Deep learning for automated fish detection in underwater images: a tool for sustainable marine ecosystem monitoring

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 remar...

ver descrição completa

Detalhes bibliográficos
Autores: Prat Bayarri, Oriol, Baños Castelló, Pol|||0000-0003-0780-3255, Martínez Padró, Enoc|||0000-0003-1233-7105, Francescangeli, Marco, Toma, Daniel|||0000-0003-0472-1190, Carandell Widmer, Matias|||0000-0003-0559-4453, Prat Farran, Joana d'Arc|||0000-0001-7628-487X, Río Fernández, Joaquín del|||0000-0002-6191-2201
Formato: capítulo de livro
Fecha de publicación:2025
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:2117/439139
Acesso em linha:https://hdl.handle.net/2117/439139
https://dx.doi.org/10.5772/intechopen.1011280
Access Level:acceso abierto
Palavra-chave:Deep learning
Fish detection
YOLO
Underwater imagery
AI-assisted labeling
Marine ecosystem monitoring
Convolutional neural networks
Object detection
Machine learning
Ecological data analysis
Marine species classification
Artificial intelligence
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Àrees temàtiques de la UPC::Enginyeria electrònica::Instrumentació i mesura
Descrição
Resumo: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.