23 results on '"Jiménez-Brenes, Francisco M."'
Search Results
2. Quantification of dwarfing effect of different rootstocks in ‘Picual’ olive cultivar using UAV-photogrammetry
- Author
-
Torres-Sánchez, Jorge, de la Rosa, Raúl, León, Lorenzo, Jiménez-Brenes, Francisco M., Kharrat, Amal, and López-Granados, Francisca
- Published
- 2022
- Full Text
- View/download PDF
3. Exploring UAV-imagery to support genotype selection in olive breeding programs
- Author
-
Rallo, Pilar, de Castro, Ana I., López-Granados, Francisca, Morales-Sillero, Ana, Torres-Sánchez, Jorge, Jiménez, María Rocío, Jiménez-Brenes, Francisco M., Casanova, Laura, and Suárez, María Paz
- Published
- 2020
- Full Text
- View/download PDF
4. Mapping the 3D structure of almond trees using UAV acquired photogrammetric point clouds and object-based image analysis
- Author
-
Torres-Sánchez, Jorge, de Castro, Ana I., Peña, José M., Jiménez-Brenes, Francisco M., Arquero, Octavio, Lovera, María, and López-Granados, Francisca
- Published
- 2018
- Full Text
- View/download PDF
5. An efficient RGB-UAV-based platform for field almond tree phenotyping: 3-D architecture and flowering traits
- Author
-
López-Granados, Francisca, Torres-Sánchez, Jorge, Jiménez-Brenes, Francisco M., Arquero, Octavio, Lovera, María, and de Castro, Ana I.
- Published
- 2019
- Full Text
- View/download PDF
6. Quantification of dwarfing effect of different rootstocks in ‘Picual’ olive cultivar using UAV-photogrammetry
- Author
-
Torres-Sánchez, Jorge, primary, de la Rosa, Raúl, additional, León, Lorenzo, additional, Jiménez-Brenes, Francisco M., additional, Kharrat, Amal, additional, and López-Granados, Francisca, additional
- Published
- 2021
- Full Text
- View/download PDF
7. Early Detection of Broad-Leaved and Grass Weeds in Wide Row Crops Using Artificial Neural Networks and UAV Imagery
- Author
-
Torres-Sánchez, Jorge, primary, Mesas-Carrascosa, Francisco Javier, additional, Jiménez-Brenes, Francisco M., additional, de Castro, Ana I., additional, and López-Granados, Francisca, additional
- Published
- 2021
- Full Text
- View/download PDF
8. Monitoring Vineyard Canopy Management Operations Using UAV-Acquired Photogrammetric Point Clouds
- Author
-
López-Granados, Francisca, primary, Torres-Sánchez, Jorge, additional, Jiménez-Brenes, Francisco M., additional, Oneka, Oihane, additional, Marín, Diana, additional, Loidi, Maite, additional, de Castro, Ana I., additional, and Santesteban, L. G., additional
- Published
- 2020
- Full Text
- View/download PDF
9. Exploring UAV-imagery to support genotype selection in olive breeding programs
- Author
-
Universidad de Sevilla. Departamento de Agronomía, Rallo Morillo, Pilar, Castro, Ana I. de, López Granados, Francisca, Morales Sillero, Ana María, Torres Sánchez, Jorge, Jiménez González, María Rocío, Jiménez Brenes, Francisco M., Casanova Lerma, Laura, Suárez, María Paz, Universidad de Sevilla. Departamento de Agronomía, Rallo Morillo, Pilar, Castro, Ana I. de, López Granados, Francisca, Morales Sillero, Ana María, Torres Sánchez, Jorge, Jiménez González, María Rocío, Jiménez Brenes, Francisco M., Casanova Lerma, Laura, and Suárez, María Paz
- Abstract
Airborne methodologies based on unmanned aerial vehicles (UAV) are becoming an extraordinary tool for implementing fast, accurate and affordable phenotyping strategies within plant breeding programs. The aim of this paper was to study the potential use of a previously developed UAV-OBIA platform, to fasten and support decision making for olive breeders regarding the selection of the most promising genotypes in terms of tree geometric traits. In particular, we have studied the feasibility of the system to efficiently classify and select olive genotypes according to four architectural parameters: tree height, crown diameter, projected crown area and canopy volume. These vegetative growth traits and their evolution during the first months after planting are key selection criteria in olive breeding programs. On-ground measurements and UAV estimations were recorded over two years (when trees were 15 and 27 months old, respectively) in two olive breeding trials using different training systems, namely intensive open vase and super high-density hedgerows. More than 1000 young trees belonging to 39 olive accessions, including new cross-bred genotypes and traditional cultivars, were assessed. Even though the accuracy in the UAV estimation compared to the on-ground measurements largely improved the second year, both methodologies detected in both years a high variability and significant differences among the studied genotypes, allowing for statistical comparisons among them. Genotype rankings based on the on-ground measures and UAV estimations were compared. The resulting Spearman’s rank coefficient correlations were very high, at above 0.85 in most cases, which highlights that very similar genotype classifications were achieved from either field-measured or airborne-estimated data. Thus, UAV imagery may be used to assess geometric traits and to develop rankings for the efficient screening and selection of genotypes in olive breeding programs.
- Published
- 2020
10. Classification of 3D Point Clouds Using Color Vegetation Indices for Precision Viticulture and Digitizing Applications
- Author
-
Mesas-Carrascosa, Francisco-Javier, primary, de Castro, Ana I., additional, Torres-Sánchez, Jorge, additional, Triviño-Tarradas, Paula, additional, Jiménez-Brenes, Francisco M., additional, García-Ferrer, Alfonso, additional, and López-Granados, Francisca, additional
- Published
- 2020
- Full Text
- View/download PDF
11. Mapping Cynodon Dactylon Infesting Cover Crops with an Automatic Decision Tree-OBIA Procedure and UAV Imagery for Precision Viticulture
- Author
-
de Castro, Ana I., primary, Peña, José M., additional, Torres-Sánchez, Jorge, additional, Jiménez-Brenes, Francisco M., additional, Valencia-Gredilla, Francisco, additional, Recasens, Jordi, additional, and López-Granados, Francisca, additional
- Published
- 2019
- Full Text
- View/download PDF
12. High-Throughput System for the Early Quantification of Major Architectural Traits in Olive Breeding Trials Using UAV Images and OBIA Techniques
- Author
-
de Castro, Ana I., primary, Rallo, Pilar, additional, Suárez, María Paz, additional, Torres-Sánchez, Jorge, additional, Casanova, Laura, additional, Jiménez-Brenes, Francisco M., additional, Morales-Sillero, Ana, additional, Jiménez, María Rocío, additional, and López-Granados, Francisca, additional
- Published
- 2019
- Full Text
- View/download PDF
13. High-Throughput System for the Early Quantification of Major Architectural Traits in Olive Breeding Trials Using UAV Images and OBIA Techniques
- Author
-
Universidad de Sevilla. Departamento de Ciencias Agroforestales, Universidad de Sevilla. AGR188: Agronomia, Castro Mejías, Ana Isabel de, Rallo Morillo, Pilar, Suárez García, María Paz, Torres Sánchez, Jorge, Casanova Lerma, Laura, Jiménez Brenes, Francisco M., Morales Sillero, Ana María, Jiménez, María Rocío, López Granados, Francisca, Universidad de Sevilla. Departamento de Ciencias Agroforestales, Universidad de Sevilla. AGR188: Agronomia, Castro Mejías, Ana Isabel de, Rallo Morillo, Pilar, Suárez García, María Paz, Torres Sánchez, Jorge, Casanova Lerma, Laura, Jiménez Brenes, Francisco M., Morales Sillero, Ana María, Jiménez, María Rocío, and López Granados, Francisca
- Abstract
The need for the olive farm modernization have encouraged the research of more efficient crop management strategies through cross-breeding programs to release new olive cultivars more suitable for mechanization and use in intensive orchards, with high quality production and resistance to biotic and abiotic stresses. The advancement of breeding programs are hampered by the lack of efficient phenotyping methods to quickly and accurately acquire crop traits such as morphological attributes (tree vigor and vegetative growth habits), which are key to identify desirable genotypes as early as possible. In this context, an UAV-based high-throughput system for olive breeding program applications was developed to extract tree traits in large-scale phenotyping studies under field conditions. The system consisted of UAV-flight configurations, in terms of flight altitude and image overlaps, and a novel, automatic, and accurate object-based image analysis (OBIA) algorithm based on point clouds, which was evaluated in two experimental trials in the framework of a table olive breeding program, with the aim to determine the earliest date for suitable quantifying of tree architectural traits. Two training systems (intensive and hedgerow) were evaluated at two very early stages of tree growth: 15 and 27 months after planting. Digital Terrain Models (DTMs) were automatically and accurately generated by the algorithm as well as every olive tree identified, independently of the training system and tree age. The architectural traits, specially tree height and crown area, were estimated with high accuracy in the second flight campaign, i.e. 27 months after planting. Differences in the quality of 3D crown reconstruction were found for the growth patterns derived from each training system. These key phenotyping traits could be used in several olive breeding programs, as well as to address some agronomical goals. In addition, this system is cost and time optimized, so that requested architect
- Published
- 2019
14. High-Throughput System for the Early Quantification of Major Architectural Traits in Olive Breeding Trials Using UAV Images and OBIA Techniques
- Author
-
Universidad de Sevilla. Departamento de Agronomía, Castro, Ana I. de, Rallo Morillo, Pilar, Suárez García, María Paz, Torres Sánchez, Jorge, Casanova Lerma, Laura, Jiménez Brenes, Francisco M., Morales-Sillero, Ana, Jiménez González, María Rocío, López Granados, Francisca, Universidad de Sevilla. Departamento de Agronomía, Castro, Ana I. de, Rallo Morillo, Pilar, Suárez García, María Paz, Torres Sánchez, Jorge, Casanova Lerma, Laura, Jiménez Brenes, Francisco M., Morales-Sillero, Ana, Jiménez González, María Rocío, and López Granados, Francisca
- Abstract
The need for the olive farm modernization have encouraged the research of more efficient crop management strategies through cross-breeding programs to release new olive cultivars more suitable for mechanization and use in intensive orchards, with high quality production and resistance to biotic and abiotic stresses. The advancement of breeding programs are hampered by the lack of efficient phenotyping methods to quickly and accurately acquire crop traits such as morphological attributes (tree vigor and vegetative growth habits), which are key to identify desirable genotypes as early as possible. In this context, an UAV-based high-throughput system for olive breeding program applications was developed to extract tree traits in large-scale phenotyping studies under field conditions. The system consisted of UAV-flight configurations, in terms of flight altitude and image overlaps, and a novel, automatic, and accurate object-based image analysis (OBIA) algorithm based on point clouds, which was evaluated in two experimental trials in the framework of a table olive breeding program, with the aim to determine the earliest date for suitable quantifying of tree architectural traits. Two training systems (intensive and hedgerow) were evaluated at two very early stages of tree growth: 15 and 27 months after planting. Digital Terrain Models (DTMs) were automatically and accurately generated by the algorithm as well as every olive tree identified, independently of the training system and tree age. The architectural traits, specially tree height and crown area, were estimated with high accuracy in the second flight campaign, i.e. 27 months after planting. Differences in the quality of 3D crown reconstruction were found for the growth patterns derived from each training system. These key phenotyping traits could be used in several olive breeding programs, as well as to address some agronomical goals. In addition, this system is cost and time optimized, so that requested architect
- Published
- 2019
15. Cartografía de Cynodon dactylon en viñedo mediante imágenes UAV y tecnología OBIA para un uso sostenible y localizado de herbicidas
- Author
-
Castro, Ana Isabel de, Peña, José Manuel, Torres Sánchez, Jorge, Jiménez Brenes, Francisco M., Recasens, Jordi, Valencia, Francisco, López Granados, Francisca, Ministerio de Economía y Competitividad (España), and European Commission
- Subjects
Viticultura de precisión ,Site-specific weed map ,Object-based image analysis (OBIA) ,Teledetección ,Análisis de imágenes basado en objetos (OBIA) ,Remote sensing ,Cover green ,Cubiertas vegetales ,Mapa de manejo localizado de malas hierbas ,Precision viticulture - Abstract
Trabajo presentado en el XVI Congreso de la Sociedad Española de Malherbología, celebrado en Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017., [ES] El manejo adecuado de las cubiertas vegetales en viñedos de regadío protege el suelo de la erosión y permite equilibrar el vigor y rendimiento de la viña, lo que redunda en una mejora de la calidad de la cosecha. Estas ventajas quedan mermadas con las infestaciones de grama (Cynodon dactylon) en las cubiertas, una especie perenne, altamente competitiva y difícilmente controlable. El objetivo de este trabajo consistió en la detección temprana y mapeo de C. dactylon en viñedos con cubierta vegetal mediante el uso de imágenes UAV (vehículos aéreos no tripulados) y técnicas de análisis de imágenes basadas en objetos (OBIA). El algoritmo desarrollado permitió la clasificación de los 4 usos principales presentes en el viñedo (viña, suelo desnudo, grama y cubierta vegetal) y la generación de mapas de grama para su control localizado, disminuyendo de esta manera el coste económico y medioambiental del tratamiento., [EN] The use of cover crops is a usual management practice for irrigated vineyards that allows controlling vineyard vigor and yield, also improving the crop quality. However, those advantages have been reduced by bermudagrass (C. dactylon) populations infesting cover crop areas. Bermudagrass is a perennial, very competitive grass and tolerant of reap, pretty difficult to control. The objective of this research was the early mapping of C. dactylon patches in order to provide an optimized site-specific weed management. Object-based image analysis (OBIA) techniques applied to unmanned aerial vehicle (UAV) imagery solved the limitation of spectral similarity between bermudagrass and cover crops or bare soil. The classified maps showed the four main classes in the vineyard (vine, cover crop, C. dactylon and bare soil) with 85% overall accuracy, that allow developing new strategies for site-specific control of C. dactylon infestations and decreasing economical and environmental costs., Esta investigación fue financiada por el proyecto AGL2014-52465-C4-4-R (Ministerio de Economía y Competitividad, fondos FEDER: Fondo Europeo de Desarrollo Regional). La investigación del Dr. Jorge Torres-Sánchez, Dr. Ana de Castro y el Dr. José M. Peña fue financiada por los programas FPI (BES-2012-052424), Juan de la Cierva (MINECO) y Ramón y Cajal (MINECO), respectivamente.
- Published
- 2017
16. Early weed detection between and within the crop row using UAV images and 3D models
- Author
-
Torres Sánchez, Jorge, López Granados, Francisca, Castro, Ana Isabel de, Jiménez Brenes, Francisco M., Peña, José Manuel, Ministerio de Economía y Competitividad (España), and European Commission
- Subjects
Sunflower ,Manejo localizado ,OBIA ,Random Forest ,Site-specific weed management ,Precision agriculture ,Vehículo aéreo no tripulado ,Agricultura de precisión ,Unmanned aerial vehicle ,Girasol - Abstract
Trabajo presentado en el XVI Congreso de la Sociedad Española de Malherbología, celebrado en Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017., [ES] Se ha desarrollado una metodología automática para la detección temprana de malas hierbas dentro y fuera de la línea de cultivo en fase temprana usando como variable discriminante la altura de las plantas (cultivo y malas hierbas), calculada mediante técnicas fotogramétricas. Se utilizó un UAV equipado con una cámara modificada para captar información en las bandas del Rojo, Verde e Infrarrojo Cercano. Se tomaron imágenes sobre una parcela de girasol infestada por diferentes especies de malas hierbas en fase temprana. Las imágenes fueron procesadas para generar una ortoimagen y un modelo tridimensional del cultivo y malas hierbas para su posterior análisis usando métodos orientados a objetos y el clasificador Random Forest. Se comparó la infestación de malas hierbas detectada con la realmente existente en el campo en una serie de marcos de referencia, obteniéndose un coeficiente de determinación de 0,91 entre ambas variables., [EN] An automatic methodology for early season weed detection between and within the crop rows has been developed, where the main innovation was the use of plant height as discriminant feature. An UAV equipped with a conventional camera modified for R (red), G (green) and NIR (near infrared) acquisition was used for taken images over a sunflower plot infested with different weed species in early season. The images were processed to generate an orthomosaic and a digital surface model (DSM) representing both the crop and weeds, and they were analyzed using object based image analysis (OBIA) and Random Forest classifier. Automatically detected weed cover was compared with the real weed cover in the field in a number of reference frames, and the determination coefficient between both variables was 0.91., Este trabajo fue financiado por el proyecto AGL2014-52465-C4-4-R MINECO-FEDER. La investigación de Jorge Torres Sánchez, Ana Isabel de Castro Megías y José Manuel Peña Barragán fue financiada por los programas FPI, Juan de la Cierva, y Ramón y Cajal, respectivamente. La estancia de Jorge Torres Sánchez en la Universidad de Salzburgo fue financiada por el programa FPI.
- Published
- 2017
17. Principales variables para la detección de plántulas de amapola (Papaver rhoeas) en imágenes tomadas con un vehículo aéreo no tripulado
- Author
-
Peña, José Manuel, Castro, Ana Isabel de, Torres Sánchez, Jorge, Jiménez Brenes, Francisco M., Valencia, Francisco, López Granados, Francisca, and Ministerio de Economía y Competitividad (España)
- Subjects
Object-based image analysis (OBIA) ,UAV ,Decision tree models ,Winter cereals ,Análisis de imágenes basado en objetos (OBIA) ,Control localizado de malas hierba ,Árboles de decisión ,Site-specific weed control ,Control localizado de malas hierbas ,Cereal de invierno - Abstract
Trabajo presentado en el XVI Congreso de la Sociedad Española de Malherbología, celebrado en la Universidad Pública de Navarra, Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017., [ES] En este trabajo se han evaluado variables espectrales, morfológicas (forma, tamaño), contextuales (posición) y texturales que permitan desarrollar un procedimiento automático de clasificación de plántulas de amapola, otras malas hierbas, cultivo y suelo desnudo en imágenes adquiridas con un vehículo aéreo no tripulado (UAV). Las imágenes se tomaron con una cámara modificada para la obtención de información en infrarrojo-color y a una resolución espacial de 0,60 cm/píxel. Se aplicaron técnicas avanzadas de análisis de imágenes basadas en objetos para la obtención de las variables descritas y se desarrolló un modelo tipo árbol de decisión para cuantificar la importancia de cada variable en la clasificación. Los resultados indicaron que la información espectral basada en el índice de vegetación de diferencias normalizadas (NDVI, por sus siglas en inglés) aportó un 46% al modelo de clasificación, principalmente para la discriminación de objetos de vegetación y suelo desnudo. Por otra parte, para la identificación de las plántulas de amapola fue necesario incorporar además variables morfológicas (principalmente, el área [tamaño] del objeto, que aportó un 36% al modelo) y texturales (p.ej., textura media y entropía, con un 11% de contribución en el modelo). Por su parte, la distancia relativa de los objetos a la línea de cultivo tuvo escasa importancia en la clasificación total., [EN] A group of spectral, morphological (shape-based, size), contextual (location), and textural features were evaluated with the aim of automatic classification of Papaver rhoeas seedlings, other weeds, crop plants and bare soil in images collected with an unmanned aerial vehicle (UAV). The images were taken with a color-infrared modified camera at 0,60 cm/pixel of spatial resolution. The features were obtained by applying advanced object-based images techniques, and their contribution to the classification was analyzed with decision tree modeling. Spectral information from the normalized difference vegetation index (NDVI) contributed 46% to the model, mainly due to its capacity to discriminate vegetation and bare soil objects. Additionally, identification of Papaver rhoeas seedlings was possible by incorporating morphological (mainly object size, which contributed to 36% to the model) and textural features (e.g., mean and entropy, which contributed to 11% to the model). Finally, relative distance of the objects to the crop-rows had a low importance in the total classification results., Investigación financiada por el proyecto MINECO AGL2014-52465-C4-4R. La investigación de Dr. José M. Peña, Dr. Ana de Castro y Dr. Jorge Torres-Sánchez fue financiada por los programas Ramón y Cajal (MINECO), Juan de la Cierva (MINECO) y FPI (BES-2012-052424), respectivamente
- Published
- 2017
18. Mapping Cynodon dactylon in vineyard by using UAV-images and OBIA technology for site-specific weed management
- Author
-
Castro, Ana Isabel de, Peña, José Manuel, Torres Sánchez, Jorge, Jiménez Brenes, Francisco M., Recasens, Jordi, Valencia, Francisco, and López Granados, Francisca
- Subjects
Viticultura de precisión ,Site-specific weed map ,Object-based image analysis (OBIA) ,Teledetección ,Análisis de imágenes basado en objetos (OBIA) ,Remote sensing ,Cover green ,Cubiertas vegetales ,Mapa de manejo localizado de malas hierbas ,Precision viticulture - Abstract
Comunicación presentada al XVI Congreso de la Sociedad Española de Malherbología, celebrado en la Universidad Pública de Navarra, Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017. El manejo adecuado de las cubiertas vegetales en viñedos de regadío protege el suelo de la erosión y permite equilibrar el vigor y rendimiento de la viña, lo que redunda en una mejora de la calidad de la cosecha. Estas ventajas quedan mermadas con las infestaciones de grama (Cynodon dactylon) en las cubiertas, una especie perenne, altamente competitiva y difícilmente controlable. El objetivo de este trabajo consistió en la detección temprana y mapeo de C. dactylon en viñedos con cubierta vegetal mediante el uso de imágenes UAV (vehículos aéreos no tripulados) y técnicas de análisis de imágenes basadas en objetos (OBIA). El algoritmo desarrollado permitió la clasificación de los 4 usos principales presentes en el viñedo (viña, suelo desnudo, grama y cubierta vegetal) y la generación de mapas de grama para su control localizado, disminuyendo de esta manera el coste económico y medioambiental del tratamiento. The use of cover crops is a usual management practice for irrigated vineyards that allows controlling vineyard vigor and yield, also improving the crop quality. However, those advantages have been reduced by bermudagrass (C. dactylon) populations infesting cover crop areas. Bermudagrass is a perennial, very competitive grass and tolerant of reap, pretty difficult to control. The objective of this research was the early mapping of C. dactylon patches in order to provide an optimized site-specific weed management. Object-based image analysis (OBIA) techniques applied to unmanned aerial vehicle (UAV) imagery solved the limitation of spectral similarity between bermudagrass and cover crops or bare soil. The classified maps showed the four main classes in the vineyard (vine, cover crop, C. dactylon and bare soil) with 85% overall accuracy, that allow developing new strategies for site-specific control of C. dactylon infestations and decreasing economical and environmental costs. Esta investigación fue financiada por el proyecto AGL2014-52465-C4-4R (Ministerio de Economía y Competitividad, fondos FEDER: Fondo Europeo de Desarrollo Regional). La investigación del Dr. Jorge Torres-Sánchez, Dr. Ana de Castro y el Dr. José M. Peña fue financiada por los programas FPI (BES-2012-052424), Juan de la Cierva (MINECO) y Ramón y Cajal (MINECO), respectivamente.
- Published
- 2017
19. Optimization of weed mapping using geostatistical techniques and remote sensing with UAV
- Author
-
Jurado Expósito, Monserrat, Castro, Ana Isabel de, Torres Sánchez, Jorge, Jiménez Brenes, Francisco M., and López Granados, Francisca
- Subjects
Kriging ,Krigeado ,Cokriging ,Variogramas ,Precision agriculture ,Agricultura de precisión ,Variograms ,Cokrigeado - Abstract
Comunicación presentada al XVI Congreso de la Sociedad Española de Malherbología, celebrado en la Universidad Pública de Navarra, Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017. Se evalúa una metodología para la cartografía de malas hierbas en época tardía del cultivo combinando datos espaciales georreferenciados (variable primaria) con información espectral (variables secundarias). Como variable 1ia se ha estudiado Papaver rhoeas L. en trigo y como variables 2ias: las bandas Rojo, Verde, Azul y NIR (Near-InfraRed) de imágenes UAV (Unmanned Aerial Vehicles) tomadas en campo el día del muestreo. Se comparan dos tipos de estimadores: krigeado ordinario (análisis de la variable 1iª) y cokrigeado (análisis incorporando variables 2ias). La comparación de la precisión de los mapas de infestación obtenidos se ha realizado en base a la incertidumbre de las estimas. Los resultados muestran que la incorporación de variables secundarias espectrales al proceso de interpolación geoestadística mejora la estimación de la variable 1ia, especialmente cuando se incluye en el análisis la banda Verde. A methodology for late weed mapping combining georeferenced spatial data (1st variable) with spectral information (2nd variables) is evaluated. The Papaver rhoeas L. spatial data in wheat was used as1st variable and Red, Green, Blue and NIR bands from UAV images as 2nd variables. Two types of algorithms were compared: Ordinary Kriging (analysis of 1st variable) and CoKriging (to incorporate the 2nd variables). Comparison of infestations maps accuracy was based on cross validation statistics. Results showed that including spectral secondary variables into geostatistical analysis improves the accuracy of 1st variable estimations, especially when band G is included as 2nd variable. Estudio financiado por el proyecto AGL2014-52465-C4-4-R MINECO-FEDER. Ana Isabel de Castro fue financiada por el programas Juan de la Cierva (MINECO).
- Published
- 2017
20. Main features for the detection of Papaver rhoeas seedlings in images collected with an unmanned aerial vehicle
- Author
-
Peña, José Manuel, Castro, Ana Isabel de, Torres Sánchez, Jorge, Jiménez Brenes, Francisco M., Valencia, Francisco, and López Granados, Francisca
- Subjects
Object-based image analysis (OBIA) ,UAV ,Decision tree models ,Winter cereals ,Análisis de imágenes basado en objetos (OBIA) ,Árboles de decisión ,Site-specific weed control ,Cereal de invierno ,Control localizado de malas hierbas - Abstract
Comunicación presentada al XVI Congreso de la Sociedad Española de Malherbología, celebrado en la Universidad Pública de Navarra, Pamplona-Iruña, entre los días 25 y 27 de octubre de 2017. En este trabajo se han evaluado variables espectrales, morfológicas (forma, tamaño), contextuales (posición) y texturales que permitan desarrollar un procedimiento automático de clasificación de plántulas de amapola, otras malas hierbas, cultivo y suelo desnudo en imágenes adquiridas con un vehículo aéreo no tripulado (UAV). Las imágenes se tomaron con una cámara modificada para la obtención de información en infrarrojo-color y a una resolución espacial de 0,60 cm/píxel. Se aplicaron técnicas avanzadas de análisis de imágenes basadas en objetos para la obtención de las variables descritas y se desarrolló un modelo tipo árbol de decisión para cuantificar la importancia de cada variable en la clasificación. Los resultados indicaron que la información espectral basada en el índice de vegetación de diferencias normalizadas (NDVI, por sus siglas en inglés) aportó un 46% al modelo de clasificación, principalmente para la discriminación de objetos de vegetación y suelo desnudo. Por otra parte, para la identificación de las plántulas de amapola fue necesario incorporar además variables morfológicas (principalmente, el área [tamaño] del objeto, que aportó un 36% al modelo) y texturales (p.ej., textura media y entropía, con un 11% de contribución en el modelo). Por su parte, la distancia relativa de los objetos a la línea de cultivo tuvo escasa importancia en la clasificación total. A group of spectral, morphological (shape-based, size), contextual (location), and textural features were evaluated with the aim of automatic classification of Papaver rhoeas seedlings, other weeds, crop plants and bare soil in images collected with an unmanned al vehicle (UAV). The images were taken with a color-infrared modified camera at 0,60 cm/pixel of spatial resolution. The features were obtained by applying advanced object-based images techniques, and their contribution to the classification was analyzed with decision tree modeling. Spectral information from the normalized difference vegetation index (NDVI) contributed 46% to the model, mainly due to its capacity to discriminate vegetation and bare soil objects. Additionally, identification of Papaver rhoeas seedlings was possible by incorporating morphological (mainly object size, which contributed to 36% to the model) and textural features (e.g., mean and entropy, which contributed to 11% to the model). Finally, relative distance of the objects to the crop-rows had a low importance in the total classification results. Investigación financiada por el proyecto MINECO AGL2014-52465-C4-4R. La investigación de Dr. José M. Peña, Dr. Ana de Castro y Dr. Jorge Torres-Sánchez fue financiada por los programas Ramón y Cajal (MINECO), Juan de la Cierva (MINECO) y FPI (BES-2012- 052424), respectivamente.
- Published
- 2017
21. An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery.
- Author
-
de Castro, Ana I., Torres-Sánchez, Jorge, Peña, Jose M., Jiménez-Brenes, Francisco M., Csillik, Ovidiu, and López-Granados, Francisca
- Subjects
CROP growth ,CROP management ,WEED control ,AGRICULTURE ,DRONE aircraft ,REMOTE-sensing images - Abstract
Accurate and timely detection of weeds between and within crop rows in the early growth stage is considered one of the main challenges in site-specific weed management (SSWM). In this context, a robust and innovative automatic object-based image analysis (OBIA) algorithm was developed on Unmanned Aerial Vehicle (UAV) images to design early post-emergence prescription maps. This novel algorithm makes the major contribution. The OBIA algorithm combined Digital Surface Models (DSMs), orthomosaics and machine learning techniques (Random Forest, RF). OBIA-based plant heights were accurately estimated and used as a feature in the automatic sample selection by the RF classifier; this was the second research contribution. RF randomly selected a class balanced training set, obtained the optimum features values and classified the image, requiring no manual training, making this procedure time-efficient and more accurate, since it removes errors due to a subjective manual task. The ability to discriminate weeds was significantly affected by the imagery spatial resolution and weed density, making the use of higher spatial resolution images more suitable. Finally, prescription maps for in-season post-emergence SSWM were created based on the weed maps--the third research contribution--which could help farmers in decision-making to optimize crop management by rationalization of the herbicide application. The short time involved in the process (image capture and analysis) would allow timely weed control during critical periods, crucial for preventing yield loss. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
22. Mapping Cynodon Dactylon Infesting Cover Crops with an Automatic Decision Tree-OBIA Procedure and UAV Imagery for Precision Viticulture.
- Author
-
de Castro, Ana I., Peña, José M., Torres-Sánchez, Jorge, Jiménez-Brenes, Francisco M., Valencia-Gredilla, Francisco, Recasens, Jordi, and López-Granados, Francisca
- Subjects
BERMUDA grass ,COVER crops ,HERBICIDE application ,VITICULTURE ,CROP management ,DIGITAL elevation models ,DRONE aircraft - Abstract
The establishment and management of cover crops are common practices widely used in irrigated viticulture around the world, as they bring great benefits not only to protect and improve the soil, but also to control vine vigor and improve the yield quality, among others. However, these benefits are often reduced when cover crops are infested by Cynodon dactylon (bermudagrass), which impacts crop production due to its competition for water and nutrients and causes important economic losses for the winegrowers. Therefore, the discrimination of Cynodon dactylon in cover crops would enable site-specific control to be applied and thus drastically mitigate damage to the vineyard. In this context, this research proposes a novel, automatic and robust image analysis algorithm for the quick and accurate mapping of Cynodon dactylon growing in vineyard cover crops. The algorithm was developed using aerial images taken with an Unmanned Aerial Vehicle (UAV) and combined decision tree (DT) and object-based image analysis (OBIA) approaches. The relevance of this work consisted in dealing with the constraint caused by the spectral similarity of these complex scenarios formed by vines, cover crops, Cynodon dactylon, and bare soil. The incorporation of height information from the Digital Surface Model and several features selected by machine learning tools in the DT-OBIA algorithm solved this spectral similarity limitation and allowed the precise design of Cynodon dactylon maps. Another contribution of this work is the short time needed to apply the full process from UAV flights to image analysis, which can enable useful maps to be created on demand (within two days of the farmer´s request) and is thus timely for controlling Cynodon dactylon in the herbicide application window. Therefore, this combination of UAV imagery and a DT-OBIA algorithm would allow winegrowers to apply site-specific control of Cynodon dactylon and maintain cover crop-based management systems and their consequent benefits in the vineyards, and also comply with the European legal framework for the sustainable use of agricultural inputs and implementation of integrated crop management. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
23. 3-D Characterization of Vineyards Using a Novel UAV Imagery-Based OBIA Procedure for Precision Viticulture Applications.
- Author
-
de Castro, Ana I., Jiménez-Brenes, Francisco M., Torres-Sánchez, Jorge, Peña, José M., Borra-Serrano, Irene, and López-Granados, Francisca
- Subjects
- *
VINEYARDS , *DRONE aircraft , *VITICULTURE , *PRECISION farming , *DIGITAL elevation models - Abstract
Precision viticulture has arisen in recent years as a new approach in grape production. It is based on assessing field spatial variability and implementing site-specific management strategies, which can require georeferenced information of the three dimensional (3D) grapevine canopy structure as one of the input data. The 3D structure of vineyard fields can be generated applying photogrammetric techniques to aerial images collected with Unmanned Aerial Vehicles (UAVs), although processing the large amount of crop data embedded in 3D models is currently a bottleneck of this technology. To solve this limitation, a novel and robust object-based image analysis (OBIA) procedure based on Digital Surface Model (DSM) was developed for 3D grapevine characterization. The significance of this work relies on the developed OBIA algorithm which is fully automatic and self-adaptive to different crop-field conditions, classifying grapevines, and row gap (missing vine plants), and computing vine dimensions without any user intervention. The results obtained in three testing fields on two different dates showed high accuracy in the classification of grapevine area and row gaps, as well as minor errors in the estimates of grapevine height. In addition, this algorithm computed the position, projected area, and volume of every grapevine in the field, which increases the potential of this UAV- and OBIA-based technology as a tool for site-specific crop management applications. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.