High-frequency Near-field Physeter macrocephalus Monitoring by Stereo-Autoencoder and 3D Model of Sonar Organ

• Main Authors: Ferrari, Maxence, Glotin, Hervé, Marxer, Ricard, Barchasz, Valentin, Sarano, Véronique, Gies, Valentin, Asch, Mark, Sarano, François
• Other Authors: Laboratoire Amiénois de Mathématique Fondamentale et Appliquée - UMR CNRS 7352 (LAMFA), Université de Picardie Jules Verne (UPJV)-Centre National de la Recherche Scientifique (CNRS), DYNamiques de l’Information (DYNI), Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon) (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Université de Toulon (UTLN), University of Sheffield Sheffield, Longitude 181, Institut des Matériaux, de Microélectronique et des Nanosciences de Provence (IM2NP), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Amiénois de Mathématique Fondamentale et Appliquée (LAMFA), Bureau des Longitudes, PNRIA
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2019
• Subjects: Long Term Survey; 3D Tracking; Tran- sient Analysis; Weak Signal Detection; Abyss Monitoring; Stereo- Autoencoder; Autoencoder; FDTD; Cetacean Survey; Index Terms-Passive Acoustic Monitoring; [SDV.BA]Life Sciences [q-bio]/Animal biology; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation; Physeter macrocephalus; Sperm whale
• Online Access: https://hal.science/hal-02313898; https://hal.science/hal-02313898/document; https://hal.science/hal-02313898/file/Sarano_OCEAN.pdf

International audience Passive acoustics allow us to study large animals and obtain information that could not be gathered through other methods. In this paper we study a set of near-field audiovisual recordings of a sperm whale pod, acquired with a ultra high-frequency and small aperture antenna. We propose a novel kind of autoencoder, a Stereo-Autoencoder, and show how it allows to build acoustic manifolds in order to increase our knowledge regarding the characterization of their vocalizations, and possible acoustic individual signature.