Assessing the Image Concept Drift at the OBSEA Coastal Underwater Cabled Observatory

13 pages, 9 figures, 2 tables.-- Data Availability Statement: The time series of specimen counts per species, obtained through the visual inspection of the image dataset, is provided as a supplementary material (only the images containing at least one specimen are reported). The image datasets analy...

ver descrição completa

Detalhes bibliográficos
Autores: Ottaviani, Ennio, Francescangeli, Marco, Gjeci, Nikolla, Río, Joaquín del, Aguzzi, Jacopo, Marini, Simone
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2022
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositório:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/268712
Acesso em linha:http://hdl.handle.net/10261/268712
Access Level:Acceso aberto
Palavra-chave:Concept drift
Automated fish classification
Automated fish detection
Deep learning
Underwater imaging
Underwater observing systems
Cabled observatories
Descrição
Resumo:13 pages, 9 figures, 2 tables.-- Data Availability Statement: The time series of specimen counts per species, obtained through the visual inspection of the image dataset, is provided as a supplementary material (only the images containing at least one specimen are reported). The image datasets analysed for this study can be accessed by contacting the OBSEA observatory [https://www.obsea.es/] on reasonable request