Multi-species Seagrass Detection and Classification from Underwater Images
This addresses the need for efficient ecological data extraction in marine biology, though it is incremental as it applies existing deep learning methods to a new domain-specific dataset.
The paper tackles the problem of automating seagrass detection and classification from underwater images to reduce manual review time and cost, achieving an overall accuracy of 92.4% with a deep convolutional neural network.
Underwater surveys conducted using divers or robots equipped with customized camera payloads can generate a large number of images. Manual review of these images to extract ecological data is prohibitive in terms of time and cost, thus providing strong incentive to automate this process using machine learning solutions. In this paper, we introduce a multi-species detector and classifier for seagrasses based on a deep convolutional neural network (achieved an overall accuracy of 92.4%). We also introduce a simple method to semi-automatically label image patches and therefore minimize manual labelling requirement. We describe and release publicly the dataset collected in this study as well as the code and pre-trained models to replicate our experiments at: https://github.com/csiro-robotics/deepseagrass