A deep neural network for multi-species fish detection using multiple acoustic cameras
Underwater acoustic cameras are high potential devices for many applications in ecology, notably for fisheries management and monitoring. However how to extract such data into high value information without a time-consuming entire dataset reading by an operator is still a challenge. Moreover the ana...
Published in: | Aquatic Ecology |
---|---|
Main Authors: | , , , , |
Other Authors: | , , , , , , , , , , , , , , , , |
Format: | Report |
Language: | English |
Published: |
HAL CCSD
2023
|
Subjects: | |
Online Access: | https://hal.science/hal-03350565 https://hal.science/hal-03350565/document https://hal.science/hal-03350565/file/Manuscript.pdf https://doi.org/10.1007/s10452-023-10004-2 |
id |
ftinstagro:oai:HAL:hal-03350565v1 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Portail HAL Institut Agro |
op_collection_id |
ftinstagro |
language |
English |
topic |
sonar cameras deep learning fisheries management DIDSON convolutional neural network artificial intelligence ARIS [SDE]Environmental Sciences [SDE.BE]Environmental Sciences/Biodiversity and Ecology [SDV.EE.ECO]Life Sciences [q-bio]/Ecology environment/Ecosystems |
spellingShingle |
sonar cameras deep learning fisheries management DIDSON convolutional neural network artificial intelligence ARIS [SDE]Environmental Sciences [SDE.BE]Environmental Sciences/Biodiversity and Ecology [SDV.EE.ECO]Life Sciences [q-bio]/Ecology environment/Ecosystems Fernandez Garcia, Guglielmo Corpetti, Thomas Nevoux, Marie Beaulaton, Laurent Martignac, François A deep neural network for multi-species fish detection using multiple acoustic cameras |
topic_facet |
sonar cameras deep learning fisheries management DIDSON convolutional neural network artificial intelligence ARIS [SDE]Environmental Sciences [SDE.BE]Environmental Sciences/Biodiversity and Ecology [SDV.EE.ECO]Life Sciences [q-bio]/Ecology environment/Ecosystems |
description |
Underwater acoustic cameras are high potential devices for many applications in ecology, notably for fisheries management and monitoring. However how to extract such data into high value information without a time-consuming entire dataset reading by an operator is still a challenge. Moreover the analysis of acoustic imaging, due to its low signal-to-noise ratio, is a perfect training ground for experimenting with new approaches, especially concerning Deep Learning techniques. We present hereby a novel approach that takes advantage of both CNN (Convolutional Neural Network) and classical CV (Computer Vision) techniques, able to detect a generic class "fish" in acoustic video streams. The pipeline pre-treats the acoustic images to extract 2 features, in order to localise the signals and improve the detection performances. To ensure the performances from an ecological point of view, we propose also a two-step validation, one to validate the results of the trainings and one to test the method on a real-world scenario. The YOLOv3-based model was trained with data of fish from multiple species recorded by the two common acoustic cameras, DIDSON and ARIS, including species of high ecological interest, as Atlantic salmon or European eels. The model we developed provides satisfying results detecting almost 80% of fish and minimizing the false positive rate, however the model is much less efficient for eel detections on ARIS videos. The first CNN pipeline for fish monitoring exploiting video data from two models of acoustic cameras satisfies most of the required features. Many challenges are still present, such as the automation of fish species identification through a multiclass model. 1 However the results point a new solution for dealing with complex data, such as sonar data, which can also be reapplied in other cases where the signal-to-noise ratio is a challenge. |
author2 |
Écologie et santé des écosystèmes (ESE) Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-INSTITUT AGRO Agrocampus Ouest Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro) Pôle OFB-INRAE-Institut Agro-UPPA pour la gestion des migrateurs amphihalins dans leur environnement (MIAME) Université de Pau et des Pays de l'Adour (UPPA)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Office français de la biodiversité (OFB)-Institut Agro Rennes Angers Littoral, Environnement, Télédétection, Géomatique (LETG - Rennes) Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG) Université de Caen Normandie (UNICAEN) Normandie Université (NU)-Normandie Université (NU)-Université d'Angers (UA)-École Pratique des Hautes Études (EPHE) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Brest (UBO)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (IGARUN) Université de Nantes (UN)-Université de Nantes (UN)-Université de Caen Normandie (UNICAEN) Université de Nantes (UN)-Université de Nantes (UN) Service conservation et gestion durable des espèces exploitées (OFB SEEX) Direction de la recherche et de l’appui scientifique (OFB - DRAS) Office français de la biodiversité (OFB)-Office français de la biodiversité (OFB) Unité Expérimentale d'Ecologie et d'Ecotoxicologie Aquatique - U3E (Rennes, France) (U3E ) Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE) |
format |
Report |
author |
Fernandez Garcia, Guglielmo Corpetti, Thomas Nevoux, Marie Beaulaton, Laurent Martignac, François |
author_facet |
Fernandez Garcia, Guglielmo Corpetti, Thomas Nevoux, Marie Beaulaton, Laurent Martignac, François |
author_sort |
Fernandez Garcia, Guglielmo |
title |
A deep neural network for multi-species fish detection using multiple acoustic cameras |
title_short |
A deep neural network for multi-species fish detection using multiple acoustic cameras |
title_full |
A deep neural network for multi-species fish detection using multiple acoustic cameras |
title_fullStr |
A deep neural network for multi-species fish detection using multiple acoustic cameras |
title_full_unstemmed |
A deep neural network for multi-species fish detection using multiple acoustic cameras |
title_sort |
deep neural network for multi-species fish detection using multiple acoustic cameras |
publisher |
HAL CCSD |
publishDate |
2023 |
url |
https://hal.science/hal-03350565 https://hal.science/hal-03350565/document https://hal.science/hal-03350565/file/Manuscript.pdf https://doi.org/10.1007/s10452-023-10004-2 |
genre |
Atlantic salmon |
genre_facet |
Atlantic salmon |
op_source |
https://hal.science/hal-03350565 2023 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1007/s10452-023-10004-2 hal-03350565 https://hal.science/hal-03350565 https://hal.science/hal-03350565/document https://hal.science/hal-03350565/file/Manuscript.pdf doi:10.1007/s10452-023-10004-2 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1007/s10452-023-10004-2 |
container_title |
Aquatic Ecology |
_version_ |
1799477233700569088 |
spelling |
ftinstagro:oai:HAL:hal-03350565v1 2024-05-19T07:37:51+00:00 A deep neural network for multi-species fish detection using multiple acoustic cameras Un Réseau Neuronal Profond pour la Détection de Poissons Multi-Espèces Utilisant un Méthode Multi-Caméras Acoustiques Fernandez Garcia, Guglielmo Corpetti, Thomas Nevoux, Marie Beaulaton, Laurent Martignac, François Écologie et santé des écosystèmes (ESE) Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-INSTITUT AGRO Agrocampus Ouest Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro) Pôle OFB-INRAE-Institut Agro-UPPA pour la gestion des migrateurs amphihalins dans leur environnement (MIAME) Université de Pau et des Pays de l'Adour (UPPA)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Office français de la biodiversité (OFB)-Institut Agro Rennes Angers Littoral, Environnement, Télédétection, Géomatique (LETG - Rennes) Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG) Université de Caen Normandie (UNICAEN) Normandie Université (NU)-Normandie Université (NU)-Université d'Angers (UA)-École Pratique des Hautes Études (EPHE) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Brest (UBO)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (IGARUN) Université de Nantes (UN)-Université de Nantes (UN)-Université de Caen Normandie (UNICAEN) Université de Nantes (UN)-Université de Nantes (UN) Service conservation et gestion durable des espèces exploitées (OFB SEEX) Direction de la recherche et de l’appui scientifique (OFB - DRAS) Office français de la biodiversité (OFB)-Office français de la biodiversité (OFB) Unité Expérimentale d'Ecologie et d'Ecotoxicologie Aquatique - U3E (Rennes, France) (U3E ) Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE) 2023-01-20 https://hal.science/hal-03350565 https://hal.science/hal-03350565/document https://hal.science/hal-03350565/file/Manuscript.pdf https://doi.org/10.1007/s10452-023-10004-2 en eng HAL CCSD info:eu-repo/semantics/altIdentifier/doi/10.1007/s10452-023-10004-2 hal-03350565 https://hal.science/hal-03350565 https://hal.science/hal-03350565/document https://hal.science/hal-03350565/file/Manuscript.pdf doi:10.1007/s10452-023-10004-2 info:eu-repo/semantics/OpenAccess https://hal.science/hal-03350565 2023 sonar cameras deep learning fisheries management DIDSON convolutional neural network artificial intelligence ARIS [SDE]Environmental Sciences [SDE.BE]Environmental Sciences/Biodiversity and Ecology [SDV.EE.ECO]Life Sciences [q-bio]/Ecology environment/Ecosystems info:eu-repo/semantics/preprint Preprints, Working Papers, . 2023 ftinstagro https://doi.org/10.1007/s10452-023-10004-2 2024-04-25T17:15:20Z Underwater acoustic cameras are high potential devices for many applications in ecology, notably for fisheries management and monitoring. However how to extract such data into high value information without a time-consuming entire dataset reading by an operator is still a challenge. Moreover the analysis of acoustic imaging, due to its low signal-to-noise ratio, is a perfect training ground for experimenting with new approaches, especially concerning Deep Learning techniques. We present hereby a novel approach that takes advantage of both CNN (Convolutional Neural Network) and classical CV (Computer Vision) techniques, able to detect a generic class "fish" in acoustic video streams. The pipeline pre-treats the acoustic images to extract 2 features, in order to localise the signals and improve the detection performances. To ensure the performances from an ecological point of view, we propose also a two-step validation, one to validate the results of the trainings and one to test the method on a real-world scenario. The YOLOv3-based model was trained with data of fish from multiple species recorded by the two common acoustic cameras, DIDSON and ARIS, including species of high ecological interest, as Atlantic salmon or European eels. The model we developed provides satisfying results detecting almost 80% of fish and minimizing the false positive rate, however the model is much less efficient for eel detections on ARIS videos. The first CNN pipeline for fish monitoring exploiting video data from two models of acoustic cameras satisfies most of the required features. Many challenges are still present, such as the automation of fish species identification through a multiclass model. 1 However the results point a new solution for dealing with complex data, such as sonar data, which can also be reapplied in other cases where the signal-to-noise ratio is a challenge. Report Atlantic salmon Portail HAL Institut Agro Aquatic Ecology |