FathomNet: An Open, Underwater Image Repository for Automated Detection and Classification of Midwater and Benthic Objects

Abstract

Abstract Ocean-going platforms and instruments are integrating cameras for observation and navigation, producing a deluge of visual data. The volume of this data collection can rapidly outpace researchers' abilities to process and analyze them. Recent advances in artificial intelligence enable fast, sophisticated analysis of visual data, but have had limited success in the oceanographic world due to lack of dataset standardization, sparse annotation tools, and insufficient formatting and aggregation of existing, expertly curated imagery for use by data scientists. To address this need, we are building FathomNet, a public platform that makes use of existing (and future), expertly curated data to know what is in the ocean and where it is for effective and responsible marine stewardship. This platform is modeled after popular terrestrial datasets (e.g., ImageNet, COCO) that enabled rapid advances in automated visual analysis. FathomNet seeks to engage a wide audience, from the general public to subject-matter experts, to further augment, contribute to, and utilize the training data set. FathomNet will accelerate development of novel algorithms to automate the analysis of underwater visual data, thereby enabling scientists, explorers, policymakers, storytellers, and the public, to learn, understand, and care more about our ocean and its inhabitants.