map the percentage of weed coverage and identify variability of these plants in the area under study, at both heights and growth stages since it presented better contrast between plants and soil than the other camera. The maps at both stages of growth presented similarity for both tested heights and cameras. |
id |
UFV_05b00ff662dc1c6c1274b292764b1116 |
---|---|
oai_identifier_str |
oai:locus.ufv.br:123456789/690 |
network_acronym_str |
UFV |
network_name_str |
LOCUS Repositório Institucional da UFV |
repository_id_str |
2145 |
spelling |
Silva Júnior, Mário Cupertino dahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4718995E3Gil, Jaime GómezQueiroz, Daniel Marçal dehttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4783625P5Pinto, Francisco de Assis de Carvalhohttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4784515P9Monteiro, Paulo Marcos de Barroshttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4798498J6Khoury Junior, Joseph Kalilhttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4760449Z9Gracia, Luis Manuel Navashttp://lattes.cnpq.br/91256896118373072015-03-26T12:31:15Z2011-09-122015-03-26T12:31:15Z2010-06-30SILVA JÚNIOR, Mário Cupertino da. Mapping of weed cover using digital images and geostatistics. 2010. 176 f. Tese (Doutorado em Construções rurais e ambiência; Energia na agricultura; Mecanização agrícola; Processamento de produ) - Universidade Federal de Viçosa, Viçosa, 2010.http://locus.ufv.br/handle/123456789/690The objective of this study was to map weed percent coverage using techniques of digital image processing and geostatistics in row crops. Two experiments were performed. The first was conducted in a 0.8 hectare experimental area belonging to the Universidade Federal de Viçosa (UFV) in the city of Coimbra, MG, Brazil, whose area was irrigated with a central pivot system. The area was planted with common beans, Ouro Vermelho cultivar, where half of the area was crop in tillage system and the other half in no-tillage. The second experiment was conducted on a private property of approximately 1.2 hectares cultivated with sunflower, with no irrigation system, located in Aguilar de Bureba, Burgos province, Spain. In the first study, a machine vision system was built, with two digital cameras and a DGPS(Trimble Pathfinder Pro XRS) set up on the central pivot structure. The central pivot moved to sample the entire area of study. One camera acquired color images in the visible bands (RGB), and the other acquired images in the near infrared band (NIR). These cameras captured images simultaneously of the same scene. The scene coordinates were acquired by the DGPS, and it was assumed to be in the center of the common area of the two images. These images were acquired in a grid pattern.The images were processed for the percentage of weed cover estimation. Once it was acquired all the georeferenced weed percentage values, it was possible to construct maps using geostatistical techniques. The system performance was access for the two cameras and for the two tillage systems. The maps generated by using color images were more reliable than those using NIR images for weed infestation detection in both tillage systems since they presented a better contrast between plants and background. In the second experiment, the system used two different digital color cameras, with different image resolutions, and a GPS. All equipments were set on a tractor, simulating height of a central pivot. The two cameras captured color imagesof the same scene and at the same height, but with different spatial resolutions. It was again assumed that the GPS coordinates referred to the image center. Sample images of the area were acquired in a grid pattern at camera heights of 3 and 4 m, and at 37 and 46 days after planting (DAP). The images were processed for weeds infestation estimation for each position. Thus, maps for camera, height and date were built by the developed system. The higher resolution camera was presented better performance to map the percentage of weed coverage and identify variability of these plants in the area under study, at both heights and growth stages since it presented better contrast between plants and soil than the other camera. The maps at both stages of growth presented similarity for both tested heights and cameras.O objetivo deste trabalho foi mapear o percentual da cobertura de plantas daninhas utilizando técnicas de processamento de imagens digitais e de geoestatística em lavouras com cultivo em linha. Para obter este mapeamento foram realizados dois experimentos. O primeiro foi conduzido em uma área experimental de 0,8 hectares, pertencente à Universidade Federal de Viçosa (UFV) na cidade de Coimbra – MG, cuja área estava sob manejo de irrigação constituído por um pivô central. A cultura implantada foi feijão, cultivar ouro vermelho, sob os sistemas de plantio direto e convencional, cada um ocupando metade da área. O segundo experimento foi conduzido em uma área de propriedade particular de aproximadamente 1,2 hectares, cultivada com girassol, sem nenhum sistema de irrigação, localizada em Aguilar de Bureba na Província de Burgos, Espanha. No primeiro estudo construiu-se um sistema de visão artificial composto por duas câmeras digitais, acopladas a estrutura móvel do pivô central, e um DGPS (Trimble Pathfinder Pro XRS). Aproveitou-se o movimento de rotação do pivô para percorrer toda a área de estudo. Uma câmera adquiriu imagens coloridas, nas bandas do visível (RGB), e a outra adquiriu imagens na banda do infravermelho próximo (NIR). Estas câmeras capturavam as imagens simultaneamente e pertencentes à mesma cena. O DGPS capturava as coordenadas de uma posição e a esta foi assumida estar no centro da área comum das duas imagens. Estas imagens adquiridas representavam amostras da área, em uma malha regular de pontos. As imagens foram processadas para estimar a porcentagem da cobertura das plantas daninhas. De posse destes valores georreferenciados foi possível construir mapas usando técnicas de geoestatística. Os mapas gerados pelas imagens coloridas foram mais adequados, do que os das imagens NIR, para detectar a infestação de plantas daninhas, em ambos os sistemas de plantio, pois apresentaram melhor contraste entre plantas e o fundo da imagem. No segundo experimento o sistema utilizou duas câmeras digitais, com diferentes resoluções espaciais, e um GPS. Todos estes equipamentos foram acoplados em um trator, simulando a altura de um pivô central. As duas câmeras capturavam imagens coloridas da mesma cena e na mesma altura, mas com resoluções espaciais diferentes. Assumiu-se novamente que as coordenadas capturadas pelo GPS eram as do centro das imagens. As amostras da área pelas imagens foram adquiridas em uma malha regular de pontos, com as câmeras posicionadas a 3 e 4 m de altura, aos 37 e 46 dias após o plantio (DAP). As imagens foram processadas para estimativa da infestação de plantas daninhas para cada posição. Logo, os mapas referentes aos tipos de câmeras, alturas de posicionamento das câmeras e estádios de crescimento da cultura foram construídos pelo sistema desenvolvido. A câmera de maior resolução apresentou melhor desempenho para mapear a porcentagem da cobertura de plantas daninhas e identificar a variabilidade de infestação destas plantas na área de estudo, em ambas as alturas e estádios de crescimento da cultura avaliados, pois apresentaram melhor contraste entre plantas e solo do que às imagens da outra câmera. Os mapas nos dois estádios de crescimento apresentaram similaridade para ambas as alturas e câmeras testadas.Fundação de Amparo a Pesquisa do Estado de Minas Geraisapplication/pdfporUniversidade Federal de ViçosaDoutorado em Engenharia AgrícolaUFVBRConstruções rurais e ambiência; Energia na agricultura; Mecanização agrícola; Processamento de produPlantasSoloPlantsSoilCNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLAMapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatísticaMapping of weed cover using digital images and geostatisticsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/openAccessreponame:LOCUS Repositório Institucional da UFVinstname:Universidade Federal de Viçosa (UFV)instacron:UFVORIGINALtexto completo.pdfapplication/pdf3869585https://locus.ufv.br//bitstream/123456789/690/1/texto%20completo.pdf324aa5627cb9d17173f728fb768a7bc0MD51TEXTtexto completo.pdf.txttexto completo.pdf.txtExtracted texttext/plain227784https://locus.ufv.br//bitstream/123456789/690/2/texto%20completo.pdf.txt6575af79ca10f5804044014b85f9c8e2MD52THUMBNAILtexto completo.pdf.jpgtexto completo.pdf.jpgIM Thumbnailimage/jpeg3593https://locus.ufv.br//bitstream/123456789/690/3/texto%20completo.pdf.jpg6d50fe27cdab4c11c4799927281b09bcMD53123456789/6902016-04-06 23:10:06.987oai:locus.ufv.br:123456789/690Repositório InstitucionalPUBhttps://www.locus.ufv.br/oai/requestfabiojreis@ufv.bropendoar:21452016-04-07T02:10:06LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV)false |
dc.title.por.fl_str_mv |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
dc.title.alternative.eng.fl_str_mv |
Mapping of weed cover using digital images and geostatistics |
title |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
spellingShingle |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística Silva Júnior, Mário Cupertino da Plantas Solo Plants Soil CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
title_short |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
title_full |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
title_fullStr |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
title_full_unstemmed |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
title_sort |
Mapeamento da cobertura de plantas daninhas utilizando imagens digitais e geoestatística |
author |
Silva Júnior, Mário Cupertino da |
author_facet |
Silva Júnior, Mário Cupertino da |
author_role |
author |
dc.contributor.authorLattes.por.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4718995E3 |
dc.contributor.author.fl_str_mv |
Silva Júnior, Mário Cupertino da |
dc.contributor.advisor-co1.fl_str_mv |
Gil, Jaime Gómez |
dc.contributor.advisor-co2.fl_str_mv |
Queiroz, Daniel Marçal de |
dc.contributor.advisor-co2Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4783625P5 |
dc.contributor.advisor1.fl_str_mv |
Pinto, Francisco de Assis de Carvalho |
dc.contributor.advisor1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4784515P9 |
dc.contributor.referee1.fl_str_mv |
Monteiro, Paulo Marcos de Barros |
dc.contributor.referee1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4798498J6 |
dc.contributor.referee2.fl_str_mv |
Khoury Junior, Joseph Kalil |
dc.contributor.referee2Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4760449Z9 |
dc.contributor.referee3.fl_str_mv |
Gracia, Luis Manuel Navas |
dc.contributor.referee3Lattes.fl_str_mv |
http://lattes.cnpq.br/9125689611837307 |
contributor_str_mv |
Gil, Jaime Gómez Queiroz, Daniel Marçal de Pinto, Francisco de Assis de Carvalho Monteiro, Paulo Marcos de Barros Khoury Junior, Joseph Kalil Gracia, Luis Manuel Navas |
dc.subject.por.fl_str_mv |
Plantas Solo |
topic |
Plantas Solo Plants Soil CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
dc.subject.eng.fl_str_mv |
Plants Soil |
dc.subject.cnpq.fl_str_mv |
CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
description |
The objective of this study was to map weed percent coverage using techniques of digital image processing and geostatistics in row crops. Two experiments were performed. The first was conducted in a 0.8 hectare experimental area belonging to the Universidade Federal de Viçosa (UFV) in the city of Coimbra, MG, Brazil, whose area was irrigated with a central pivot system. The area was planted with common beans, Ouro Vermelho cultivar, where half of the area was crop in tillage system and the other half in no-tillage. The second experiment was conducted on a private property of approximately 1.2 hectares cultivated with sunflower, with no irrigation system, located in Aguilar de Bureba, Burgos province, Spain. In the first study, a machine vision system was built, with two digital cameras and a DGPS(Trimble Pathfinder Pro XRS) set up on the central pivot structure. The central pivot moved to sample the entire area of study. One camera acquired color images in the visible bands (RGB), and the other acquired images in the near infrared band (NIR). These cameras captured images simultaneously of the same scene. The scene coordinates were acquired by the DGPS, and it was assumed to be in the center of the common area of the two images. These images were acquired in a grid pattern.The images were processed for the percentage of weed cover estimation. Once it was acquired all the georeferenced weed percentage values, it was possible to construct maps using geostatistical techniques. The system performance was access for the two cameras and for the two tillage systems. The maps generated by using color images were more reliable than those using NIR images for weed infestation detection in both tillage systems since they presented a better contrast between plants and background. In the second experiment, the system used two different digital color cameras, with different image resolutions, and a GPS. All equipments were set on a tractor, simulating height of a central pivot. The two cameras captured color imagesof the same scene and at the same height, but with different spatial resolutions. It was again assumed that the GPS coordinates referred to the image center. Sample images of the area were acquired in a grid pattern at camera heights of 3 and 4 m, and at 37 and 46 days after planting (DAP). The images were processed for weeds infestation estimation for each position. Thus, maps for camera, height and date were built by the developed system. The higher resolution camera was presented better performance to map the percentage of weed coverage and identify variability of these plants in the area under study, at both heights and growth stages since it presented better contrast between plants and soil than the other camera. The maps at both stages of growth presented similarity for both tested heights and cameras. |
publishDate |
2010 |
dc.date.issued.fl_str_mv |
2010-06-30 |
dc.date.available.fl_str_mv |
2011-09-12 2015-03-26T12:31:15Z |
dc.date.accessioned.fl_str_mv |
2015-03-26T12:31:15Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
SILVA JÚNIOR, Mário Cupertino da. Mapping of weed cover using digital images and geostatistics. 2010. 176 f. Tese (Doutorado em Construções rurais e ambiência; Energia na agricultura; Mecanização agrícola; Processamento de produ) - Universidade Federal de Viçosa, Viçosa, 2010. |
dc.identifier.uri.fl_str_mv |
http://locus.ufv.br/handle/123456789/690 |
identifier_str_mv |
SILVA JÚNIOR, Mário Cupertino da. Mapping of weed cover using digital images and geostatistics. 2010. 176 f. Tese (Doutorado em Construções rurais e ambiência; Energia na agricultura; Mecanização agrícola; Processamento de produ) - Universidade Federal de Viçosa, Viçosa, 2010. |
url |
http://locus.ufv.br/handle/123456789/690 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Viçosa |
dc.publisher.program.fl_str_mv |
Doutorado em Engenharia Agrícola |
dc.publisher.initials.fl_str_mv |
UFV |
dc.publisher.country.fl_str_mv |
BR |
dc.publisher.department.fl_str_mv |
Construções rurais e ambiência; Energia na agricultura; Mecanização agrícola; Processamento de produ |
publisher.none.fl_str_mv |
Universidade Federal de Viçosa |
dc.source.none.fl_str_mv |
reponame:LOCUS Repositório Institucional da UFV instname:Universidade Federal de Viçosa (UFV) instacron:UFV |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
UFV |
institution |
UFV |
reponame_str |
LOCUS Repositório Institucional da UFV |
collection |
LOCUS Repositório Institucional da UFV |
bitstream.url.fl_str_mv |
https://locus.ufv.br//bitstream/123456789/690/1/texto%20completo.pdf https://locus.ufv.br//bitstream/123456789/690/2/texto%20completo.pdf.txt https://locus.ufv.br//bitstream/123456789/690/3/texto%20completo.pdf.jpg |
bitstream.checksum.fl_str_mv |
324aa5627cb9d17173f728fb768a7bc0 6575af79ca10f5804044014b85f9c8e2 6d50fe27cdab4c11c4799927281b09bc |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
fabiojreis@ufv.br |
_version_ |
1801212865452965888 |