Assessing benthic marine habitats colonized with posidonia oceanica using autonomous marine robots and deep learning: a Eurofleets campaign
Assessing benthic marine habitats colonized with posidonia oceanica using autonomous marine robots and deep learning: a Eurofleets campaign
This paper presents a methodology for observing and analyzing marine ecosystems using images gathered from autonomous marine vehicles. Visual data is composed in photo-mosaics and classified using machine learning algorithms. The approach expands existing solutions, enabling extended monitoring in time, space, and depth. Imagery was collected during a field campaign in the Spanish marine and terrestrial protected area of Cabrera, Balearic Islands, colonized by the endemic seagrass species Posidonia oceanica (Po). The operations were performed using three distinct platforms, an Autonomous Underwater Vehicle (AUV), an Autonomous Surface Vehicle (ASV) and a Lagrangian Drifter (LD). Results are compared to prior habitat maps to assess seagrass meadow distribution. The proposed solution can be scaled and adapted to other locations and species, considering limitations in data storage and battery endurance.
Assessment of marine ecosystems, Autonomous marine vehicles, Computer vision, Convolutional neural networks, Lagrangian drifters, Seagrass
Massot-Campos, Miquel
a55d7b32-c097-4adf-9483-16bbf07f9120
Bonin-Font, Francisco
c5618f01-7ab3-440c-9551-f2db395d82c3
Guerrero-Font, Eric
6e4ed4c6-59b8-4d11-9c3b-0acaaa9dd3a5
Martorell-Torres, Antoni
063e0f40-785c-490a-82d9-7238a1e7fe34
Abadal, Miguel Martin
632e230d-31d4-446b-bafc-7c0b53f4c125
Muntaner-Gonzalez, Caterina
0da4869e-42e8-457c-aa12-ee79fcba1267
Nordfeldt-Fiol, Bo Miquel
eb1ad5e1-0d27-4d7c-b3bf-e6ec1877b153
Oliver-Codina, Gabriel
99a9b816-4f5d-4724-8525-aa7c45fb0d3d
Cappelletto, Jose
a6620d58-0abe-4f9d-9fd9-9ac474de9230
Thornton, Blair
8293beb5-c083-47e3-b5f0-d9c3cee14be9
30 September 2023
Massot-Campos, Miquel
a55d7b32-c097-4adf-9483-16bbf07f9120
Bonin-Font, Francisco
c5618f01-7ab3-440c-9551-f2db395d82c3
Guerrero-Font, Eric
6e4ed4c6-59b8-4d11-9c3b-0acaaa9dd3a5
Martorell-Torres, Antoni
063e0f40-785c-490a-82d9-7238a1e7fe34
Abadal, Miguel Martin
632e230d-31d4-446b-bafc-7c0b53f4c125
Muntaner-Gonzalez, Caterina
0da4869e-42e8-457c-aa12-ee79fcba1267
Nordfeldt-Fiol, Bo Miquel
eb1ad5e1-0d27-4d7c-b3bf-e6ec1877b153
Oliver-Codina, Gabriel
99a9b816-4f5d-4724-8525-aa7c45fb0d3d
Cappelletto, Jose
a6620d58-0abe-4f9d-9fd9-9ac474de9230
Thornton, Blair
8293beb5-c083-47e3-b5f0-d9c3cee14be9
Massot-Campos, Miquel, Bonin-Font, Francisco, Guerrero-Font, Eric, Martorell-Torres, Antoni, Abadal, Miguel Martin, Muntaner-Gonzalez, Caterina, Nordfeldt-Fiol, Bo Miquel, Oliver-Codina, Gabriel, Cappelletto, Jose and Thornton, Blair
(2023)
Assessing benthic marine habitats colonized with posidonia oceanica using autonomous marine robots and deep learning: a Eurofleets campaign.
Estuarine, Coastal and Shelf Science, 291, [108438].
(doi:10.1016/j.ecss.2023.108438).
Abstract
This paper presents a methodology for observing and analyzing marine ecosystems using images gathered from autonomous marine vehicles. Visual data is composed in photo-mosaics and classified using machine learning algorithms. The approach expands existing solutions, enabling extended monitoring in time, space, and depth. Imagery was collected during a field campaign in the Spanish marine and terrestrial protected area of Cabrera, Balearic Islands, colonized by the endemic seagrass species Posidonia oceanica (Po). The operations were performed using three distinct platforms, an Autonomous Underwater Vehicle (AUV), an Autonomous Surface Vehicle (ASV) and a Lagrangian Drifter (LD). Results are compared to prior habitat maps to assess seagrass meadow distribution. The proposed solution can be scaled and adapted to other locations and species, considering limitations in data storage and battery endurance.
Text
1-s2.0-S0272771423002287-main
- Version of Record
More information
In preparation date: 22 January 2023
Accepted/In Press date: 14 July 2023
e-pub ahead of print date: 20 July 2023
Published date: 30 September 2023
Additional Information:
Funding Information:
RV SOCIB ship-time was provided free of charge for the GRASSMAP survey, as part of the Eurofleets+ project which received funding from the European Union H2020 Research and Innovation Program under grant agreement No. 824077 .
Publisher Copyright:
© 2023 The Author(s)
Keywords:
Assessment of marine ecosystems, Autonomous marine vehicles, Computer vision, Convolutional neural networks, Lagrangian drifters, Seagrass
Identifiers
Local EPrints ID: 480681
URI: http://eprints.soton.ac.uk/id/eprint/480681
ISSN: 0272-7714
PURE UUID: a8d4abeb-9de3-4b65-a4b7-39f21dc126db
Catalogue record
Date deposited: 08 Aug 2023 16:45
Last modified: 18 Mar 2024 03:50
Export record
Altmetrics
Contributors
Author:
Francisco Bonin-Font
Author:
Eric Guerrero-Font
Author:
Antoni Martorell-Torres
Author:
Miguel Martin Abadal
Author:
Caterina Muntaner-Gonzalez
Author:
Bo Miquel Nordfeldt-Fiol
Author:
Gabriel Oliver-Codina
Author:
Jose Cappelletto
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
