Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels. In this paper, we present a comprehensive real-time machine learning-based underwater data collection and curation system on edge devices for COTS monitoring. In particular, we leverage the power of deep learning-based object detection techniques, and propose a resource-efficient COTS detector that performs detection inferences on the edge device to assist marine experts with COTS identification during the data collection phase. The preliminary results show that several strategies for improving computational efficiency (e.g., batch-wise processing, frame skipping, model input size) can be combined to run the proposed detection model on edge hardware with low resource consumption and low information loss.
Cite
@article{arxiv.2208.00598,
title = {A Real-time Edge-AI System for Reef Surveys},
author = {Yang Li and Jiajun Liu and Brano Kusy and Ross Marchant and Brendan Do and Torsten Merz and Joey Crosswell and Andy Steven and Lachlan Tychsen-Smith and David Ahmedt-Aristizabal and Jeremy Oorloff and Peyman Moghadam and Russ Babcock and Megha Malpani and Ard Oerlemans},
journal= {arXiv preprint arXiv:2208.00598},
year = {2022}
}