METHODS article
Front. Mar. Sci.
Sec. Ocean Observation
This article is part of the Research TopicBest Practices in Ocean ObservingView all 90 articles
Squidle+: a collaborative platform to manage, discover and annotate marine imagery
Provisionally accepted
Ariell Friedman1
Jacquomo Monk2
Oscar Pizarro3*
Dhugal John Lindsay4
Elizabeth Oh2
Blair Thornton5
Andrew Gerard Carroll6
Rachel Przeslawski2
Stefan Bernard Williams7- 1Greybits Engineering, Sydney, Australia
- 2University of Tasmania, Hobart, Australia
- 3Norges teknisk-naturvitenskapelige universitet, Trondheim, Norway
- 4Japan Agency for Marine-Earth Science and Technology, Yokosuka, Japan
- 5University of Southampton, Southampton, United Kingdom
- 6Geoscience Australia, Canberra, Australia
- 7The University of Sydney, Sydney, Australia
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The rapid growth of marine imaging has outpaced our ability to efficiently analyse the imagery, creating challenges in data management, collaboration, and standardisation. This paper presents Squidle+, a web-based, collaborative platform for the end-to-end management, delivery, discovery, and annotation of marine imagery. Squidle+ provides a centralised portal and annotation repository while linking to imagery hosted on pre-existing cloud storage, eliminating data transfer and duplication. The system features a user-friendly interface with map-based exploration tools, advanced annotation workflows, and integrated analytics through a comprehensive API back-end. Collaboration is managed through user groups with granular permissions, while integrated QA/QC tools enable cross-validation between human annotators and machine learning (ML) algorithms. A key innovation is a framework to translate between multiple standardised or user-defined annotation vocabularies. This gives users the flexibility to construct data sets that target specific scientific questions and facilitates data reuse, cross-project syntheses, large-scale machine learning training, and broad summaries that can be fed into national-level reporting. Squidle+ has been developed in close collaboration with an active user community and currently contains datasets from several platforms and operators around the world. It is currently the largest known repository of openly accessible georeferenced marine images with associated annotations. Squidle+ streamlines complex workflows and significantly enhances the Findability, Accessibility, Interoperability, and Reusability (FAIR) of marine image data.
Keywords: FAIR (findable accessible interoperable and reusable) principles, Marine imagery data management, Web-based Image Annotation, Collaborative workflows, Machine-learning integration, Vocabulary translation framework, Geospatial exploration (OGC-compliant), Underwater image repository
Received: 31 Jul 2025; Accepted: 17 Nov 2025.
Copyright: © 2025 Friedman, Monk, Pizarro, Lindsay, Oh, Thornton, Carroll, Przeslawski and Williams. 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: Oscar Pizarro, oscar.pizarro@ntnu.no
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.