Novelty detection in UAV images to identify emerging threats in eucalyptus crops
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.compag.2022.106901 http://hdl.handle.net/11449/223751 |
Resumo: | Supervised learning-based methods can identify crop threats in the visual data collected by an Unmanned Aerial Vehicle (UAV). However, as these methods induce classification models from a finite set of a priori known classes, they cannot recognize new patterns emerging in visual data to be classified. In agricultural environments, these patterns may appear over time, so that those related to diseases/pests should be addressed by the classifier timely. This study investigates an extension of a semi-supervised classification algorithm to identify new classes of threats appearing in UAV visual data. To do so, the algorithm aggregates information from clusters with Support Vector Machine (SVM) outcomes operating on the unlabeled (target) data. From an iterative active learning procedure, the classification model is then fed back to learn a new class. Experimental results showed that our algorithm can discover a new threat, named Ceratocystis wilt, in Eucalyptus plantations even with labeled data scarcity and class imbalance. Also, even this new class being the minority one, its error rate was reduced to almost zero in few iterations on a tested dataset. This is due to the adopted Entropy and Density-based Selection approach, which explored the new class better than an SVM Margin Sampling baseline. When operating on VGGNet-16 deep features, our algorithm achieved accuracies between 92% and 97% being slightly better than those results based on hand-crafted features. |
id |
UNSP_5046aa88dfb18801b86f919e15fb56b8 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/223751 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Novelty detection in UAV images to identify emerging threats in eucalyptus cropsActive learningNew threats classificationNovelty detectionSemi-supervised learningSupervised learning-based methods can identify crop threats in the visual data collected by an Unmanned Aerial Vehicle (UAV). However, as these methods induce classification models from a finite set of a priori known classes, they cannot recognize new patterns emerging in visual data to be classified. In agricultural environments, these patterns may appear over time, so that those related to diseases/pests should be addressed by the classifier timely. This study investigates an extension of a semi-supervised classification algorithm to identify new classes of threats appearing in UAV visual data. To do so, the algorithm aggregates information from clusters with Support Vector Machine (SVM) outcomes operating on the unlabeled (target) data. From an iterative active learning procedure, the classification model is then fed back to learn a new class. Experimental results showed that our algorithm can discover a new threat, named Ceratocystis wilt, in Eucalyptus plantations even with labeled data scarcity and class imbalance. Also, even this new class being the minority one, its error rate was reduced to almost zero in few iterations on a tested dataset. This is due to the adopted Entropy and Density-based Selection approach, which explored the new class better than an SVM Margin Sampling baseline. When operating on VGGNet-16 deep features, our algorithm achieved accuracies between 92% and 97% being slightly better than those results based on hand-crafted features.Biosystems Engineering Department School of Sciences and Engineering São Paulo State University (UNESP), SPDepartment of Information Systems Faculty of Computing Federal University of Uberlândia (UFU), MGBiosystems Engineering Department School of Sciences and Engineering São Paulo State University (UNESP), SPUniversidade Estadual Paulista (UNESP)Universidade Federal de Uberlândia (UFU)Coletta, Luiz F.S. [UNESP]de Almeida, Douglas C. [UNESP]Souza, Jefferson R.Manzione, Rodrigo L. [UNESP]2022-04-28T19:52:52Z2022-04-28T19:52:52Z2022-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.compag.2022.106901Computers and Electronics in Agriculture, v. 196.0168-1699http://hdl.handle.net/11449/22375110.1016/j.compag.2022.1069012-s2.0-85127470718Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengComputers and Electronics in Agricultureinfo:eu-repo/semantics/openAccess2022-04-28T19:52:52Zoai:repositorio.unesp.br:11449/223751Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:57:42.656828Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
title |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
spellingShingle |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops Coletta, Luiz F.S. [UNESP] Active learning New threats classification Novelty detection Semi-supervised learning |
title_short |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
title_full |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
title_fullStr |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
title_full_unstemmed |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
title_sort |
Novelty detection in UAV images to identify emerging threats in eucalyptus crops |
author |
Coletta, Luiz F.S. [UNESP] |
author_facet |
Coletta, Luiz F.S. [UNESP] de Almeida, Douglas C. [UNESP] Souza, Jefferson R. Manzione, Rodrigo L. [UNESP] |
author_role |
author |
author2 |
de Almeida, Douglas C. [UNESP] Souza, Jefferson R. Manzione, Rodrigo L. [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade Federal de Uberlândia (UFU) |
dc.contributor.author.fl_str_mv |
Coletta, Luiz F.S. [UNESP] de Almeida, Douglas C. [UNESP] Souza, Jefferson R. Manzione, Rodrigo L. [UNESP] |
dc.subject.por.fl_str_mv |
Active learning New threats classification Novelty detection Semi-supervised learning |
topic |
Active learning New threats classification Novelty detection Semi-supervised learning |
description |
Supervised learning-based methods can identify crop threats in the visual data collected by an Unmanned Aerial Vehicle (UAV). However, as these methods induce classification models from a finite set of a priori known classes, they cannot recognize new patterns emerging in visual data to be classified. In agricultural environments, these patterns may appear over time, so that those related to diseases/pests should be addressed by the classifier timely. This study investigates an extension of a semi-supervised classification algorithm to identify new classes of threats appearing in UAV visual data. To do so, the algorithm aggregates information from clusters with Support Vector Machine (SVM) outcomes operating on the unlabeled (target) data. From an iterative active learning procedure, the classification model is then fed back to learn a new class. Experimental results showed that our algorithm can discover a new threat, named Ceratocystis wilt, in Eucalyptus plantations even with labeled data scarcity and class imbalance. Also, even this new class being the minority one, its error rate was reduced to almost zero in few iterations on a tested dataset. This is due to the adopted Entropy and Density-based Selection approach, which explored the new class better than an SVM Margin Sampling baseline. When operating on VGGNet-16 deep features, our algorithm achieved accuracies between 92% and 97% being slightly better than those results based on hand-crafted features. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-04-28T19:52:52Z 2022-04-28T19:52:52Z 2022-05-01 |
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/10.1016/j.compag.2022.106901 Computers and Electronics in Agriculture, v. 196. 0168-1699 http://hdl.handle.net/11449/223751 10.1016/j.compag.2022.106901 2-s2.0-85127470718 |
url |
http://dx.doi.org/10.1016/j.compag.2022.106901 http://hdl.handle.net/11449/223751 |
identifier_str_mv |
Computers and Electronics in Agriculture, v. 196. 0168-1699 10.1016/j.compag.2022.106901 2-s2.0-85127470718 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Computers and Electronics in Agriculture |
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_ |
1808129003903516672 |