A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic
Underwater imagery is widely used for a variety of applications in marine biology and environmental sciences, such as classification and mapping of seabed habitats, marine environment monitoring and impact assessment, biogeographic reconstructions in the context of climate change, etc. This approach...
Published in: | Data in Brief |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | http://ku.oai.elaba.lt/documents/83384345.pdf http://ku.lvb.lt/KU:ELABAPDB83384345&prefLang=en_US |
id |
ftlitinstagrecon:oai:elaba:83384345 |
---|---|
record_format |
openpolar |
spelling |
ftlitinstagrecon:oai:elaba:83384345 2023-05-15T15:00:38+02:00 A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic Šiaulys, Andrius Vaičiukynas, Evaldas Medelytė, Saulė Olenin, Sergej Šaškov, Aleksej Buškus, Kazimieras Verikas, Antanas 2021 application/pdf http://ku.oai.elaba.lt/documents/83384345.pdf http://ku.lvb.lt/KU:ELABAPDB83384345&prefLang=en_US eng eng info:eu-repo/semantics/altIdentifier/doi/10.1016/j.dib.2021.106823 http://ku.oai.elaba.lt/documents/83384345.pdf http://ku.lvb.lt/KU:ELABAPDB83384345&prefLang=en_US info:eu-repo/semantics/openAccess Data in brief, Amsterdam : Elsevier, 2021, vol. 35, art. no. 106823, p. 1-11 ISSN 2352-3409 underwater imagery mosaicking ROV drop-down camera machine vision image segmentation semantic segmentation info:eu-repo/semantics/article 2021 ftlitinstagrecon https://doi.org/10.1016/j.dib.2021.106823 2021-12-02T01:08:49Z Underwater imagery is widely used for a variety of applications in marine biology and environmental sciences, such as classification and mapping of seabed habitats, marine environment monitoring and impact assessment, biogeographic reconstructions in the context of climate change, etc. This approach is relatively simple and cost-effective, allowing the rapid collection of large amounts of data. However, due to the laborious and time-consuming manual analysis procedure, only a small part of the information stored in the archives of underwater images is retrieved. Emerging novel deep learning methods open up the opportunity for more effective, accurate and rapid analysis of seabed images than ever before. We present annotated images of the bottom macrofauna obtained from underwater video recorded in Spitsbergen island's European Arctic waters, Svalbard Archipelago. Our videos were filmed in both the photic and aphotic zones of polar waters, often influenced by melting glaciers. We used artificial lighting and shot close to the seabed (<1 m) to preserve natural colours and avoid the distorting effect of muddy water. The underwater video footage was captured using a remotely operated vehicle (ROV) and a drop-down camera. The footage was converted to 2D mosaic images of the seabed. 2D mosaics were manually annotated by several experts using the Labelbox tool and co-annotations were refined using the SurveyJS platform. A set of carefully annotated underwater images associated with the original videos can be used by marine biologists as a biological atlas, as well as practitioners in the fields of machine vision, pattern recognition, and deep learning as training materials for the development of various tools for automatic analysis of underwater imagery. Article in Journal/Newspaper Arctic Climate change Svalbard Spitsbergen LAEI VL (Lithuanian Institute of Agrarian Economics Virtual Library) Arctic Svalbard Svalbard Archipelago Data in Brief 35 106823 |
institution |
Open Polar |
collection |
LAEI VL (Lithuanian Institute of Agrarian Economics Virtual Library) |
op_collection_id |
ftlitinstagrecon |
language |
English |
topic |
underwater imagery mosaicking ROV drop-down camera machine vision image segmentation semantic segmentation |
spellingShingle |
underwater imagery mosaicking ROV drop-down camera machine vision image segmentation semantic segmentation Šiaulys, Andrius Vaičiukynas, Evaldas Medelytė, Saulė Olenin, Sergej Šaškov, Aleksej Buškus, Kazimieras Verikas, Antanas A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
topic_facet |
underwater imagery mosaicking ROV drop-down camera machine vision image segmentation semantic segmentation |
description |
Underwater imagery is widely used for a variety of applications in marine biology and environmental sciences, such as classification and mapping of seabed habitats, marine environment monitoring and impact assessment, biogeographic reconstructions in the context of climate change, etc. This approach is relatively simple and cost-effective, allowing the rapid collection of large amounts of data. However, due to the laborious and time-consuming manual analysis procedure, only a small part of the information stored in the archives of underwater images is retrieved. Emerging novel deep learning methods open up the opportunity for more effective, accurate and rapid analysis of seabed images than ever before. We present annotated images of the bottom macrofauna obtained from underwater video recorded in Spitsbergen island's European Arctic waters, Svalbard Archipelago. Our videos were filmed in both the photic and aphotic zones of polar waters, often influenced by melting glaciers. We used artificial lighting and shot close to the seabed (<1 m) to preserve natural colours and avoid the distorting effect of muddy water. The underwater video footage was captured using a remotely operated vehicle (ROV) and a drop-down camera. The footage was converted to 2D mosaic images of the seabed. 2D mosaics were manually annotated by several experts using the Labelbox tool and co-annotations were refined using the SurveyJS platform. A set of carefully annotated underwater images associated with the original videos can be used by marine biologists as a biological atlas, as well as practitioners in the fields of machine vision, pattern recognition, and deep learning as training materials for the development of various tools for automatic analysis of underwater imagery. |
format |
Article in Journal/Newspaper |
author |
Šiaulys, Andrius Vaičiukynas, Evaldas Medelytė, Saulė Olenin, Sergej Šaškov, Aleksej Buškus, Kazimieras Verikas, Antanas |
author_facet |
Šiaulys, Andrius Vaičiukynas, Evaldas Medelytė, Saulė Olenin, Sergej Šaškov, Aleksej Buškus, Kazimieras Verikas, Antanas |
author_sort |
Šiaulys, Andrius |
title |
A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
title_short |
A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
title_full |
A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
title_fullStr |
A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
title_full_unstemmed |
A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic |
title_sort |
fully-annotated imagery dataset of sublittoral benthic species in svalbard, arctic |
publishDate |
2021 |
url |
http://ku.oai.elaba.lt/documents/83384345.pdf http://ku.lvb.lt/KU:ELABAPDB83384345&prefLang=en_US |
geographic |
Arctic Svalbard Svalbard Archipelago |
geographic_facet |
Arctic Svalbard Svalbard Archipelago |
genre |
Arctic Climate change Svalbard Spitsbergen |
genre_facet |
Arctic Climate change Svalbard Spitsbergen |
op_source |
Data in brief, Amsterdam : Elsevier, 2021, vol. 35, art. no. 106823, p. 1-11 ISSN 2352-3409 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.dib.2021.106823 http://ku.oai.elaba.lt/documents/83384345.pdf http://ku.lvb.lt/KU:ELABAPDB83384345&prefLang=en_US |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1016/j.dib.2021.106823 |
container_title |
Data in Brief |
container_volume |
35 |
container_start_page |
106823 |
_version_ |
1766332707907829760 |