Recognition of marine mammal vocalizations in seismic environment
In partnership with Sercel, the thesis concerns the implementation of algorithms for recognizing the sounds emitted by mysticetes (baleen whales). These sounds can be studiedusing passive acoustic monitoring systems. Sercel, through its seismic activities related to oïl exploration, has its own soft...
Main Author: | |
---|---|
Other Authors: | , |
Format: | Thesis |
Language: | French |
Published: |
2018
|
Subjects: | |
Online Access: | http://www.theses.fr/2018IMTA0080/document |
id |
fttriple:oai:gotriple.eu:10670/1.ygflmo |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:10670/1.ygflmo 2023-05-15T15:37:15+02:00 Recognition of marine mammal vocalizations in seismic environment Classification de vocalises de mammifères marins en environnement sismique Guilment, Thomas Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire Pastor, Dominique 2018-06-21 http://www.theses.fr/2018IMTA0080/document fr fre 10670/1.ygflmo http://www.theses.fr/2018IMTA0080/document other Theses.fr Reconnaissance Mammifères marins Sismique Représentations parcimonieuses Apprentissage automatique Classification Marine mammal Seismic environment Sparse representation Machine learning geo manag Thesis https://vocabularies.coar-repositories.org/resource_types/c_46ec/ 2018 fttriple 2023-01-22T16:56:43Z In partnership with Sercel, the thesis concerns the implementation of algorithms for recognizing the sounds emitted by mysticetes (baleen whales). These sounds can be studiedusing passive acoustic monitoring systems. Sercel, through its seismic activities related to oïl exploration, has its own software to detect and locate underwater sound energy sources. The thesis work therefore consists in adding a recognition module to identify if the detected andlocalized energy corresponds to a possible mysticete. Since seismic shooting campaigns areexpensive, the method used must be able to reduce the probability of false alarms, as recognitioncan invalidate detection. The proposed method is based on dictionary learning. It is dynamic, modular, depends on few parameters and is robust to false alarms. An experiment on five types of vocalizations is presented. We obtain an average recall of 92.1% while rejecting 97.3% of the noises (persistent and transient). In addition, a confidence coefficient is associated with each recognition and allows semi-supervised incremental learning to be achieved. Finally, we propose a method capable of managing detection and recognition together. This "multiclassdetector" best respects the constraints of false alarm management and allows several types of vocalizations to be identified at the same time. This method is well adapted to the industrial context for which it is dedicated. It also opens up very promising prospects in the bioacoustic context. En partenariat avec l’entreprise Sercel, la thèse concerne la mise en œuvre d’algorithmes de reconnaissance des sons émis par les mysticètes (baleines à fanons). Cessons peuvent être étudiés grâce aux systèmes de surveillance par acoustique passive. L’entreprise Sercel, par ses activités sismiques liées à la prospection pétrolière, a son propre logiciel pour détecter et localiser les sources d’énergie sonores sous-marines. Le travail de la thèse consiste dès lors à ajouter un module de reconnaissance pour identifier si l'énergie détectée et ... Thesis baleen whales Unknown |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
French |
topic |
Reconnaissance Mammifères marins Sismique Représentations parcimonieuses Apprentissage automatique Classification Marine mammal Seismic environment Sparse representation Machine learning geo manag |
spellingShingle |
Reconnaissance Mammifères marins Sismique Représentations parcimonieuses Apprentissage automatique Classification Marine mammal Seismic environment Sparse representation Machine learning geo manag Guilment, Thomas Recognition of marine mammal vocalizations in seismic environment |
topic_facet |
Reconnaissance Mammifères marins Sismique Représentations parcimonieuses Apprentissage automatique Classification Marine mammal Seismic environment Sparse representation Machine learning geo manag |
description |
In partnership with Sercel, the thesis concerns the implementation of algorithms for recognizing the sounds emitted by mysticetes (baleen whales). These sounds can be studiedusing passive acoustic monitoring systems. Sercel, through its seismic activities related to oïl exploration, has its own software to detect and locate underwater sound energy sources. The thesis work therefore consists in adding a recognition module to identify if the detected andlocalized energy corresponds to a possible mysticete. Since seismic shooting campaigns areexpensive, the method used must be able to reduce the probability of false alarms, as recognitioncan invalidate detection. The proposed method is based on dictionary learning. It is dynamic, modular, depends on few parameters and is robust to false alarms. An experiment on five types of vocalizations is presented. We obtain an average recall of 92.1% while rejecting 97.3% of the noises (persistent and transient). In addition, a confidence coefficient is associated with each recognition and allows semi-supervised incremental learning to be achieved. Finally, we propose a method capable of managing detection and recognition together. This "multiclassdetector" best respects the constraints of false alarm management and allows several types of vocalizations to be identified at the same time. This method is well adapted to the industrial context for which it is dedicated. It also opens up very promising prospects in the bioacoustic context. En partenariat avec l’entreprise Sercel, la thèse concerne la mise en œuvre d’algorithmes de reconnaissance des sons émis par les mysticètes (baleines à fanons). Cessons peuvent être étudiés grâce aux systèmes de surveillance par acoustique passive. L’entreprise Sercel, par ses activités sismiques liées à la prospection pétrolière, a son propre logiciel pour détecter et localiser les sources d’énergie sonores sous-marines. Le travail de la thèse consiste dès lors à ajouter un module de reconnaissance pour identifier si l'énergie détectée et ... |
author2 |
Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire Pastor, Dominique |
format |
Thesis |
author |
Guilment, Thomas |
author_facet |
Guilment, Thomas |
author_sort |
Guilment, Thomas |
title |
Recognition of marine mammal vocalizations in seismic environment |
title_short |
Recognition of marine mammal vocalizations in seismic environment |
title_full |
Recognition of marine mammal vocalizations in seismic environment |
title_fullStr |
Recognition of marine mammal vocalizations in seismic environment |
title_full_unstemmed |
Recognition of marine mammal vocalizations in seismic environment |
title_sort |
recognition of marine mammal vocalizations in seismic environment |
publishDate |
2018 |
url |
http://www.theses.fr/2018IMTA0080/document |
genre |
baleen whales |
genre_facet |
baleen whales |
op_source |
Theses.fr |
op_relation |
10670/1.ygflmo http://www.theses.fr/2018IMTA0080/document |
op_rights |
other |
_version_ |
1766367716598349824 |