Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires

The present work aims to obtain a classifier for summer crops in the northwest of Buenos Aires province from Landsat satellite images. Active Learning (AL) was used as the classification technique since it obtains satisfactory results using a small set of labeled samples to train the algorithm. The...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Cicerchia, Lucas Benjamín, Russo, Claudia, Abasolo, María José
Otros Autores: 0000-0003-0316-7896
Formato: Artículo publishedVersion
Lenguaje:Inglés
Publicado: Springer, Cham. 2021
Materias:
Active learning
Cropland classification
Land cover classification
Remote sensing
Multispectral Image
Big data
Acceso en línea:https://repositorio.unnoba.edu.ar/xmlui/handle/23601/151
Aporte de:
Re DI Repositorio Digital UNNOBA de Universidad Nacional del Noroeste de la Provincia de Buenos Aires
id I103-R405-23601-151
record_format dspace
spelling I103-R405-23601-1512021-07-27T12:45:49Z Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires Cicerchia, Lucas Benjamín Russo, Claudia Abasolo, María José 0000-0003-0316-7896 0000-0002-0345-4783 0000-0003-4441-3264 Active learning Cropland classification Land cover classification Remote sensing Multispectral Image Big data The present work aims to obtain a classifier for summer crops in the northwest of Buenos Aires province from Landsat satellite images. Active Learning (AL) was used as the classification technique since it obtains satisfactory results using a small set of labeled samples to train the algorithm. The construction of the training set is iteratively performed by means of a heuristic for the selection of the unlabeled samples to be classified by an expert. The following heuristics were used for comparison: Breaking Ties, Multiclass Level Uncertainty, Margin Sampling, and Random Sampling. The algorithm was also compared with the supervised technique Support Vector Machine (SVM). The experiments were tested on three Landsat 8 images from different dates using 6 bands per image and various vegetation indices. The results obtained using AL in combination with the different heuristics do not differ substantially from SVM. Fil: Cicerchia, Lucas Benjamín. Universidad Nacional del Noroeste de la Provincia de Buenos. Instituto de Investigación y Transferencia en Tecnología (ITT) – (Centro CICPBA); Argentina Fil: Russo, Claudia. Universidad Nacional del Noroeste de la Provincia de Buenos. Instituto de Investigación y Transferencia en Tecnología (ITT) – (Centro CICPBA); Argentina Fil: Abasolo, María José, Commission of Scientific Research of the Buenos Aires Province (CICPBA)Buenos Aires. III-LIDI, Faculty of InformaticsNational University of La Plata (UNLP)La Plata; Argentina Con referato 2021-07-27T12:45:49Z 2021-07-27T12:45:49Z 2020-10-24 info:eu-repo/semantics/article info:ar-repo/semantics/artículo info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article info:ar-repo/semantics/artículo info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article info:ar-repo/semantics/artículo info:eu-repo/semantics/publishedVersion Cicerchia, L; Russo, C.; Abasolo, M.J. (2020). Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires (Jornadas de Cloud Computing, Big Data & Emerging Topics (JCC-BD&ET) - UNLP; 7 al 11 de septiembre de 2020. La Plata). ISBN: 978-3-030-61218-4. DOI: https://doi.org/10.1007/978-3-030-61218-4_10. 978-3-030-61218-4 https://repositorio.unnoba.edu.ar/xmlui/handle/23601/151 eng https://doi.org/10.1007/978-3-030-61218-4_10 info:eu-repo/semantics/closedAccess https://creativecommons.org/licenses/by-nc-nd/2.5/ar/ application/pdf application/pdf Springer, Cham. JCC-BD&ET 2020: Cloud Computing, Big Data & Emerging Topics
institution Universidad Nacional del Noroeste de la Provincia de Buenos Aires
institution_str I-103
repository_str R-405
collection Re DI Repositorio Digital UNNOBA
language Inglés
topic Active learning
Cropland classification
Land cover classification
Remote sensing
Multispectral Image
Big data
spellingShingle Active learning
Cropland classification
Land cover classification
Remote sensing
Multispectral Image
Big data
Cicerchia, Lucas Benjamín
Russo, Claudia
Abasolo, María José
Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
topic_facet Active learning
Cropland classification
Land cover classification
Remote sensing
Multispectral Image
Big data
description The present work aims to obtain a classifier for summer crops in the northwest of Buenos Aires province from Landsat satellite images. Active Learning (AL) was used as the classification technique since it obtains satisfactory results using a small set of labeled samples to train the algorithm. The construction of the training set is iteratively performed by means of a heuristic for the selection of the unlabeled samples to be classified by an expert. The following heuristics were used for comparison: Breaking Ties, Multiclass Level Uncertainty, Margin Sampling, and Random Sampling. The algorithm was also compared with the supervised technique Support Vector Machine (SVM). The experiments were tested on three Landsat 8 images from different dates using 6 bands per image and various vegetation indices. The results obtained using AL in combination with the different heuristics do not differ substantially from SVM.
author2 0000-0003-0316-7896
author_facet 0000-0003-0316-7896
Cicerchia, Lucas Benjamín
Russo, Claudia
Abasolo, María José
format Artículo
Artículo
publishedVersion
Artículo
Artículo
publishedVersion
Artículo
Artículo
publishedVersion
author Cicerchia, Lucas Benjamín
Russo, Claudia
Abasolo, María José
author_sort Cicerchia, Lucas Benjamín
title Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
title_short Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
title_full Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
title_fullStr Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
title_full_unstemmed Classification of summer crops using Active Learning techniques on Landsat images in the Northwest of the Province of Buenos Aires
title_sort classification of summer crops using active learning techniques on landsat images in the northwest of the province of buenos aires
publisher Springer, Cham.
publishDate 2021
url https://repositorio.unnoba.edu.ar/xmlui/handle/23601/151
work_keys_str_mv AT cicerchialucasbenjamin classificationofsummercropsusingactivelearningtechniquesonlandsatimagesinthenorthwestoftheprovinceofbuenosaires
AT russoclaudia classificationofsummercropsusingactivelearningtechniquesonlandsatimagesinthenorthwestoftheprovinceofbuenosaires
AT abasolomariajose classificationofsummercropsusingactivelearningtechniquesonlandsatimagesinthenorthwestoftheprovinceofbuenosaires
_version_ 1850060847672459264

Ejemplares similares