Active Acoustic Signature Extraction by Machine Learning Data Analysis for Underwater Fish Counters

Gabriel Vasile (1) , Alexandre Girard (2) , Guy d'Urso (2) , Eric de Oliveira (2) , Franck Hieramente (3) , Olivier Philippe (3)

1 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
2 EDF R&D LNHE - Laboratoire National d’Hydraulique et Environnement
3 OSEAN S.A.S [Le Pradet]

This paper illustrates our recent advances in terms of supervised classification of different acoustics signatures employed for fish monitoring by the ACOUEAU active ultrasound system. The obtained results are analyzed, both qualitatively and quantitatively, by taking into consideration five target types.

Mots clés: underwater acoustics; fish classification; machine learning

Domaines: Traitement du signal et de l'image [eess.SP]

Gabriel Vasile, Alexandre Girard, Guy d'Urso, Eric de Oliveira, Franck Hieramente, et al.. Active Acoustic Signature Extraction by Machine Learning Data Analysis for Underwater Fish Counters. OCEANS 2020 - OCEANS '20 MTS/IEEE, Oct 2020, Gulf Coast, United States. ⟨10.1109/IEEECONF38699.2020.9389105⟩. ⟨hal-03004372⟩