PLOME: Platform for Long-lasting Observation of Marine Ecosystems

DESCRIPTION

PLOME (plomeproject.es) is a multidisciplinary project leaded by the CIRS (Underwater Vision and Robotics Research Center) of the UdG (University of Girona) and it proposes a spatially adaptive, non-invasive, modular platform of independent and wirelessly connected benthic stations and AUVs to intelligently observe, monitor and map marine ecosystems, during long-lasting periods with real-time supervision. The proposal brings together elements that can be effectively developed with current technology, to provide a solution to the problem of marine observation that is technologically and economically realistic in the following decade. Moreover, it is scalable in terms of cost and required resources for marine ecosystems’ observation. PLOME aims at creating a monitoring solution that has a simple deployment and is easy-to-move from an experimental site to another, without any cable installation, for coastal and deep-water environments. Stations will provide continuous and intensive temporal observation, while AUVs will be able to provide such intensive measurement at spatial level. Each system will be powered with self-contained electric batteries, allowing a platform duration between one week to one month. AUVs will typically be docked in standby mode, allowing wireless data transmission and battery recharging for various missions. AUVs will be able to undock and perform intelligent trajectories to explore an area. Stations and AUVs will cooperate between them through acoustic or visual light communications. The platform as a whole will acquire biological, geochemical and oceanographic data from a diverse set of sensors, including acoustic and optic cameras. Some information will be processed in real-time, with advanced data analysis and deep learning techniques. Metadata information will be spread over the platform and transmitted in real-time to the surface where a USV connects the platform to the shore using aerial communications. Unattended operation will also be possible with innovative pop-up buoys that will be recorded with relevant data and will be freely released to the surface to send the information. Complex ecological indicators will be computed from the collected data, by applying advanced computer vision techniques to classify, count and size individuals in video images and to generate multimodal maps of the seabed. These indicators will be processed in an automated data treatment pipeline to enable a multiparametric analysis and derive cause-effect relationships between biological variables and the habitat conditioning. The overall objective of the PLOME project is to design, develop and validate several key aspects that will enable the proposed concept. To that end, the work has been divided into highly interdisciplinary work packages that can be tackled only through the summoning of different robotic expertise, engineering, data analysis, and fishery-ecology management. The project aims to validate the different developments and the overall concept in three proof-of-concept consortium experiments: 1) in a coastal environment; 2) in a deep marine protected area; and 3) during one-week in the OBSEA cabled observatory. Expected outcomes involve the development of new underwater technologies, the contribution to existing EU directives and strategies for habitat management and restoration, the knowledge transfer to existing EU monitoring infrastructure, and the potential to become a monitoring solution to advise stakeholders and policy makers in achieving clean, healthy and productive seas. PARTNERS: UdG, UPC, UIB, ICM-CSIC, IQUA-Robotics, UPM.

PUBLICATIONS

A. Burguera. Combining Progressive Hierarchical Image Encoding and YOLO to Detect Fish in their Natural Habitat. In 19th International Conference on Computer Vision Theory and Applications (VISAPP), Rome, pp. 333-340, 2024.

R. Fos, A. Burguera. Using Deep Neural Networks to Detect and Track Fish in Underwater Video Sequences. In MTS/IEEE Oceans conference, Limerick (Ireland), 2023.

C. Muntaner, B. M. Nordfeldt-Fiol, M. Martín, A. Martorell, F. Bonin-Font, F. Molina, R. Marín, G. Oliver, P. J. Sanz. Towards Underwater Robust Image Transmission Using Acoustic Communications. In IEEE Oceans, 2023.

A. Burguera. Hierarchical Color Encoding for Progressive Image Transmission in Underwater Environments. In IEEE Robotics and Automation Letters , IEEE, IEEE, vol. 8, no. 5, pp. 2970-2975, May, 2023.

A. Burguera, F. Bonin-Font. Progressive Hierarchical Encoding for Image Transmission in Underwater Environments. In Oceans, Hampton Roads (USA, Virtual), 2022.

A. Burguera. A Loop Selection Front-end for Underwater Visual GraphSLAM. In Oceans, Hampton Roads (USA, Virtual), 2022.


Uso de cookies

Este sitio web utiliza cookies para que usted tenga la mejor experiencia de usuario. Si continúa navegando está dando su consentimiento para la aceptación de las mencionadas cookies y la aceptación de nuestra política de cookies, pinche el enlace para mayor información.

ACEPTAR
Aviso de cookies