SeagrassFinder: Deep Learning for Eelgrass Detection and Coverage Estimation in the Wild

TL;DR

This paper presents SeagrassFinder, a deep learning approach using models like Vision Transformers to automate seagrass detection and coverage estimation from underwater videos, significantly improving efficiency and accuracy for marine ecosystem monitoring.

Contribution

The work introduces a new annotated dataset, evaluates multiple deep learning architectures, and proposes a novel method for estimating seagrass coverage from underwater videos.

Findings

Deep learning models achieve AUROC > 0.95 in seagrass presence detection.

Underwater image enhancement improves model performance.

Preliminary results show promising coverage estimation aligned with expert labels.

Abstract

Seagrass meadows play a crucial role in marine ecosystems, providing benefits such as carbon sequestration, water quality improvement, and habitat provision. Monitoring the distribution and abundance of seagrass is essential for environmental impact assessments and conservation efforts. However, the current manual methods of analyzing underwater video data to assess seagrass coverage are time-consuming and subjective. This work explores the use of deep learning models to automate the process of seagrass detection and coverage estimation from underwater video data. We create a new dataset of over 8,300 annotated underwater images, and subsequently evaluate several deep learning architectures, including ResNet, InceptionNetV3, DenseNet, and Vision Transformer for the task of binary classification on the presence and absence of seagrass by transfer learning. The results demonstrate that deep learning models, particularly Vision Transformers, can achieve high performance in predicting eelgrass presence, with AUROC scores exceeding 0.95 on the final test dataset. The application of underwater image enhancement further improved the models' prediction capabilities. Furthermore, we introduce a novel approach for estimating seagrass coverage from video data, showing promising preliminary results that align with expert manual labels, and indicating potential for consistent and scalable monitoring. The proposed methodology allows for the efficient processing of large volumes of video data, enabling the acquisition of much more detailed information on seagrass distributions in comparison to current manual methods. This information is crucial for environmental impact assessments and monitoring programs, as seagrasses are important indicators of coastal ecosystem health. This project demonstrates the value that deep learning can bring to the field of marine ecology and environmental monitoring.