Assessing the image concept drift at the OBSEA coastal underwater cabled observatory

The marine science community is engaged in the exploration and monitoring of biodiversity dynamics, with a special interest for understanding the ecosystem functioning and for tracking the growing anthropogenic impacts. The accurate monitoring of marine ecosystems requires the development of innovat...

ver descrição completa

Detalhes bibliográficos
Autores: Ottaviani, Ennio, Francescangeli, Marco, Gjeci, Nikolla, Río Fernández, Joaquín del|||0000-0002-6191-2201, Aguzzi, Jacopo, Marini, Simone
Formato: artículo
Fecha de publicación:2022
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/365750
Acesso em linha:https://hdl.handle.net/2117/365750
https://dx.doi.org/10.3389/fmars.2022.840088
Access Level:acceso abierto
Palavra-chave:Oceanography--Equipment and supplies
Concept drift
automated fish classification
automated fish detection
deep learning
underwater imaging
underwater observing systems
cabled observatories
Oceanografia--Aparells i instruments
Àrees temàtiques de la UPC::Enginyeria civil::Geologia::Oceanografia
id ES_41f2eca7392ca23f4cf0edbba39fcb85
oai_identifier_str oai:upcommons.upc.edu:2117/365750
network_acronym_str ES
network_name_str España
repository_id_str
spelling Assessing the image concept drift at the OBSEA coastal underwater cabled observatoryOttaviani, EnnioFrancescangeli, MarcoGjeci, NikollaRío Fernández, Joaquín del|||0000-0002-6191-2201Aguzzi, JacopoMarini, SimoneOceanography--Equipment and suppliesConcept driftautomated fish classificationautomated fish detectiondeep learningunderwater imagingunderwater observing systemscabled observatoriesOceanografia--Aparells i instrumentsÀrees temàtiques de la UPC::Enginyeria civil::Geologia::OceanografiaThe marine science community is engaged in the exploration and monitoring of biodiversity dynamics, with a special interest for understanding the ecosystem functioning and for tracking the growing anthropogenic impacts. The accurate monitoring of marine ecosystems requires the development of innovative and effective technological solutions to allow a remote and continuous collection of data. Cabled fixed observatories, equipped with camera systems and multiparametric sensors, allow for a non-invasive acquisition of valuable datasets, at a high-frequency rate and for periods extended in time. When large collections of visual data are acquired, the implementation of automated intelligent services is mandatory to automatically extract the relevant biological information from the gathered data. Nevertheless, the automated detection and classification of streamed visual data suffer from the “concept drift” phenomenon, consisting of a drop of performance over the time, mainly caused by the dynamic variation of the acquisition conditions. This work quantifies the degradation of the fish detection and classification performance on an image dataset acquired at the OBSEA cabled video-observatory over a one-year period and finally discusses the methodological solutions needed to implement an effective automated classification service operating in real time.Frontiers Media20222022-04-0720222022-04-12journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/365750https://dx.doi.org/10.3389/fmars.2022.840088reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3657502026-05-27T15:37:01Z
dc.title.none.fl_str_mv Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
title Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
spellingShingle Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
Ottaviani, Ennio
Oceanography--Equipment and supplies
Concept drift
automated fish classification
automated fish detection
deep learning
underwater imaging
underwater observing systems
cabled observatories
Oceanografia--Aparells i instruments
Àrees temàtiques de la UPC::Enginyeria civil::Geologia::Oceanografia
title_short Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
title_full Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
title_fullStr Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
title_full_unstemmed Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
title_sort Assessing the image concept drift at the OBSEA coastal underwater cabled observatory
dc.creator.none.fl_str_mv Ottaviani, Ennio
Francescangeli, Marco
Gjeci, Nikolla
Río Fernández, Joaquín del|||0000-0002-6191-2201
Aguzzi, Jacopo
Marini, Simone
author Ottaviani, Ennio
author_facet Ottaviani, Ennio
Francescangeli, Marco
Gjeci, Nikolla
Río Fernández, Joaquín del|||0000-0002-6191-2201
Aguzzi, Jacopo
Marini, Simone
author_role author
author2 Francescangeli, Marco
Gjeci, Nikolla
Río Fernández, Joaquín del|||0000-0002-6191-2201
Aguzzi, Jacopo
Marini, Simone
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Oceanography--Equipment and supplies
Concept drift
automated fish classification
automated fish detection
deep learning
underwater imaging
underwater observing systems
cabled observatories
Oceanografia--Aparells i instruments
Àrees temàtiques de la UPC::Enginyeria civil::Geologia::Oceanografia
topic Oceanography--Equipment and supplies
Concept drift
automated fish classification
automated fish detection
deep learning
underwater imaging
underwater observing systems
cabled observatories
Oceanografia--Aparells i instruments
Àrees temàtiques de la UPC::Enginyeria civil::Geologia::Oceanografia
description The marine science community is engaged in the exploration and monitoring of biodiversity dynamics, with a special interest for understanding the ecosystem functioning and for tracking the growing anthropogenic impacts. The accurate monitoring of marine ecosystems requires the development of innovative and effective technological solutions to allow a remote and continuous collection of data. Cabled fixed observatories, equipped with camera systems and multiparametric sensors, allow for a non-invasive acquisition of valuable datasets, at a high-frequency rate and for periods extended in time. When large collections of visual data are acquired, the implementation of automated intelligent services is mandatory to automatically extract the relevant biological information from the gathered data. Nevertheless, the automated detection and classification of streamed visual data suffer from the “concept drift” phenomenon, consisting of a drop of performance over the time, mainly caused by the dynamic variation of the acquisition conditions. This work quantifies the degradation of the fish detection and classification performance on an image dataset acquired at the OBSEA cabled video-observatory over a one-year period and finally discusses the methodological solutions needed to implement an effective automated classification service operating in real time.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-04-07
2022
2022-04-12
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/365750
https://dx.doi.org/10.3389/fmars.2022.840088
url https://hdl.handle.net/2117/365750
https://dx.doi.org/10.3389/fmars.2022.840088
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869406889935110144
score 15,300719

Registos relacionados