State of the art applications of deep learning within tracking and detecting marine debris: A survey

TL;DR

This survey reviews recent deep learning applications in marine debris detection, highlighting the dominance of YOLO models, the lack of comprehensive underwater debris datasets, and the need for future research directions.

Contribution

It provides an up-to-date analysis of 28 key studies, evaluates YOLOv5 on a new dataset, and discusses open challenges and future research recommendations.

Findings

YOLO models outperform other detection methods

Current datasets are insufficient for effective marine debris detection

YOLOv5 showed low accuracy and high false positives on a small dataset

Abstract

Deep learning techniques have been explored within the marine litter problem for approximately 20 years but the majority of the research has developed rapidly in the last five years. We provide an in-depth, up to date, summary and analysis of 28 of the most recent and significant contributions of deep learning in marine debris. From cross referencing the research paper results, the YOLO family significantly outperforms all other methods of object detection but there are many respected contributions to this field that have categorically agreed that a comprehensive database of underwater debris is not currently available for machine learning. Using a small dataset curated and labelled by us, we tested YOLOv5 on a binary classification task and found the accuracy was low and the rate of false positives was high; highlighting the importance of a comprehensive database. We conclude this survey with over 40 future research recommendations and open challenges.