Here are our current projects in offshore wind farms in order to automatically characterize the marine megafauna species likely to be present on these future wind farms.
Fécamp et courseulles sur Mer (FR)
2020-23 : OWFSOMM Project : Standardization of tools and methods for monitoring marine megafauna at the scale of offshore wind farms
Funding : France Energies Marines, its members and partners, as well as state aid managed by the french National Research Agency under the Investments Program for the Future.
Problem : Demonstrate the technical relevance of digital methods while guaranteeing commensurability with existing data from aerial surveys with on-board observers.
Solution :
L'Avion Jaune acquires very high resolution images.
WIPSEA uses, as part of this project, the neural network developed in the context of the SEMMACAPE project (see project below) to automatically detect and classify the marine megafauna present in the photos corresponding to the visual observations.
Results : Development of an intercalibration methodology between aerial surveys with human observers and those carried out with digital techniques.
Gironde estuary, France
2019-23 : SEMMACAPE project : Monitoring and survey of marine megafauna by automatic characterization in offshore wind farms
Funding : ADEME
Problem : compare detections obtained by the automatic digital systems based on high-resolution aerial photographs with the observations made by observers on board the same aircraft as the camera. Automatically characterize the species of marine megafauna likely to be present on future offshore wind farms in France.
Solution : investigate the capabilities of algorithms based on supervised deep learning and those based on unsupervised learning.
Results : publications expected in 2022
