94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Mar. Sci.
Sec. Marine Fisheries, Aquaculture and Living Resources
Volume 12 - 2025 | doi: 10.3389/fmars.2025.1525524
Automatic deep learning-based pipeline for Mediterranean fish segmentation
Provisionally accepted- University of the Balearic Islands, Palma de Mallorca, Spain
Climate change and human activities are altering the Mediterranean marine biodiversity. Monitoring these alterations over time is crucial for assessing the health of coastal environments and preserving local species. However, this monitoring process is resource-intensive, requiring taxonomic experts and significant amounts of time. Recently, deep learning approaches have attempted to automate the detection and monitoring of fish species of biological and commercial interest. This work presents an automated pipeline to automatically detect, segment and track endemic fish species using YOLOv8 and its integration into an underwater stereo vision system capable of performing online inference and storing only relevant data.
Keywords: deep learning, Instance segmentation, Fish classification, Mediterranean fish, Ecosystem monitoring
Received: 11 Nov 2024; Accepted: 24 Feb 2025.
Copyright: © 2025 Muntaner, Nadal-Martinez, Martin and González Cid. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Caterina Muntaner, University of the Balearic Islands, Palma de Mallorca, Spain
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.