Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking

Coral reefs are vital for biodiversity, coastal protection, food security, and tourism, yet they face severe threats from anthropogenic activities and climate change, which are leading to their decline. Effective coral reef monitoring is essential for ecological understanding and conservation, but t...

Full description

Saved in:
Bibliographic Details
Main Authors: Younes Ouassine, Noël Conruyt, Mohsen Kayal, Philippe A. Martin, Lionel Bigot, Vignes Lebbe Regine, Hajar Moussanif, Jihad Zahir
Format: Article
Language:English
Published: Elsevier 2025-11-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125001797
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850235360701841408
author Younes Ouassine
Noël Conruyt
Mohsen Kayal
Philippe A. Martin
Lionel Bigot
Vignes Lebbe Regine
Hajar Moussanif
Jihad Zahir
author_facet Younes Ouassine
Noël Conruyt
Mohsen Kayal
Philippe A. Martin
Lionel Bigot
Vignes Lebbe Regine
Hajar Moussanif
Jihad Zahir
author_sort Younes Ouassine
collection DOAJ
description Coral reefs are vital for biodiversity, coastal protection, food security, and tourism, yet they face severe threats from anthropogenic activities and climate change, which are leading to their decline. Effective coral reef monitoring is essential for ecological understanding and conservation, but traditional methods are resource-intensive and rely on experts. To address these challenges, we present an automated, deep learning-based monitoring system that integrates YOLOv8, a state-of-the-art object detection algorithm, with DeepSORT, a robust multi-object tracking method, to identify and track coral formations in underwater video footage. Our system was fine-tuned using two curated and annotated datasets: AIMECORAL1 (580 images from the Southwest Indian Ocean) and AIMECORAL2 (282 images from New Caledonia, Pacific Ocean), encompassing diverse coral species and environmental conditions. The system's performance was evaluated using established metrics: object detection precision, Multiple Object Tracking Accuracy (MOTA), Multiple Object Tracking Precision (MOTP), and Identity F1 Score (IDF1). Precision improved from 59.9 % (after fine-tuning on AIMECORAL1) to 84.7 % on the combined datasets. The tracking system achieved a MOTA of 82.63 %, MOTP of 83.28 %, and IDF1 of 70.76 %, demonstrating reliable multi-object tracking in complex underwater environments. We applied our framework to a case study involving video transects from an outer reef site in New Caledonia, comparing data from 2021 and 2022. This automated solution offers a scalable, cost-effective alternative to traditional monitoring methods, supporting seamless, large-scale reef assessment. By leveraging deep learning, our approach enables more efficient data collection, contributing to the protection of these vulnerable ecosystems in the face of increasing environmental pressures.
format Article
id doaj-art-80a0cb824fe14065b3bed8a3c3bf46bc
institution OA Journals
issn 1574-9541
language English
publishDate 2025-11-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-80a0cb824fe14065b3bed8a3c3bf46bc2025-08-20T02:02:17ZengElsevierEcological Informatics1574-95412025-11-018910317010.1016/j.ecoinf.2025.103170Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT trackingYounes Ouassine0Noël Conruyt1Mohsen Kayal2Philippe A. Martin3Lionel Bigot4Vignes Lebbe Regine5Hajar Moussanif6Jihad Zahir7Computer Science Department, LISI, Cadi Ayyad University, Morocco; Corresponding author.EA2525 LIM, (I.T. Department), University of La Réunion, 97400 Saint-Denis, FranceENTROPIE, IRD, IFREMER, CNRS, University of La Reunion, University of New Caledonia, Noumea, New Caledonia; Station Marine d'Endoume, Marseille, FranceEA2525 LIM, (I.T. Department), University of La Réunion, 97400 Saint-Denis, FranceEA2525 LIM, (I.T. Department), University of La Réunion, 97400 Saint-Denis, FranceInstitut de Systématique, Evolution, Biodiversité (ISYEB), SU, MNHN, CNRS, EPHE, UA - CP 48, 57 rue Cuvier, 75005 Paris, FranceComputer Science Department, LISI, Cadi Ayyad University, MoroccoComputer Science Department, LISI, Cadi Ayyad University, Morocco; EA2525 LIM, (I.T. Department), University of La Réunion, 97400 Saint-Denis, France; ENTROPIE, IRD, IFREMER, CNRS, University of La Reunion, University of New Caledonia, Noumea, New Caledonia; Institut de Systématique, Evolution, Biodiversité (ISYEB), SU, MNHN, CNRS, EPHE, UA - CP 48, 57 rue Cuvier, 75005 Paris, France; Station Marine d'Endoume, Marseille, France; UMMISCO, IRD, Computer Science Department, LISI, CADI Ayyad University, MoroccoCoral reefs are vital for biodiversity, coastal protection, food security, and tourism, yet they face severe threats from anthropogenic activities and climate change, which are leading to their decline. Effective coral reef monitoring is essential for ecological understanding and conservation, but traditional methods are resource-intensive and rely on experts. To address these challenges, we present an automated, deep learning-based monitoring system that integrates YOLOv8, a state-of-the-art object detection algorithm, with DeepSORT, a robust multi-object tracking method, to identify and track coral formations in underwater video footage. Our system was fine-tuned using two curated and annotated datasets: AIMECORAL1 (580 images from the Southwest Indian Ocean) and AIMECORAL2 (282 images from New Caledonia, Pacific Ocean), encompassing diverse coral species and environmental conditions. The system's performance was evaluated using established metrics: object detection precision, Multiple Object Tracking Accuracy (MOTA), Multiple Object Tracking Precision (MOTP), and Identity F1 Score (IDF1). Precision improved from 59.9 % (after fine-tuning on AIMECORAL1) to 84.7 % on the combined datasets. The tracking system achieved a MOTA of 82.63 %, MOTP of 83.28 %, and IDF1 of 70.76 %, demonstrating reliable multi-object tracking in complex underwater environments. We applied our framework to a case study involving video transects from an outer reef site in New Caledonia, comparing data from 2021 and 2022. This automated solution offers a scalable, cost-effective alternative to traditional monitoring methods, supporting seamless, large-scale reef assessment. By leveraging deep learning, our approach enables more efficient data collection, contributing to the protection of these vulnerable ecosystems in the face of increasing environmental pressures.http://www.sciencedirect.com/science/article/pii/S1574954125001797Coral reefs ecosystemsDeep learningMethodologyYOLOv8DeepSORT
spellingShingle Younes Ouassine
Noël Conruyt
Mohsen Kayal
Philippe A. Martin
Lionel Bigot
Vignes Lebbe Regine
Hajar Moussanif
Jihad Zahir
Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
Ecological Informatics
Coral reefs ecosystems
Deep learning
Methodology
YOLOv8
DeepSORT
title Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
title_full Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
title_fullStr Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
title_full_unstemmed Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
title_short Deep learning for automated coral reef monitoring a novel system based on YOLOv8 detection and DeepSORT tracking
title_sort deep learning for automated coral reef monitoring a novel system based on yolov8 detection and deepsort tracking
topic Coral reefs ecosystems
Deep learning
Methodology
YOLOv8
DeepSORT
url http://www.sciencedirect.com/science/article/pii/S1574954125001797
work_keys_str_mv AT younesouassine deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT noelconruyt deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT mohsenkayal deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT philippeamartin deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT lionelbigot deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT vigneslebberegine deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT hajarmoussanif deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking
AT jihadzahir deeplearningforautomatedcoralreefmonitoringanovelsystembasedonyolov8detectionanddeepsorttracking