Simultaneous, vision-based fish instance segmentation, species classification and size regression
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/140144
Título: | Simultaneous, vision-based fish instance segmentation, species classification and size regression |
---|---|
Autor/es: | Climent-Pérez, Pau | Galán Cuenca, Alejandro | Garcia-d’Urso, Nahuel | Saval-Calvo, Marcelo | Azorin-Lopez, Jorge | Fuster-Guilló, Andrés |
Grupo/s de investigación o GITE: | Entornos Inteligentes para un Envejecimiento Activo y Saludable (AmI4AHA) | Informática Industrial y Redes de Computadores | Arquitecturas Inteligentes Aplicadas (AIA) |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Tecnología Informática y Computación |
Palabras clave: | Fish size estimation | Species recognition | Segmentation | Computer vision | Deep learning |
Fecha de publicación: | 24-ene-2024 |
Editor: | PeerJ |
Cita bibliográfica: | Climent-Perez P, Galán-Cuenca A, Garcia-d’Urso NE, Saval-Calvo M, Azorin-Lopez J, Fuster-Guillo A. 2024. Simultaneous, vision-based fish instance segmentation, species classification and size regression. PeerJ Computer Science 10:e1770 https://doi.org/10.7717/peerj-cs.1770 |
Resumen: | Overexploitation of fisheries is a worldwide problem, which is leading to a large loss of diversity, and affects human communities indirectly through the loss of traditional jobs, cultural heritage, etc. To address this issue, governments have started accumulating data on fishing activities, to determine biomass extraction rates, and fisheries status. However, these data are often estimated from small samplings, which can lead to partially inaccurate assessments. Fishing can also benefit of the digitization process that many industries are undergoing. Wholesale fish markets, where vessels disembark, can be the point of contact to retrieve valuable information on biomass extraction rates, and can do so automatically. Fine-grained knowledge about the fish species, quantities, sizes, etc. that are caught can be therefore very valuable to all stakeholders, and particularly decision-makers regarding fisheries conservation, sustainable, and long-term exploitation. In this regard, this article presents a full workflow for fish instance segmentation, species classification, and size estimation from uncalibrated images of fish trays at the fish market, in order to automate information extraction that can be helpful in such scenarios. Our results on fish instance segmentation and species classification show an overall mean average precision (mAP) at 50% intersection-over-union (IoU) of 70.42%, while fish size estimation shows a mean average error (MAE) of only 1.27 cm. |
Patrocinador/es: | This work was developed with the collaboration of the Biodiversity Foundation (Spanish Ministry for the Ecological Transition and the Demographic Challenge), through the Pleamar Programme, co-financed by the European Maritime and Fisheries Fund (EMFF) Deepfish/Deepfish 2 projects. The European Regional Development Fund (ERDF) and MCIN/AEI/10.13039/501100011033 supported this research under the “CHAN-TWIN” project (grant TED2021-130890B-C21) and the HORIZON-MSCA-2021-SE-0 action number: 101086387, REMARKABLE, Rural Environmental Monitoring via ultra wide-ARea networKs And distriButed federated Learning. |
URI: | http://hdl.handle.net/10045/140144 |
ISSN: | 2376-5992 |
DOI: | 10.7717/peerj-cs.1770 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2024 Climent-Perez et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited. |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.7717/peerj-cs.1770 |
Aparece en las colecciones: | INV - AIA - Artículos de Revistas INV - AmI4AHA - Artículos de Revistas Investigaciones financiadas por la UE INV - I2RC - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Climent-Perez_etal_2024_PeerJComputSci.pdf | 41,55 MB | Adobe PDF | Abrir Vista previa | |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.