FathomNet: A global image database for enabling artificial intelligence in the ocean
Abstract The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly ou...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-19939-2 |
| _version_ | 1811265044809252864 |
|---|---|
| author | Kakani Katija Eric Orenstein Brian Schlining Lonny Lundsten Kevin Barnard Giovanna Sainz Oceane Boulais Megan Cromwell Erin Butler Benjamin Woodward Katherine L. C. Bell |
| author_facet | Kakani Katija Eric Orenstein Brian Schlining Lonny Lundsten Kevin Barnard Giovanna Sainz Oceane Boulais Megan Cromwell Erin Butler Benjamin Woodward Katherine L. C. Bell |
| author_sort | Kakani Katija |
| collection | DOAJ |
| description | Abstract The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean. |
| first_indexed | 2024-04-12T20:15:28Z |
| format | Article |
| id | doaj.art-f6fc35db7a0f4197b321c3d77f2ac86e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T20:15:28Z |
| publishDate | 2022-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-f6fc35db7a0f4197b321c3d77f2ac86e2022-12-22T03:18:08ZengNature PortfolioScientific Reports2045-23222022-09-0112111410.1038/s41598-022-19939-2FathomNet: A global image database for enabling artificial intelligence in the oceanKakani Katija0Eric Orenstein1Brian Schlining2Lonny Lundsten3Kevin Barnard4Giovanna Sainz5Oceane Boulais6Megan Cromwell7Erin Butler8Benjamin Woodward9Katherine L. C. Bell10Monterey Bay Aquarium Research Institute, Research and DevelopmentMonterey Bay Aquarium Research Institute, Research and DevelopmentMonterey Bay Aquarium Research Institute, Research and DevelopmentMonterey Bay Aquarium Research Institute, Research and DevelopmentMonterey Bay Aquarium Research Institute, Research and DevelopmentMonterey Bay Aquarium Research Institute, Research and DevelopmentNOAA, Southeast Fisheries Science CenterNOAA, National Centers for Environmental Information, Stennis Space CenterCVision AI Inc., Research and DevelopmentCVision AI Inc., Research and DevelopmentOcean Discovery LeagueAbstract The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean.https://doi.org/10.1038/s41598-022-19939-2 |
| spellingShingle | Kakani Katija Eric Orenstein Brian Schlining Lonny Lundsten Kevin Barnard Giovanna Sainz Oceane Boulais Megan Cromwell Erin Butler Benjamin Woodward Katherine L. C. Bell FathomNet: A global image database for enabling artificial intelligence in the ocean Scientific Reports |
| title | FathomNet: A global image database for enabling artificial intelligence in the ocean |
| title_full | FathomNet: A global image database for enabling artificial intelligence in the ocean |
| title_fullStr | FathomNet: A global image database for enabling artificial intelligence in the ocean |
| title_full_unstemmed | FathomNet: A global image database for enabling artificial intelligence in the ocean |
| title_short | FathomNet: A global image database for enabling artificial intelligence in the ocean |
| title_sort | fathomnet a global image database for enabling artificial intelligence in the ocean |
| url | https://doi.org/10.1038/s41598-022-19939-2 |
| work_keys_str_mv | AT kakanikatija fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT ericorenstein fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT brianschlining fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT lonnylundsten fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT kevinbarnard fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT giovannasainz fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT oceaneboulais fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT megancromwell fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT erinbutler fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT benjaminwoodward fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean AT katherinelcbell fathomnetaglobalimagedatabaseforenablingartificialintelligenceintheocean |