Smart agriculture framework from imagery based on representation learning
Nowadays, with the increasing need for food due to the high population, there are needed new alternatives in agriculture that avoid yield losses, while augmenting food security. Smart agriculture arises as a solution that gathers technology and agronomics, including aerial imagery, digital surface m...
- Autores:
-
García Murillo, Daniel Guillermo
- Tipo de recurso:
- Fecha de publicación:
- 2019
- Institución:
- Universidad Nacional de Colombia
- Repositorio:
- Universidad Nacional de Colombia
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unal.edu.co:unal/76881
- Acceso en línea:
- https://repositorio.unal.edu.co/handle/unal/76881
http://bdigital.unal.edu.co/73815/
- Palabra clave:
- Kernel Representation
Centered Kernel Alignment
Smart Agriculture
Digital Surface Model
Mathematical Morphology
Feature Extraction
Feature Selection
Representaciones Kernel
Alineamiento de Kernels Centralizados
Agricultura Inteligente
Modelo Digital de Supercie
Morfología Matemática
Extracción de Características
- Rights
- openAccess
- License
- Atribución-NoComercial 4.0 Internacional
id |
UNACIONAL2_5094f46f357524307ec9d9d583b30d09 |
---|---|
oai_identifier_str |
oai:repositorio.unal.edu.co:unal/76881 |
network_acronym_str |
UNACIONAL2 |
network_name_str |
Universidad Nacional de Colombia |
repository_id_str |
|
dc.title.spa.fl_str_mv |
Smart agriculture framework from imagery based on representation learning |
title |
Smart agriculture framework from imagery based on representation learning |
spellingShingle |
Smart agriculture framework from imagery based on representation learning Kernel Representation Centered Kernel Alignment Smart Agriculture Digital Surface Model Mathematical Morphology Feature Extraction Feature Selection Representaciones Kernel Alineamiento de Kernels Centralizados Agricultura Inteligente Modelo Digital de Supercie Morfología Matemática Extracción de Características |
title_short |
Smart agriculture framework from imagery based on representation learning |
title_full |
Smart agriculture framework from imagery based on representation learning |
title_fullStr |
Smart agriculture framework from imagery based on representation learning |
title_full_unstemmed |
Smart agriculture framework from imagery based on representation learning |
title_sort |
Smart agriculture framework from imagery based on representation learning |
dc.creator.fl_str_mv |
García Murillo, Daniel Guillermo |
dc.contributor.advisor.spa.fl_str_mv |
Cárdenas Peña, David Augusto (Thesis advisor) |
dc.contributor.author.spa.fl_str_mv |
García Murillo, Daniel Guillermo |
dc.contributor.spa.fl_str_mv |
Castellanos Domínguez, César Germán |
dc.subject.proposal.spa.fl_str_mv |
Kernel Representation Centered Kernel Alignment Smart Agriculture Digital Surface Model Mathematical Morphology Feature Extraction Feature Selection Representaciones Kernel Alineamiento de Kernels Centralizados Agricultura Inteligente Modelo Digital de Supercie Morfología Matemática Extracción de Características |
topic |
Kernel Representation Centered Kernel Alignment Smart Agriculture Digital Surface Model Mathematical Morphology Feature Extraction Feature Selection Representaciones Kernel Alineamiento de Kernels Centralizados Agricultura Inteligente Modelo Digital de Supercie Morfología Matemática Extracción de Características |
description |
Nowadays, with the increasing need for food due to the high population, there are needed new alternatives in agriculture that avoid yield losses, while augmenting food security. Smart agriculture arises as a solution that gathers technology and agronomics, including aerial imagery, digital surface models, meteorological stations, and machine learning techniques, to improve agricultural management, improving traditional techniques as human interpretation. Nevertheless, we identify two main problems: First, the lack of information about tree inventory due to not accurate maps. Second, the absence of accurate weed management derived from inefficient weed vs crop discrimination. In this work, we propose a new morphological transformation to deal with not accurate digital surface models, improving tree identification, and thus, generating tree inventories. Furthermore, we introduce a sparse feature extraction approach that remarkably separates overlapped classes. Finally, we propose a feature selection algorithm that extracts relevant features from a matrix projection. As a result, this work uses a smart agriculture framework from imagery based on representation learning to improve tree identification and weed/crop discrimination |
publishDate |
2019 |
dc.date.issued.spa.fl_str_mv |
2019-08-03 |
dc.date.accessioned.spa.fl_str_mv |
2020-03-30T06:31:54Z |
dc.date.available.spa.fl_str_mv |
2020-03-30T06:31:54Z |
dc.type.spa.fl_str_mv |
Trabajo de grado - Maestría |
dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/masterThesis |
dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
dc.type.content.spa.fl_str_mv |
Text |
dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/TM |
status_str |
acceptedVersion |
dc.identifier.uri.none.fl_str_mv |
https://repositorio.unal.edu.co/handle/unal/76881 |
dc.identifier.eprints.spa.fl_str_mv |
http://bdigital.unal.edu.co/73815/ |
url |
https://repositorio.unal.edu.co/handle/unal/76881 http://bdigital.unal.edu.co/73815/ |
dc.language.iso.spa.fl_str_mv |
spa |
language |
spa |
dc.relation.ispartof.spa.fl_str_mv |
Universidad Nacional de Colombia Sede Manizales Facultad de Ingeniería y Arquitectura Departamento de Ingeniería Eléctrica, Electrónica y Computación Departamento de Ingeniería Eléctrica, Electrónica y Computación |
dc.relation.haspart.spa.fl_str_mv |
6 Tecnología (ciencias aplicadas) / Technology |
dc.relation.references.spa.fl_str_mv |
García Murillo, Daniel Guillermo (2019) Smart agriculture framework from imagery based on representation learning. Maestría thesis, Universidad Nacional de Colombia - Sede Manizales. |
dc.rights.spa.fl_str_mv |
Derechos reservados - Universidad Nacional de Colombia |
dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
dc.rights.license.spa.fl_str_mv |
Atribución-NoComercial 4.0 Internacional |
dc.rights.uri.spa.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0/ |
dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Atribución-NoComercial 4.0 Internacional Derechos reservados - Universidad Nacional de Colombia http://creativecommons.org/licenses/by-nc/4.0/ http://purl.org/coar/access_right/c_abf2 |
eu_rights_str_mv |
openAccess |
dc.format.mimetype.spa.fl_str_mv |
application/pdf |
institution |
Universidad Nacional de Colombia |
bitstream.url.fl_str_mv |
https://repositorio.unal.edu.co/bitstream/unal/76881/1/1053839441.2019.pdf https://repositorio.unal.edu.co/bitstream/unal/76881/2/1053839441.2019.pdf.jpg |
bitstream.checksum.fl_str_mv |
141d2c9c8abba41669434208d8d9ae38 c4284d1b76486f31a56e5e73a72945b7 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositorio Institucional Universidad Nacional de Colombia |
repository.mail.fl_str_mv |
repositorio_nal@unal.edu.co |
_version_ |
1814090011550679040 |
spelling |
Atribución-NoComercial 4.0 InternacionalDerechos reservados - Universidad Nacional de Colombiahttp://creativecommons.org/licenses/by-nc/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Castellanos Domínguez, César GermánCárdenas Peña, David Augusto (Thesis advisor)4d4899ac-0b9a-4de3-bafd-f5b1abb9df44García Murillo, Daniel Guillermo5bed5913-4632-4a74-a636-7a04bfde535d3002020-03-30T06:31:54Z2020-03-30T06:31:54Z2019-08-03https://repositorio.unal.edu.co/handle/unal/76881http://bdigital.unal.edu.co/73815/Nowadays, with the increasing need for food due to the high population, there are needed new alternatives in agriculture that avoid yield losses, while augmenting food security. Smart agriculture arises as a solution that gathers technology and agronomics, including aerial imagery, digital surface models, meteorological stations, and machine learning techniques, to improve agricultural management, improving traditional techniques as human interpretation. Nevertheless, we identify two main problems: First, the lack of information about tree inventory due to not accurate maps. Second, the absence of accurate weed management derived from inefficient weed vs crop discrimination. In this work, we propose a new morphological transformation to deal with not accurate digital surface models, improving tree identification, and thus, generating tree inventories. Furthermore, we introduce a sparse feature extraction approach that remarkably separates overlapped classes. Finally, we propose a feature selection algorithm that extracts relevant features from a matrix projection. As a result, this work uses a smart agriculture framework from imagery based on representation learning to improve tree identification and weed/crop discriminationHoy en día, con la creciente necesidad de alimentos debido a la alta población, son necesarias nuevas alternativas en la agricultura que eviten las pérdidas de rendimiento y al mismo tiempo que aumentan la seguridad alimentaria. La agricultura inteligente surge como una solución que reúne la tecnología y la agronomía, incluyendo imágenes aéreas, modelos digitales de superficie, estaciones meteorológicas y técnicas de aprendizaje de máquina, para mejorar el manejo agrícola, superando las técnicas tradicionales como la interpretación humana. Sin embargo, se identificaron dos problemas principales: Primero, la falta de información sobre el inventario de ´arboles debido a mapas no precisos. En segundo lugar, la ausencia de un manejo preciso de las malezas derivado de la ineficiente discriminación de malezas vs cultivos. En este trabajo, proponemos una nueva transformación morfológica para tratar con modelos digitales de superficie no precisos, mejorando la identificación de los ´árboles y, por lo tanto, generar inventarios de ´arboles. Además, se presenta un enfoque de extracción de características dispersas que separa notablemente las clases superpuestas. Finalmente, proponemos un algoritmo de selección de características que extrae características relevantes de una matriz de proyección. Como resultado, este trabajo utiliza un marco de agricultura inteligente a partir de imágenes basadas en el aprendizaje de representación para mejorar la identificación de ´árboles y la discriminación de malezas vs cultivosMaestríaapplication/pdfspaUniversidad Nacional de Colombia Sede Manizales Facultad de Ingeniería y Arquitectura Departamento de Ingeniería Eléctrica, Electrónica y ComputaciónDepartamento de Ingeniería Eléctrica, Electrónica y Computación6 Tecnología (ciencias aplicadas) / TechnologyGarcía Murillo, Daniel Guillermo (2019) Smart agriculture framework from imagery based on representation learning. Maestría thesis, Universidad Nacional de Colombia - Sede Manizales.Smart agriculture framework from imagery based on representation learningTrabajo de grado - Maestríainfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/acceptedVersionTexthttp://purl.org/redcol/resource_type/TMKernel RepresentationCentered Kernel AlignmentSmart AgricultureDigital Surface ModelMathematical MorphologyFeature ExtractionFeature SelectionRepresentaciones KernelAlineamiento de Kernels CentralizadosAgricultura InteligenteModelo Digital de SupercieMorfología MatemáticaExtracción de CaracterísticasORIGINAL1053839441.2019.pdfTesis de Maestría en Ingeniería - Automatización Industrialapplication/pdf162174299https://repositorio.unal.edu.co/bitstream/unal/76881/1/1053839441.2019.pdf141d2c9c8abba41669434208d8d9ae38MD51THUMBNAIL1053839441.2019.pdf.jpg1053839441.2019.pdf.jpgGenerated Thumbnailimage/jpeg4379https://repositorio.unal.edu.co/bitstream/unal/76881/2/1053839441.2019.pdf.jpgc4284d1b76486f31a56e5e73a72945b7MD52unal/76881oai:repositorio.unal.edu.co:unal/768812024-09-16 16:04:24.592Repositorio Institucional Universidad Nacional de Colombiarepositorio_nal@unal.edu.co |