{"authors":[{"id":null,"fullName":"Prat Bayarri, Oriol","name":"Oriol","surname":"Prat Bayarri","rank":1,"pid":null},{"id":null,"fullName":"Baños Castelló, Pol","name":"Pol","surname":"Baños Castelló","rank":2,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-0780-3255"},"provenance":null}},{"id":null,"fullName":"Martínez Padró, Enoc","name":"Enoc","surname":"Martínez Padró","rank":3,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-1233-7105"},"provenance":null}},{"id":null,"fullName":"Francescangeli, Marco","name":"Marco","surname":"Francescangeli","rank":4,"pid":null},{"id":null,"fullName":"Toma, Daniel","name":"Daniel","surname":"Toma","rank":5,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-0472-1190"},"provenance":null}},{"id":null,"fullName":"Carandell Widmer, Matias","name":"Matias","surname":"Carandell Widmer","rank":6,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-0559-4453"},"provenance":null}},{"id":null,"fullName":"Prat Farran, Joana d'Arc","name":"Joana D. Arc","surname":"Prat Farran","rank":7,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-7628-487x"},"provenance":null}},{"id":null,"fullName":"Río Fernández, Joaquín del","name":"Joaquín Del","surname":"Río Fernández","rank":8,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-6191-2201"},"provenance":null}}],"openAccessColor":"hybrid","publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"ES","label":"Spain","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"Artificial intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"Object detection"},"provenance":null},{"subject":{"scheme":"keyword","value":"Fish detection"},"provenance":null},{"subject":{"scheme":"keyword","value":"Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial"},"provenance":null},{"subject":{"scheme":"keyword","value":"Deep learning"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"AI-assisted labeling"},"provenance":null},{"subject":{"scheme":"keyword","value":"Marine ecosystem monitoring"},"provenance":null},{"subject":{"scheme":"keyword","value":"Àrees temàtiques de la UPC::Enginyeria electrònica::Instrumentació i mesura"},"provenance":null},{"subject":{"scheme":"keyword","value":"Ecological data analysis"},"provenance":null},{"subject":{"scheme":"keyword","value":"Underwater imagery"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine learning"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"YOLO"},"provenance":null},{"subject":{"scheme":"keyword","value":"Convolutional neural networks"},"provenance":null},{"subject":{"scheme":"keyword","value":"Marine species classification"},"provenance":null}],"mainTitle":"Deep Learning for Automated Fish Detection in Underwater Images: A Tool for Sustainable Marine Ecosystem Monitoring","subTitle":null,"descriptions":["<jats:p>Deep learning has emerged as a powerful tool for automated object detection, offering unprecedented speed and accuracy in analyzing complex visual data. In the context of marine ecosystem monitoring, convolutional neural networks (CNNs), particularly YOLO-based architectures, have demonstrated remarkable efficiency in detecting and classifying fish species in underwater imagery. Traditional fish identification methods rely on manual annotation, which is both time-consuming and prone to inconsistencies. By implementing a semi-automated labeling approach, where human experts refine AI-generated predictions, the annotation process can be streamlined while ensuring taxonomic precision. A key aspect of this research is the creation of a comprehensive training guide that optimizes the model’s performance by detailing best practices in dataset preparation, annotation techniques, hyperparameter tuning, and augmentation strategies. Using a dataset derived from the OBSEA marine observatory, results indicate that the YOLO extra-large model, trained with a small learning rate and high-resolution images, achieves optimal performance in fish identification. The findings underscore the potential of AI-assisted methodologies in ecological research, offering a scalable and efficient alternative to manual annotation for sustainable marine biodiversity monitoring.</jats:p>"],"publicationDate":"2025-07-21","publisher":"IntechOpen","embargoEndDate":null,"sources":["Crossref","Artificial Intelligence ISBN: 9781836352532","reponame:UPCommons. Portal del coneixement obert de la UPC","instname:Universitat Politècnica de Catalunya (UPC)"],"formats":["application/pdf"],"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":null,"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::3d1e7fb2d214df992f310c259be35963","originalIds":["10.5772/intechopen.1011280","50|doiboost____|3d1e7fb2d214df992f310c259be35963","50|RECOLECTA___::35c8592274921205d8fbe67aaba7b7d1","oai:dnet:upcommonspor::959c1f964be6c6d760e54b6cadbc56af","oai:upcommons.upc.edu:2117/439139","50|od______3484::959c1f964be6c6d760e54b6cadbc56af"],"pids":[{"scheme":"doi","value":"10.5772/intechopen.1011280"},{"scheme":"handle","value":"2117/439139"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":1.0,"influence":2.3178888E-9,"popularity":3.0353307E-9,"impulse":1.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C5"}},"projects":[{"id":"corda_____he::9564b89d92500185b2be987c5937d0a2","code":"101112883","acronym":"DIGI4ECO","title":"Digital Twin-sustained 4D ecological monitoring of restoration in fishery depleted areas","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101112883"}]},{"id":"corda_____he::e82ffe09e25f376dfd068deb21a7ba6e","code":"101094924","acronym":"ANERIS","title":"operAtional seNsing lifE technologies for maRIne ecosystemS","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101094924"}]},{"id":"corda_____he::cee20577a3cf295391e596e40621449f","code":"101058625","acronym":"iMagine","title":"Imaging data and services for aquatic science","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101058625"}]}],"organizations":[{"legalName":"Universitat Polite`cnica de Catalunya","acronym":"Universitat Polite`cnica de Catalunya","id":"pending_org_::02a082f2d3b44e86583dc0461f22e653","pids":null},{"legalName":"Marche Polytechnic University","acronym":"Marche Polytechnic University","id":"openorgs____::c40decc21f2dc88fc55f9253536de4f5","pids":[{"scheme":"ROR","value":"https://ror.org/00x69rs40"},{"scheme":"FundRef","value":"501100005758"},{"scheme":"OrgReg","value":"IT0001"},{"scheme":"mag_id","value":"122534668"},{"scheme":"ISNI","value":"0000000110173210"},{"scheme":"fundref","value":"501100005758"},{"scheme":"GRID","value":"grid.7010.6"},{"scheme":"OrgRef","value":"4651007"},{"scheme":"PIC","value":"999866689"},{"scheme":"Wikidata","value":"Q1084409"},{"scheme":"wikidata","value":"Q1084409"}]},{"legalName":"Universitat Politècnica de Catalunya","acronym":"UPC","id":"openorgs____::97dd3670a610655bd733fcf83d0eed4d","pids":[{"scheme":"OrgReg","value":"ES0020"},{"scheme":"fundref","value":"501100014374"},{"scheme":"OrgRef","value":"63871"},{"scheme":"mag_id","value":"9617848"},{"scheme":"FundRef","value":"501100014374"},{"scheme":"ISNI","value":"000000041937028X"},{"scheme":"ROR","value":"https://ror.org/03mb6wj31"},{"scheme":"PIC","value":"999976202"},{"scheme":"wikidata","value":"Q1640731"},{"scheme":"GRID","value":"grid.6835.8"},{"scheme":"Wikidata","value":"Q1640731"}]},{"legalName":"Universitat Polit?cnica de Catalunya","acronym":"Universitat Polit?cnica de Catalunya","id":"pending_org_::04c48928af1d147d20064809e815b171","pids":null}],"communities":[{"code":"nbfc","label":"Italian National Biodiversity Future Center","provenance":null},{"code":"eu-conexus","label":"European University for Smart Urban Coastal Sustainability","provenance":null},{"code":"lifewatch-eric","label":"LifeWatch ERIC","provenance":null},{"code":"egi","label":"EGI : advanced computing for research","provenance":null}],"collectedFrom":[{"key":"openaire____::4cb2a3eb94033446c37331f60fad0847","value":"Recolector de Ciencia Abierta, RECOLECTA"},{"key":"opendoar____::966b6dfb6b0819cc10644bea3115cf20","value":"UPCommons. Portal del coneixement obert de la UPC"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}],"instances":[{"pids":[{"scheme":"doi","value":"10.5772/intechopen.1011280"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"hybrid"},"type":"Part of book or chapter of book","urls":["https://doi.org/10.5772/intechopen.1011280"],"publicationDate":"2025-07-21","refereed":"peerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"handle","value":"2117/439139"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.5772/intechopen.1011280"},{"scheme":"doi","value":"10.13039/501100000780he101058625imagingdataandservicesforaquaticscience"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Part of book or chapter of book","urls":["https://hdl.handle.net/2117/439139","https://dx.doi.org/10.5772/intechopen.1011280"],"publicationDate":"2025-01-01","refereed":"peerReviewed","hostedBy":{"key":"openaire____::4cb2a3eb94033446c37331f60fad0847","value":"Recolector de Ciencia Abierta, RECOLECTA"},"collectedFrom":{"key":"openaire____::4cb2a3eb94033446c37331f60fad0847","value":"Recolector de Ciencia Abierta, RECOLECTA"}},{"pids":[{"scheme":"handle","value":"2117/439139"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.5772/intechopen.1011280"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Part of book or chapter of book","urls":["https://hdl.handle.net/2117/439139","https://doi.org/10.5772/intechopen.1011280"],"publicationDate":"2025-07-21","refereed":"peerReviewed","hostedBy":{"key":"opendoar____::966b6dfb6b0819cc10644bea3115cf20","value":"UPCommons. Portal del coneixement obert de la UPC"},"collectedFrom":{"key":"opendoar____::966b6dfb6b0819cc10644bea3115cf20","value":"UPCommons. Portal del coneixement obert de la UPC"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::9564b89d92500185b2be987c5937d0a2","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk:repository","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"Digital Twin-sustained 4D ecological monitoring of restoration in fishery depleted areas","code":"101112883","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-IA","description":"HORIZON Innovation Actions","name":"HORIZON-IA"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2024-03-01","endDate":"2028-02-29"},{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::e82ffe09e25f376dfd068deb21a7ba6e","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk:repository","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"operAtional seNsing lifE technologies for maRIne ecosystemS","code":"101094924","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-RIA","description":"HORIZON  Research and Innovation Actions","name":"HORIZON-RIA"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2023-01-01","endDate":"2026-12-31"},{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::cee20577a3cf295391e596e40621449f","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk:repository","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"Imaging data and services for aquatic science","code":"101058625","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-RIA","description":"HORIZON  Research and Innovation Actions","name":"HORIZON-RIA"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2022-09-01","endDate":"2025-08-31"}],"otherTitles":null,"inDiamondJournal":false,"green":true,"isGreen":true,"isInDiamondJournal":false}