ORIGINAL RESEARCH article
Front. Mar. Sci.
Sec. Marine Ecosystem Ecology
Volume 12 - 2025 | doi: 10.3389/fmars.2025.1658205
This article is part of the Research TopicEcological Risk and Management of Nonindigenous Aquatic SpeciesView all articles
Efficient Underwater Ecological Monitoring with Embedded AI: Detecting Crown-of-Thorns Starfish via DCGAN and YOLOv6
Provisionally accepted
- Vellore Institute of Technology - Chennai Campus, Chennai, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Coral reefs are among the most vital and diverse ecosystems on the planet, providing critical habitats for marine life, supporting fisheries, and protecting coastlines. However, they are increasingly threatened by outbreaks of Crown-of-Thorns Starfish (COTS), a coral eating predator capable of shattering reef structures. Traditional monitoring techniques, which uses heavily on manual surveys by divers, are time consuming, labour intensive, and fail to offer the scale or speed required for timely intervention across vast reef regions such as the Great Barrier Reef. To overcome these limitations, this study presents an AI powered, novel framework for detecting COTS in underwater imagery. The proposed system combines advanced deep learning techniques with synthetic data augmentation to ensure robustness and adaptability under complex underwater conditions. Synthetic training images are generated to enhance model generalization, and optimized object detection models are deployed for both high accuracy and real time inference. The final detection model achieves impressive results, with a precision of 0.927, recall of 0.903, and mAP@50 of 0.938. Designed for deployment on embedded systems, this solution offers a practical, scalable, and efficient approach to reef monitoring, contributing to the conservation and ecological resilience of coral reef ecosystems.
Keywords: Crown-of-thorns starfish (COTS), underwater object detection, YOLOv6, Faster R-CNN, generative adversarial network, Embedded AI
Received: 02 Jul 2025; Accepted: 21 Aug 2025.
Copyright: © 2025 S, J and murugan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Pavithra S, Vellore Institute of Technology - Chennai Campus, Chennai, India
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.