Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Geolocation and Tracking of Pop-Up Buoys Using ADALM-PLUTO Software-Defined Radio on a BlueBoat Unmanned Surface Vessel

  • Armajach, Joan
  • Carandell, Matias
  • Vega, Carlos de la
  • Río, Joaquín del
  • Aguzzi, Jacopo
  • Masmitja, Ivan
OCEANS 2025, 16-19 June 2025, Brest, France .-- 8 pages, 7 figures, 1 table, Pop-up buoys present a promising solution for obtaining diverse ocean data from stand-alone, seafloor oceanographic platforms without needing to extract them to the surface. Once these pop-up buoys have stored part of the data, they ascend to the surface with the purpose of sending fragments of data via satellite. Using a Software-Defined Radio (SDR) receiver installed on a surface vehicle to capture the GPS messages is a significant step towards the automatization of geolocating the pop-up buoys and tracking their trajectory as they drift. Here we have demonstrated their feasibility and performance in laboratory condition tests and field campaigns. In the future, the implementation of an unmanned vehicle will be crucial to locate and establish direct communication with the pop-up buoy and assemble all stored data without relying on the passage of satellites. Additionally, it could be used as an aid to localise and recover these devices, reducing the time spent in the sea by the researchers and therefore their cost, Project supported by a 2024 Leonardo Grant for Scientific Research and Cultural Creation from the BBVA Foundation (LEO24-1-13125). This work acknowledges the Spanish Ministerio de Ciencia, Innovación y Universidades project PLOME: PLEC2021-007525/AEI/10.13039/501100011033 and Generalitat de Catalunya’s “SARTI-MAR” 2017 SGR 371. The European Union’s H2020 projects: DIGI4ECO, GAP-101112883; SUN-BIO, GAP-101157493; MERLIN, GAP-01189796. IM received financial support from the MCIN/AEI/10.13039/501100011033 and FSE+, grant agreement No RYC2022-038056-I. This work also acknowledges the ’Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S) and the Research Unit Tecnoterra (ICM-CSIC/UPC), Peer reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Capítulo o parte de un libro (BookPart)

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

  • 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
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., This work has been supported by various funding sources and research initiatives. We acknowledge the financial support from grants 2023 INV-2 00044 (position codes 200044TC31 and 200044TC6). Additionally, this research has been funded by the European Commission’s HORIZON-INFRA-2021-SERV-01 program under the iMagine project (grant agreement 101058625). We also recognize the use of the EGI infrastructure with dedicated support from EGI-IFCA-STACK, which contributed to the computational resources required for this study. Furthermore, the researchers wish to acknowledge the support of the Associated Unit Tecnoterra, composed of members from UPC and ICM-CSIC, for their valuable collaboration in this work., Peer Reviewed