A Real-time Edge-AI System for Reef Surveys

TL;DR

This paper introduces a real-time, resource-efficient Edge-AI system utilizing deep learning for underwater Crown-of-Thorn Starfish detection, aiding coral reef monitoring and conservation efforts.

Contribution

It presents a novel edge device-based COTS detection system that combines multiple efficiency strategies for real-time underwater surveillance.

Findings

System runs with low resource consumption

Combines batch processing, frame skipping, and input size reduction

Achieves effective COTS detection in real-time

Abstract

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.