Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach

Detalhes bibliográficos
Autor(a) principal: Negri, Rogério G. [UNESP]
Data de Publicação: 2021
Outros Autores: Frery, Alejandro C.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/s10044-020-00954-w
http://hdl.handle.net/11449/205698
Resumo: The Earth’s environment is continually changing due to both human and natural factors. Timely identification of the location and kind of change is of paramount importance in several areas of application. Because of that, remote sensing change detection is a topic of great interest. The development of precise change detection methods is a constant challenge. This study introduces a novel unsupervised change detection method based on data clustering and optimization. The proposal is less dependent on radiometric normalization than classical approaches. We carried experiments with remote sensing images and simulated datasets to compare the proposed method with other unsupervised well-known techniques. At its best, the proposal improves by 50% the accuracy concerning the second best technique. Such improvement is most noticeable with uncalibrated data. Experiments with simulated data reveal that the proposal is better than all other compared methods at any practical significance level. The results show the potential of the proposed method.
id UNSP_6068682e330458011f7231c6715eb6e6
oai_identifier_str oai:repositorio.unesp.br:11449/205698
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Unsupervised Change Detection Driven by Floating References: A Pattern Analysis ApproachPattern analysisRemote sensingUnsupervised change detectionThe Earth’s environment is continually changing due to both human and natural factors. Timely identification of the location and kind of change is of paramount importance in several areas of application. Because of that, remote sensing change detection is a topic of great interest. The development of precise change detection methods is a constant challenge. This study introduces a novel unsupervised change detection method based on data clustering and optimization. The proposal is less dependent on radiometric normalization than classical approaches. We carried experiments with remote sensing images and simulated datasets to compare the proposed method with other unsupervised well-known techniques. At its best, the proposal improves by 50% the accuracy concerning the second best technique. Such improvement is most noticeable with uncalibrated data. Experiments with simulated data reveal that the proposal is better than all other compared methods at any practical significance level. The results show the potential of the proposed method.Department of Environmental Engineering Institute of Science and Technology—ICT São Paulo State University—UNESPSchool of Mathematics and Statistics Victoria University of WellingtonDepartment of Environmental Engineering Institute of Science and Technology—ICT São Paulo State University—UNESPUniversidade Estadual Paulista (Unesp)Victoria University of WellingtonNegri, Rogério G. [UNESP]Frery, Alejandro C.2021-06-25T10:19:49Z2021-06-25T10:19:49Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1007/s10044-020-00954-wPattern Analysis and Applications.1433-755X1433-7541http://hdl.handle.net/11449/20569810.1007/s10044-020-00954-w2-s2.0-85099041428Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPattern Analysis and Applicationsinfo:eu-repo/semantics/openAccess2021-10-22T13:22:22Zoai:repositorio.unesp.br:11449/205698Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T21:03:29.882056Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
title Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
spellingShingle Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
Negri, Rogério G. [UNESP]
Pattern analysis
Remote sensing
Unsupervised change detection
title_short Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
title_full Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
title_fullStr Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
title_full_unstemmed Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
title_sort Unsupervised Change Detection Driven by Floating References: A Pattern Analysis Approach
author Negri, Rogério G. [UNESP]
author_facet Negri, Rogério G. [UNESP]
Frery, Alejandro C.
author_role author
author2 Frery, Alejandro C.
author2_role author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Victoria University of Wellington
dc.contributor.author.fl_str_mv Negri, Rogério G. [UNESP]
Frery, Alejandro C.
dc.subject.por.fl_str_mv Pattern analysis
Remote sensing
Unsupervised change detection
topic Pattern analysis
Remote sensing
Unsupervised change detection
description The Earth’s environment is continually changing due to both human and natural factors. Timely identification of the location and kind of change is of paramount importance in several areas of application. Because of that, remote sensing change detection is a topic of great interest. The development of precise change detection methods is a constant challenge. This study introduces a novel unsupervised change detection method based on data clustering and optimization. The proposal is less dependent on radiometric normalization than classical approaches. We carried experiments with remote sensing images and simulated datasets to compare the proposed method with other unsupervised well-known techniques. At its best, the proposal improves by 50% the accuracy concerning the second best technique. Such improvement is most noticeable with uncalibrated data. Experiments with simulated data reveal that the proposal is better than all other compared methods at any practical significance level. The results show the potential of the proposed method.
publishDate 2021
dc.date.none.fl_str_mv 2021-06-25T10:19:49Z
2021-06-25T10:19:49Z
2021-01-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1007/s10044-020-00954-w
Pattern Analysis and Applications.
1433-755X
1433-7541
http://hdl.handle.net/11449/205698
10.1007/s10044-020-00954-w
2-s2.0-85099041428
url http://dx.doi.org/10.1007/s10044-020-00954-w
http://hdl.handle.net/11449/205698
identifier_str_mv Pattern Analysis and Applications.
1433-755X
1433-7541
10.1007/s10044-020-00954-w
2-s2.0-85099041428
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Pattern Analysis and Applications
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129279331926016