Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage

The detection, geolocation, and classification of weeds in agricultural fields is a problem of interest associated with Precision Agriculture (PA). The main contribution of this work is to describe a workflow (feasible to automate) based on open-source software tools and open information to: 1) meas...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Bussi, Ulises, Sauczuk, Martín, Mandile, Guillermo, Poggio, Santiago, Oliva, Damián
Formato: Articulo
Lenguaje:Inglés
Publicado: 2023
Materias:
Ciencias Informáticas
Weed
Sentinel-2
Unmanned Aerial Vehicle
UAV
Malezas
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/157807
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-157807
record_format dspace
spelling I19-R120-10915-1578072023-09-19T04:03:01Z http://sedici.unlp.edu.ar/handle/10915/157807 Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage Fusión de información satelital con vuelos a baja altura de vehículos aéreos no tripulados para estimar la cobertura de malezas Bussi, Ulises Sauczuk, Martín Mandile, Guillermo Poggio, Santiago Oliva, Damián 2023-06 2023-09-18T18:47:27Z en Ciencias Informáticas Weed Sentinel-2 Unmanned Aerial Vehicle UAV Malezas The detection, geolocation, and classification of weeds in agricultural fields is a problem of interest associated with Precision Agriculture (PA). The main contribution of this work is to describe a workflow (feasible to automate) based on open-source software tools and open information to: 1) measure the spatiotemporal evolution of weed patches through satellite images, and 2) register high-resolution images (taken at low altitude) on top of the satellite image to identify the weeds that compose the detected patches. To merge the satellite and low-altitude information, the following problems must be solved: 1) correct distortions in the acquired images; 2) develop an image formation model that allows registering the low-altitude image on top of the satellite image, and 3) analyze green indices to measure patch coverage in both multiespectral satellite images and RGB images obtained from a camera mounted on an unmanned aerial vehicle. Finally, the feasibility of merging information is demonstrated through an analysis of the correlation in the coverage measures obtained from satellite and low-altitude images. La deteccion, geolocalizacion y clasificacion de malezas en campos agricolas es un problema de interes asociado a la Agricultura de Precision (AP). El aporte principal de este trabajo es describir un flujo de trabajo (factible de automatizar) basado en herramientas de software libre e informacion abierta para: 1) medir la evolucion espaciotemporal de los parches de malezas a traves de imagenes satelitales y; 2) registrar las imagenes de alta resolucion (tomadas a baja altura) sobre la imagen satelital, para identificar las malezas que componen los parches detectados. Para fusionar la informacion satelital y de baja altura, se deben resolver los siguientes problemas: 1) corregir las distorsiones en las imagenes adquiridas; 2) desarrollar un modelo de formacion de imagenes que permita registrar la imagen a baja altura sobre la imagen satelital; 3) analizar los indices de verde para medir la cobertura de los parches, tanto en las imagenes satelitales multiespectrales, como en las imagenes RGB obtenidas desde una camara montada en un vehıculo aereo no tripulado. Finalmente, se muestra la factibilidad de realizar la fusion de informacion a partir de un analisis de la correlacion en las medidas de cobertura obtenidas de las imagenes satelitales y de las de baja altura. Sociedad Argentina de Informática e Investigación Operativa Articulo Articulo http://creativecommons.org/licenses/by-nc/4.0/ Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) application/pdf 2-21
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Weed
Sentinel-2
Unmanned Aerial Vehicle
UAV
Malezas
spellingShingle Ciencias Informáticas
Weed
Sentinel-2
Unmanned Aerial Vehicle
UAV
Malezas
Bussi, Ulises
Sauczuk, Martín
Mandile, Guillermo
Poggio, Santiago
Oliva, Damián
Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
topic_facet Ciencias Informáticas
Weed
Sentinel-2
Unmanned Aerial Vehicle
UAV
Malezas
description The detection, geolocation, and classification of weeds in agricultural fields is a problem of interest associated with Precision Agriculture (PA). The main contribution of this work is to describe a workflow (feasible to automate) based on open-source software tools and open information to: 1) measure the spatiotemporal evolution of weed patches through satellite images, and 2) register high-resolution images (taken at low altitude) on top of the satellite image to identify the weeds that compose the detected patches. To merge the satellite and low-altitude information, the following problems must be solved: 1) correct distortions in the acquired images; 2) develop an image formation model that allows registering the low-altitude image on top of the satellite image, and 3) analyze green indices to measure patch coverage in both multiespectral satellite images and RGB images obtained from a camera mounted on an unmanned aerial vehicle. Finally, the feasibility of merging information is demonstrated through an analysis of the correlation in the coverage measures obtained from satellite and low-altitude images.
format Articulo
Articulo
author Bussi, Ulises
Sauczuk, Martín
Mandile, Guillermo
Poggio, Santiago
Oliva, Damián
author_facet Bussi, Ulises
Sauczuk, Martín
Mandile, Guillermo
Poggio, Santiago
Oliva, Damián
author_sort Bussi, Ulises
title Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
title_short Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
title_full Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
title_fullStr Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
title_full_unstemmed Satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
title_sort satellite information fusion with low-altitude unmanned aerial vehicle flights for estimating weed coverage
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/157807
work_keys_str_mv AT bussiulises satelliteinformationfusionwithlowaltitudeunmannedaerialvehicleflightsforestimatingweedcoverage
AT sauczukmartin satelliteinformationfusionwithlowaltitudeunmannedaerialvehicleflightsforestimatingweedcoverage
AT mandileguillermo satelliteinformationfusionwithlowaltitudeunmannedaerialvehicleflightsforestimatingweedcoverage
AT poggiosantiago satelliteinformationfusionwithlowaltitudeunmannedaerialvehicleflightsforestimatingweedcoverage
AT olivadamian satelliteinformationfusionwithlowaltitudeunmannedaerialvehicleflightsforestimatingweedcoverage
AT bussiulises fusiondeinformacionsatelitalconvuelosabajaalturadevehiculosaereosnotripuladosparaestimarlacoberturademalezas
AT sauczukmartin fusiondeinformacionsatelitalconvuelosabajaalturadevehiculosaereosnotripuladosparaestimarlacoberturademalezas
AT mandileguillermo fusiondeinformacionsatelitalconvuelosabajaalturadevehiculosaereosnotripuladosparaestimarlacoberturademalezas
AT poggiosantiago fusiondeinformacionsatelitalconvuelosabajaalturadevehiculosaereosnotripuladosparaestimarlacoberturademalezas
AT olivadamian fusiondeinformacionsatelitalconvuelosabajaalturadevehiculosaereosnotripuladosparaestimarlacoberturademalezas
_version_ 1807221314170126336

Ejemplares similares