From underwater to aerial: a novel multi-scale knowledge distillation approach for coral reef monitoring

TL;DR

This paper introduces a multi-scale AI-based approach combining underwater and aerial imagery to improve coral reef monitoring accuracy and scalability, demonstrating high classification performance across large reef areas.

Contribution

It presents a novel multi-scale knowledge distillation method integrating underwater and aerial imagery with deep learning for coral reef classification.

Findings

Achieved an AUC score of 0.9251 in coral classification.

Successfully extended fine-scale underwater analysis to larger reef areas.

Demonstrated high accuracy in predicting coral morphotypes and habitats.

Abstract

Drone-based remote sensing combined with AI-driven methodologies has shown great potential for accurate mapping and monitoring of coral reef ecosystems. This study presents a novel multi-scale approach to coral reef monitoring, integrating fine-scale underwater imagery with medium-scale aerial imagery. Underwater images are captured using an Autonomous Surface Vehicle (ASV), while aerial images are acquired with an aerial drone. A transformer-based deep-learning model is trained on underwater images to detect the presence of 31 classes covering various coral morphotypes, associated fauna, and habitats. These predictions serve as annotations for training a second model applied to aerial images. The transfer of information across scales is achieved through a weighted footprint method that accounts for partial overlaps between underwater image footprints and aerial image tiles. The results show that the multi-scale methodology successfully extends fine-scale classification to larger reef areas, achieving a high degree of accuracy in predicting coral morphotypes and associated habitats. The method showed a strong alignment between underwater-derived annotations and ground truth data, reflected by an AUC (Area Under the Curve) score of 0.9251. This shows that the integration of underwater and aerial imagery, supported by deep-learning models, can facilitate scalable and accurate reef assessments. This study demonstrates the potential of combining multi-scale imaging and AI to facilitate the monitoring and conservation of coral reefs. Our approach leverages the strengths of underwater and aerial imagery, ensuring the precision of fine-scale analysis while extending it to cover a broader reef area.