FathomNet: An underwater image training database for ocean exploration and discovery

Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Boulais, Océane, Woodward, Ben, Schlining, Brian, Lundsten, Lonny, Barnard, Kevin, Bell, Katy Croff, Katija, Kakani
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Boulais, Océane
Woodward, Ben
Schlining, Brian
Lundsten, Lonny
Barnard, Kevin
Bell, Katy Croff
Katija, Kakani
description Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is a novel baseline image training set, optimized to accelerate development of modern, intelligent, and automated analysis of underwater imagery. Our seed data set consists of an expertly annotated and continuously maintained database with more than 26,000 hours of videotape, 6.8 million annotations, and 4,349 terms in the knowledge base. FathomNet leverages this data set by providing imagery, localizations, and class labels of underwater concepts in order to enable machine learning algorithm development. To date, there are more than 80,000 images and 106,000 localizations for 233 different classes, including midwater and benthic organisms. Our experiments consisted of training various deep learning algorithms with approaches to address weakly supervised localization, image labeling, object detection and classification which prove to be promising. While we find quality results on prediction for this new dataset, our results indicate that we are ultimately in need of a larger data set for ocean exploration.
doi_str_mv 10.48550/arxiv.2007.00114
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2007_00114</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2007_00114</sourcerecordid><originalsourceid>FETCH-LOGICAL-a1634-2f51881001d45e02070276ddbf4c193ff09a65b106cda66abed46aa2278c8e2a3</originalsourceid><addsrcrecordid>eNotz8FOAjEUheFuXBj0AVzZF5jxttN2BnaEiJoQ3eB6cqe9hSbQkk5FeHsRXZ3dyf8x9iCgVp3W8IT5FI61BGhrACHULVsvsWzT_p3KjM8j_4qO8jcWyjzscUO8ZAwxxA13WHDAkbhPmSdLGDmdDruUsYQUOUbHXRhtOlI-37Ebj7uR7v93wj6Xz-vFa7X6eHlbzFcVCtOoSnotuk5cSpzSBBJakK1xbvDKimnjPUzR6EGAsQ6NwYGcMohStp3tSGIzYY9_v1dXf8iX5nzuf3391df8AOkRS2A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>FathomNet: An underwater image training database for ocean exploration and discovery</title><source>arXiv.org</source><creator>Boulais, Océane ; Woodward, Ben ; Schlining, Brian ; Lundsten, Lonny ; Barnard, Kevin ; Bell, Katy Croff ; Katija, Kakani</creator><creatorcontrib>Boulais, Océane ; Woodward, Ben ; Schlining, Brian ; Lundsten, Lonny ; Barnard, Kevin ; Bell, Katy Croff ; Katija, Kakani</creatorcontrib><description>Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is a novel baseline image training set, optimized to accelerate development of modern, intelligent, and automated analysis of underwater imagery. Our seed data set consists of an expertly annotated and continuously maintained database with more than 26,000 hours of videotape, 6.8 million annotations, and 4,349 terms in the knowledge base. FathomNet leverages this data set by providing imagery, localizations, and class labels of underwater concepts in order to enable machine learning algorithm development. To date, there are more than 80,000 images and 106,000 localizations for 233 different classes, including midwater and benthic organisms. Our experiments consisted of training various deep learning algorithms with approaches to address weakly supervised localization, image labeling, object detection and classification which prove to be promising. While we find quality results on prediction for this new dataset, our results indicate that we are ultimately in need of a larger data set for ocean exploration.</description><identifier>DOI: 10.48550/arxiv.2007.00114</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Databases</subject><creationdate>2020-06</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a1634-2f51881001d45e02070276ddbf4c193ff09a65b106cda66abed46aa2278c8e2a3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2007.00114$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2007.00114$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Boulais, Océane</creatorcontrib><creatorcontrib>Woodward, Ben</creatorcontrib><creatorcontrib>Schlining, Brian</creatorcontrib><creatorcontrib>Lundsten, Lonny</creatorcontrib><creatorcontrib>Barnard, Kevin</creatorcontrib><creatorcontrib>Bell, Katy Croff</creatorcontrib><creatorcontrib>Katija, Kakani</creatorcontrib><title>FathomNet: An underwater image training database for ocean exploration and discovery</title><description>Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is a novel baseline image training set, optimized to accelerate development of modern, intelligent, and automated analysis of underwater imagery. Our seed data set consists of an expertly annotated and continuously maintained database with more than 26,000 hours of videotape, 6.8 million annotations, and 4,349 terms in the knowledge base. FathomNet leverages this data set by providing imagery, localizations, and class labels of underwater concepts in order to enable machine learning algorithm development. To date, there are more than 80,000 images and 106,000 localizations for 233 different classes, including midwater and benthic organisms. Our experiments consisted of training various deep learning algorithms with approaches to address weakly supervised localization, image labeling, object detection and classification which prove to be promising. While we find quality results on prediction for this new dataset, our results indicate that we are ultimately in need of a larger data set for ocean exploration.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Databases</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8FOAjEUheFuXBj0AVzZF5jxttN2BnaEiJoQ3eB6cqe9hSbQkk5FeHsRXZ3dyf8x9iCgVp3W8IT5FI61BGhrACHULVsvsWzT_p3KjM8j_4qO8jcWyjzscUO8ZAwxxA13WHDAkbhPmSdLGDmdDruUsYQUOUbHXRhtOlI-37Ebj7uR7v93wj6Xz-vFa7X6eHlbzFcVCtOoSnotuk5cSpzSBBJakK1xbvDKimnjPUzR6EGAsQ6NwYGcMohStp3tSGIzYY9_v1dXf8iX5nzuf3391df8AOkRS2A</recordid><startdate>20200630</startdate><enddate>20200630</enddate><creator>Boulais, Océane</creator><creator>Woodward, Ben</creator><creator>Schlining, Brian</creator><creator>Lundsten, Lonny</creator><creator>Barnard, Kevin</creator><creator>Bell, Katy Croff</creator><creator>Katija, Kakani</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200630</creationdate><title>FathomNet: An underwater image training database for ocean exploration and discovery</title><author>Boulais, Océane ; Woodward, Ben ; Schlining, Brian ; Lundsten, Lonny ; Barnard, Kevin ; Bell, Katy Croff ; Katija, Kakani</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a1634-2f51881001d45e02070276ddbf4c193ff09a65b106cda66abed46aa2278c8e2a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Boulais, Océane</creatorcontrib><creatorcontrib>Woodward, Ben</creatorcontrib><creatorcontrib>Schlining, Brian</creatorcontrib><creatorcontrib>Lundsten, Lonny</creatorcontrib><creatorcontrib>Barnard, Kevin</creatorcontrib><creatorcontrib>Bell, Katy Croff</creatorcontrib><creatorcontrib>Katija, Kakani</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Boulais, Océane</au><au>Woodward, Ben</au><au>Schlining, Brian</au><au>Lundsten, Lonny</au><au>Barnard, Kevin</au><au>Bell, Katy Croff</au><au>Katija, Kakani</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>FathomNet: An underwater image training database for ocean exploration and discovery</atitle><date>2020-06-30</date><risdate>2020</risdate><abstract>Thousands of hours of marine video data are collected annually from remotely operated vehicles (ROVs) and other underwater assets. However, current manual methods of analysis impede the full utilization of collected data for real time algorithms for ROV and large biodiversity analyses. FathomNet is a novel baseline image training set, optimized to accelerate development of modern, intelligent, and automated analysis of underwater imagery. Our seed data set consists of an expertly annotated and continuously maintained database with more than 26,000 hours of videotape, 6.8 million annotations, and 4,349 terms in the knowledge base. FathomNet leverages this data set by providing imagery, localizations, and class labels of underwater concepts in order to enable machine learning algorithm development. To date, there are more than 80,000 images and 106,000 localizations for 233 different classes, including midwater and benthic organisms. Our experiments consisted of training various deep learning algorithms with approaches to address weakly supervised localization, image labeling, object detection and classification which prove to be promising. While we find quality results on prediction for this new dataset, our results indicate that we are ultimately in need of a larger data set for ocean exploration.</abstract><doi>10.48550/arxiv.2007.00114</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2007.00114
ispartof
issn
language eng
recordid cdi_arxiv_primary_2007_00114
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Databases
title FathomNet: An underwater image training database for ocean exploration and discovery
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T10%3A51%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=FathomNet:%20An%20underwater%20image%20training%20database%20for%20ocean%20exploration%20and%20discovery&rft.au=Boulais,%20Oc%C3%A9ane&rft.date=2020-06-30&rft_id=info:doi/10.48550/arxiv.2007.00114&rft_dat=%3Carxiv_GOX%3E2007_00114%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true