Automatic Coral Detection with YOLO: A Deep Learning Approach for Efficient and Accurate Coral Reef Monitoring
Younes Ouassine
(1)
,
Jihad Zahir
(1)
,
Noël Conruyt
(2)
,
Mohsen Kayal
(3)
,
Philippe A Martin
(2)
,
Eric Chenin
(4)
,
Lionel Bigot
(3)
,
Regine Vignes
(5)
1
UCA -
Université Cadi Ayyad [Marrakech]
2 LIM - Laboratoire d'Informatique et de Mathématiques
3 ENTROPIE [Réunion] - Ecologie marine tropicale dans les Océans Pacifique et Indien
4 UMMISCO - Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]
5 ISYEB - Institut de Systématique, Evolution, Biodiversité
2 LIM - Laboratoire d'Informatique et de Mathématiques
3 ENTROPIE [Réunion] - Ecologie marine tropicale dans les Océans Pacifique et Indien
4 UMMISCO - Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]
5 ISYEB - Institut de Systématique, Evolution, Biodiversité
Noël Conruyt
- Fonction : Auteur
- PersonId : 176983
- IdHAL : noel-conruyt
- IdRef : 05030805X
Mohsen Kayal
- Fonction : Auteur
- PersonId : 1197165
- ORCID : 0000-0003-3675-9855
Philippe A Martin
- Fonction : Auteur
- PersonId : 12700
- IdHAL : phmartin83
- ORCID : 0000-0002-6793-8760
Eric Chenin
- Fonction : Auteur
- PersonId : 1372520
Lionel Bigot
- Fonction : Auteur
- PersonId : 830491
Regine Vignes
- Fonction : Auteur
- PersonId : 176959
- IdHAL : regine-vignes-lebbe
- ORCID : 0000-0002-6912-6248
- IdRef : 081808097
Résumé
Coral reefs are vital ecosystems that are under increasing threat due to local human impacts and climate change. Efficient and accurate monitoring of coral reefs is crucial for their conservation and management. In this paper, we present an automatic coral detection system utilizing the You Only Look Once (YOLO) deep learning model, which is specifically tailored for underwater imagery analysis. To train and evaluate our system, we employ a dataset consisting of 400 original underwater images. We increased the number of annotated images to 580 through image manipulation using data augmentation techniques, which can improve the model's performance by providing more diverse examples for training. The dataset is carefully collected from underwater videos that capture various coral reef environments, species, and lighting conditions. Our system leverages the YOLOv5 algorithm's real-time object detection capabilities, enabling efficient and accurate coral detection. We used YOLOv5 to extract discriminating features from the annotated dataset, enabling the system to generalize, including previously unseen underwater images. The successful implementation of the automatic coral detection system with YOLOv5 on our original image dataset highlights the potential of advanced computer vision techniques for coral reef research and conservation. Further research will focus on refining the algorithm to handle challenging underwater image conditions, and expanding the dataset to incorporate a wider range of coral species and spatio-temporal variations.
Domaines
Intelligence artificielle [cs.AI]Format du dépôt | Fichier |
---|---|
Type de dépôt | Communication dans un congrès |
Titre |
en
Automatic Coral Detection with YOLO: A Deep Learning Approach for Efficient and Accurate Coral Reef Monitoring
|
Résumé |
en
Coral reefs are vital ecosystems that are under increasing threat due to local human impacts and climate change. Efficient and accurate monitoring of coral reefs is crucial for their conservation and management. In this paper, we present an automatic coral detection system utilizing the You Only Look Once (YOLO) deep learning model, which is specifically tailored for underwater imagery analysis. To train and evaluate our system, we employ a dataset consisting of 400 original underwater images. We increased the number of annotated images to 580 through image manipulation using data augmentation techniques, which can improve the model's performance by providing more diverse examples for training. The dataset is carefully collected from underwater videos that capture various coral reef environments, species, and lighting conditions. Our system leverages the YOLOv5 algorithm's real-time object detection capabilities, enabling efficient and accurate coral detection. We used YOLOv5 to extract discriminating features from the annotated dataset, enabling the system to generalize, including previously unseen underwater images. The successful implementation of the automatic coral detection system with YOLOv5 on our original image dataset highlights the potential of advanced computer vision techniques for coral reef research and conservation. Further research will focus on refining the algorithm to handle challenging underwater image conditions, and expanding the dataset to incorporate a wider range of coral species and spatio-temporal variations.
|
Auteur(s) |
Younes Ouassine
1
, Jihad Zahir
1
, Noël Conruyt
2
, Mohsen Kayal
3
, Philippe A Martin
2
, Eric Chenin
4
, Lionel Bigot
3
, Regine Vignes
5
1
UCA -
Université Cadi Ayyad [Marrakech]
( 302207 )
- Av Abdelkrim Khattabi, B.P. 511 - 40000 - Marrakech
- Maroc
2
LIM -
Laboratoire d'Informatique et de Mathématiques
( 54305 )
- Faculté des Sciences et Technologies - Université de la Réunion, 2, rue Joseph Wetzell 97490 Sainte-Clotilde
- France
3
ENTROPIE [Réunion] -
Ecologie marine tropicale dans les Océans Pacifique et Indien
( 418794 )
- UNIVERSITE DE LA REUNION
Faculté des Sciences et Technolo
15 Avenue René Casin
BP 92003
97744 ST DENIS CEDEX 9
- France
4
UMMISCO -
Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]
( 541946 )
- IRD France Nord - 32 avenue Henri Varagnat - 93143 Bondy cedex
- France
5
ISYEB -
Institut de Systématique, Evolution, Biodiversité
( 542193 )
- 57 rue Cuvier - CP 50 - 75005 Paris
- France
|
Comité de lecture |
Oui
|
Audience |
Internationale
|
Titre de la collection |
Communications in Computer and Information Science
|
Langue du document |
Anglais
|
Titre du congrès |
ECAI 2023 International Workshops
|
ISBN |
978-3-031-50484-6
|
Volume |
1948
|
Page/Identifiant |
170-177
|
Lieu de publication |
Cham
|
Date de publication |
2023-12-01
|
Date début congrès |
2023-09-30
|
Date fin congrès |
2023-10-04
|
Ville |
Kraków
|
Pays |
France
|
Actes |
Non
|
Vulgarisation |
Non
|
Invité |
Non
|
Voir aussi |
|
Éditeur commercial |
|
Domaine(s) |
|
Mots-clés |
en
Machine Learning, Deep Learning, Underwater ecosystems, Corals, Object Detection, YOLO
|
DOI | 10.1007/978-3-031-50485-3_16 |
Fichier sous embargo
Fichier sous embargo
0 | ― | 0 | ― | 8 |
Année | Mois | Jours |
Fin d'embargo le vendredi 10 mai 2024
Loading...