Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-09
Hauptverfasser: Islam, Md Jahidul, Edge, Chelsey, Xiao, Yuyang, Luo, Peigen, Mehtaz, Muntaqim, Morse, Christopher, Sadman Sakib Enan, Sattar, Junaed
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Islam, Md Jahidul
Edge, Chelsey
Xiao, Yuyang
Luo, Peigen
Mehtaz, Muntaqim
Morse, Christopher
Sadman Sakib Enan
Sattar, Junaed
description In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images have been rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. We also present a benchmark evaluation of state-of-the-art semantic segmentation approaches based on standard performance metrics. In addition, we present SUIM-Net, a fully-convolutional encoder-decoder model that balances the trade-off between performance and computational efficiency. It offers competitive performance while ensuring fast end-to-end inference, which is essential for its use in the autonomy pipeline of visually-guided underwater robots. In particular, we demonstrate its usability benefits for visual servoing, saliency prediction, and detailed scene understanding. With a variety of use cases, the proposed model and benchmark dataset open up promising opportunities for future research in underwater robot vision.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2386619510</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2386619510</sourcerecordid><originalsourceid>FETCH-proquest_journals_23866195103</originalsourceid><addsrcrecordid>eNqNyr0OgjAUQOHGxESivEMTZ5LSCqIj_kRnZCY3cEHQttpeYnx7HXwApzN8Z8ICqVQcZSspZyz0fhBCyHQtk0QFLC9Qg6G-5gV2Gg0B9dZw2_LSNOheQOj4WUOH7r3leyDwSBxMw3M09VWDuy3YtIW7x_DXOVseD5fdKXo4-xzRUzXY0ZkvVVJlaRpvklio_64Pq8Q5nQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2386619510</pqid></control><display><type>article</type><title>Semantic Segmentation of Underwater Imagery: Dataset and Benchmark</title><source>Free E- Journals</source><creator>Islam, Md Jahidul ; Edge, Chelsey ; Xiao, Yuyang ; Luo, Peigen ; Mehtaz, Muntaqim ; Morse, Christopher ; Sadman Sakib Enan ; Sattar, Junaed</creator><creatorcontrib>Islam, Md Jahidul ; Edge, Chelsey ; Xiao, Yuyang ; Luo, Peigen ; Mehtaz, Muntaqim ; Morse, Christopher ; Sadman Sakib Enan ; Sattar, Junaed</creatorcontrib><description>In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images have been rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. We also present a benchmark evaluation of state-of-the-art semantic segmentation approaches based on standard performance metrics. In addition, we present SUIM-Net, a fully-convolutional encoder-decoder model that balances the trade-off between performance and computational efficiency. It offers competitive performance while ensuring fast end-to-end inference, which is essential for its use in the autonomy pipeline of visually-guided underwater robots. In particular, we demonstrate its usability benefits for visual servoing, saliency prediction, and detailed scene understanding. With a variety of use cases, the proposed model and benchmark dataset open up promising opportunities for future research in underwater robot vision.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Aquatic plants ; Benchmarks ; Datasets ; Image annotation ; Image segmentation ; Machine vision ; Ocean floor ; Performance measurement ; Scene analysis ; Semantic segmentation ; Semantics ; State-of-the-art reviews ; Underwater robots ; Vertebrates ; Visual control</subject><ispartof>arXiv.org, 2020-09</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Islam, Md Jahidul</creatorcontrib><creatorcontrib>Edge, Chelsey</creatorcontrib><creatorcontrib>Xiao, Yuyang</creatorcontrib><creatorcontrib>Luo, Peigen</creatorcontrib><creatorcontrib>Mehtaz, Muntaqim</creatorcontrib><creatorcontrib>Morse, Christopher</creatorcontrib><creatorcontrib>Sadman Sakib Enan</creatorcontrib><creatorcontrib>Sattar, Junaed</creatorcontrib><title>Semantic Segmentation of Underwater Imagery: Dataset and Benchmark</title><title>arXiv.org</title><description>In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images have been rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. We also present a benchmark evaluation of state-of-the-art semantic segmentation approaches based on standard performance metrics. In addition, we present SUIM-Net, a fully-convolutional encoder-decoder model that balances the trade-off between performance and computational efficiency. It offers competitive performance while ensuring fast end-to-end inference, which is essential for its use in the autonomy pipeline of visually-guided underwater robots. In particular, we demonstrate its usability benefits for visual servoing, saliency prediction, and detailed scene understanding. With a variety of use cases, the proposed model and benchmark dataset open up promising opportunities for future research in underwater robot vision.</description><subject>Aquatic plants</subject><subject>Benchmarks</subject><subject>Datasets</subject><subject>Image annotation</subject><subject>Image segmentation</subject><subject>Machine vision</subject><subject>Ocean floor</subject><subject>Performance measurement</subject><subject>Scene analysis</subject><subject>Semantic segmentation</subject><subject>Semantics</subject><subject>State-of-the-art reviews</subject><subject>Underwater robots</subject><subject>Vertebrates</subject><subject>Visual control</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNyr0OgjAUQOHGxESivEMTZ5LSCqIj_kRnZCY3cEHQttpeYnx7HXwApzN8Z8ICqVQcZSspZyz0fhBCyHQtk0QFLC9Qg6G-5gV2Gg0B9dZw2_LSNOheQOj4WUOH7r3leyDwSBxMw3M09VWDuy3YtIW7x_DXOVseD5fdKXo4-xzRUzXY0ZkvVVJlaRpvklio_64Pq8Q5nQ</recordid><startdate>20200913</startdate><enddate>20200913</enddate><creator>Islam, Md Jahidul</creator><creator>Edge, Chelsey</creator><creator>Xiao, Yuyang</creator><creator>Luo, Peigen</creator><creator>Mehtaz, Muntaqim</creator><creator>Morse, Christopher</creator><creator>Sadman Sakib Enan</creator><creator>Sattar, Junaed</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200913</creationdate><title>Semantic Segmentation of Underwater Imagery: Dataset and Benchmark</title><author>Islam, Md Jahidul ; Edge, Chelsey ; Xiao, Yuyang ; Luo, Peigen ; Mehtaz, Muntaqim ; Morse, Christopher ; Sadman Sakib Enan ; Sattar, Junaed</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23866195103</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Aquatic plants</topic><topic>Benchmarks</topic><topic>Datasets</topic><topic>Image annotation</topic><topic>Image segmentation</topic><topic>Machine vision</topic><topic>Ocean floor</topic><topic>Performance measurement</topic><topic>Scene analysis</topic><topic>Semantic segmentation</topic><topic>Semantics</topic><topic>State-of-the-art reviews</topic><topic>Underwater robots</topic><topic>Vertebrates</topic><topic>Visual control</topic><toplevel>online_resources</toplevel><creatorcontrib>Islam, Md Jahidul</creatorcontrib><creatorcontrib>Edge, Chelsey</creatorcontrib><creatorcontrib>Xiao, Yuyang</creatorcontrib><creatorcontrib>Luo, Peigen</creatorcontrib><creatorcontrib>Mehtaz, Muntaqim</creatorcontrib><creatorcontrib>Morse, Christopher</creatorcontrib><creatorcontrib>Sadman Sakib Enan</creatorcontrib><creatorcontrib>Sattar, Junaed</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Islam, Md Jahidul</au><au>Edge, Chelsey</au><au>Xiao, Yuyang</au><au>Luo, Peigen</au><au>Mehtaz, Muntaqim</au><au>Morse, Christopher</au><au>Sadman Sakib Enan</au><au>Sattar, Junaed</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Semantic Segmentation of Underwater Imagery: Dataset and Benchmark</atitle><jtitle>arXiv.org</jtitle><date>2020-09-13</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>In this paper, we present the first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM). It contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images have been rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. We also present a benchmark evaluation of state-of-the-art semantic segmentation approaches based on standard performance metrics. In addition, we present SUIM-Net, a fully-convolutional encoder-decoder model that balances the trade-off between performance and computational efficiency. It offers competitive performance while ensuring fast end-to-end inference, which is essential for its use in the autonomy pipeline of visually-guided underwater robots. In particular, we demonstrate its usability benefits for visual servoing, saliency prediction, and detailed scene understanding. With a variety of use cases, the proposed model and benchmark dataset open up promising opportunities for future research in underwater robot vision.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2386619510
source Free E- Journals
subjects Aquatic plants
Benchmarks
Datasets
Image annotation
Image segmentation
Machine vision
Ocean floor
Performance measurement
Scene analysis
Semantic segmentation
Semantics
State-of-the-art reviews
Underwater robots
Vertebrates
Visual control
title Semantic Segmentation of Underwater Imagery: Dataset and Benchmark
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T04%3A43%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Semantic%20Segmentation%20of%20Underwater%20Imagery:%20Dataset%20and%20Benchmark&rft.jtitle=arXiv.org&rft.au=Islam,%20Md%20Jahidul&rft.date=2020-09-13&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2386619510%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2386619510&rft_id=info:pmid/&rfr_iscdi=true