Deep Learning Architecture for Forest Detection in Satellite Data

Deep Learning algorithms have achieved great progress in different applications due to their training capabilities, parameter reduction and increased accuracy. Image processing is a particular area that has received recent attention promoted by the growing processing power and data availability. Rem...

Descripción completa

Detalles Bibliográficos
Autores principales: Caffaratti, Gabriel D., Marchetta, Martín G., Forradellas Martinez, Raymundo Quilez, Euillades, Leonardo D., Euillades, Pablo A.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2019
Materias:
Ciencias Informáticas
Remote sensing
Forest detection
Deep learning
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/90894
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-90894
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Remote sensing
Forest detection
Deep learning
spellingShingle Ciencias Informáticas
Remote sensing
Forest detection
Deep learning
Caffaratti, Gabriel D.
Marchetta, Martín G.
Forradellas Martinez, Raymundo Quilez
Euillades, Leonardo D.
Euillades, Pablo A.
Deep Learning Architecture for Forest Detection in Satellite Data
topic_facet Ciencias Informáticas
Remote sensing
Forest detection
Deep learning
description Deep Learning algorithms have achieved great progress in different applications due to their training capabilities, parameter reduction and increased accuracy. Image processing is a particular area that has received recent attention promoted by the growing processing power and data availability. Remote sensing devices provide image-like data that can be used to characterize Earth’s natural or artificial phenomena. Particularly, forest detection is important in many applications like flooding simulations, analysis of forest health or detection of area desertification. The existing techniques for forest detection based on satellite data lack accuracy or still require human expert intervention to correct recognition errors or parameter setup. In this work a Deep Learning architecture for forest detection is presented, that aims at increasing accuracy and reducing expert dependency. A data preprocessing procedure, analysis and dataset composition for robust automatic forest detection is described. The proposed approach was validated with real SRTM and Landsat-8 satellite data.
format Objeto de conferencia
Objeto de conferencia
author Caffaratti, Gabriel D.
Marchetta, Martín G.
Forradellas Martinez, Raymundo Quilez
Euillades, Leonardo D.
Euillades, Pablo A.
author_facet Caffaratti, Gabriel D.
Marchetta, Martín G.
Forradellas Martinez, Raymundo Quilez
Euillades, Leonardo D.
Euillades, Pablo A.
author_sort Caffaratti, Gabriel D.
title Deep Learning Architecture for Forest Detection in Satellite Data
title_short Deep Learning Architecture for Forest Detection in Satellite Data
title_full Deep Learning Architecture for Forest Detection in Satellite Data
title_fullStr Deep Learning Architecture for Forest Detection in Satellite Data
title_full_unstemmed Deep Learning Architecture for Forest Detection in Satellite Data
title_sort deep learning architecture for forest detection in satellite data
publishDate 2019
url http://sedici.unlp.edu.ar/handle/10915/90894
work_keys_str_mv AT caffarattigabrield deeplearningarchitectureforforestdetectioninsatellitedata
AT marchettamarting deeplearningarchitectureforforestdetectioninsatellitedata
AT forradellasmartinezraymundoquilez deeplearningarchitectureforforestdetectioninsatellitedata
AT euilladesleonardod deeplearningarchitectureforforestdetectioninsatellitedata
AT euilladespabloa deeplearningarchitectureforforestdetectioninsatellitedata
bdutipo_str Repositorios
_version_ 1764820490497556485

Ejemplares similares