Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories
Special issue Imaging Sensor Systems for Analyzing Subsea Environment and Life).-- 25 pages, 8 figures, 4 tables, 1 appendix An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, i...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , |
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Molecular Diversity Preservation International
2020
|
Subjects: | |
Online Access: | http://hdl.handle.net/10261/201975 https://doi.org/10.3390/s20030726 https://doi.org/10.13039/501100011033 |
id |
ftcsic:oai:digital.csic.es:10261/201975 |
---|---|
record_format |
openpolar |
spelling |
ftcsic:oai:digital.csic.es:10261/201975 2024-02-11T10:02:28+01:00 Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories López-Vázquez, Vanesa López-Guede, José Manuel Marini, Simone Fanelli, Emanuela Johnsen, Espen Aguzzi, Jacopo Agencia Estatal de Investigación (España) Ministerio de Ciencia, Innovación y Universidades (España) 2020-01 http://hdl.handle.net/10261/201975 https://doi.org/10.3390/s20030726 https://doi.org/10.13039/501100011033 unknown Molecular Diversity Preservation International #PLACEHOLDER_PARENT_METADATA_VALUE# TEC2017-87861-R/AEI/10.13039/501100011033 info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TEC2017-87861-R https://doi.org/10.3390/s20030726 Sí issn: 1424-3210 e-issn: 1424-8220 Sensors 20(3): 726 (2020) CEX2019-000928-S http://hdl.handle.net/10261/201975 doi:10.3390/s20030726 http://dx.doi.org/10.13039/501100011033 32012976 open Cabled observatories Artificial intelligence Deep learning Machine learning Deep-sea fauna artículo http://purl.org/coar/resource_type/c_6501 2020 ftcsic https://doi.org/10.3390/s2003072610.13039/501100011033 2024-01-16T10:49:06Z Special issue Imaging Sensor Systems for Analyzing Subsea Environment and Life).-- 25 pages, 8 figures, 4 tables, 1 appendix An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, it is important to develop spatially widespread monitoring networks capable of providing large amounts of multiparametric information, encompassing both biotic and abiotic variables, and describing the ecological dynamics of the observed species. In this context, imaging devices are valuable tools that complement other biological and oceanographic monitoring devices. Nevertheless, large amounts of images or movies cannot all be manually processed, and autonomous routines for recognizing the relevant content, classification, and tagging are urgently needed. In this work, we propose a pipeline for the analysis of visual data that integrates video/image annotation tools for defining, training, and validation of datasets with video/image enhancement and machine and deep learning approaches. Such a pipeline is required to achieve good performance in the recognition and classification tasks of mobile and sessile megafauna, in order to obtain integrated information on spatial distribution and temporal dynamics. A prototype implementation of the analysis pipeline is provided in the context of deep¿sea videos taken by one of the fixed cameras at the LoVe Ocean Observatory network of Lofoten Islands (Norway) at 260 m depth, in the Barents Sea, which has shown good classification results on an independent test dataset with an accuracy value of 76.18% and an area under the curve (AUC) value of 87.59% This work was developed within the framework of the Tecnoterra (ICM-CSIC/UPC) and the following project activities: ARIM (Autonomous Robotic Sea-Floor Infrastructure for Benthopelagic Monitoring; MarTERA ERA-Net Cofound) and RESBIO (TEC2017-87861-R; Ministerio de Ciencia, Innovación y Universidades) With the funding support of ... Article in Journal/Newspaper Barents Sea Lofoten Digital.CSIC (Spanish National Research Council) Barents Sea Lofoten Norway Sensors 20 3 726 |
institution |
Open Polar |
collection |
Digital.CSIC (Spanish National Research Council) |
op_collection_id |
ftcsic |
language |
unknown |
topic |
Cabled observatories Artificial intelligence Deep learning Machine learning Deep-sea fauna |
spellingShingle |
Cabled observatories Artificial intelligence Deep learning Machine learning Deep-sea fauna López-Vázquez, Vanesa López-Guede, José Manuel Marini, Simone Fanelli, Emanuela Johnsen, Espen Aguzzi, Jacopo Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
topic_facet |
Cabled observatories Artificial intelligence Deep learning Machine learning Deep-sea fauna |
description |
Special issue Imaging Sensor Systems for Analyzing Subsea Environment and Life).-- 25 pages, 8 figures, 4 tables, 1 appendix An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, it is important to develop spatially widespread monitoring networks capable of providing large amounts of multiparametric information, encompassing both biotic and abiotic variables, and describing the ecological dynamics of the observed species. In this context, imaging devices are valuable tools that complement other biological and oceanographic monitoring devices. Nevertheless, large amounts of images or movies cannot all be manually processed, and autonomous routines for recognizing the relevant content, classification, and tagging are urgently needed. In this work, we propose a pipeline for the analysis of visual data that integrates video/image annotation tools for defining, training, and validation of datasets with video/image enhancement and machine and deep learning approaches. Such a pipeline is required to achieve good performance in the recognition and classification tasks of mobile and sessile megafauna, in order to obtain integrated information on spatial distribution and temporal dynamics. A prototype implementation of the analysis pipeline is provided in the context of deep¿sea videos taken by one of the fixed cameras at the LoVe Ocean Observatory network of Lofoten Islands (Norway) at 260 m depth, in the Barents Sea, which has shown good classification results on an independent test dataset with an accuracy value of 76.18% and an area under the curve (AUC) value of 87.59% This work was developed within the framework of the Tecnoterra (ICM-CSIC/UPC) and the following project activities: ARIM (Autonomous Robotic Sea-Floor Infrastructure for Benthopelagic Monitoring; MarTERA ERA-Net Cofound) and RESBIO (TEC2017-87861-R; Ministerio de Ciencia, Innovación y Universidades) With the funding support of ... |
author2 |
Agencia Estatal de Investigación (España) Ministerio de Ciencia, Innovación y Universidades (España) |
format |
Article in Journal/Newspaper |
author |
López-Vázquez, Vanesa López-Guede, José Manuel Marini, Simone Fanelli, Emanuela Johnsen, Espen Aguzzi, Jacopo |
author_facet |
López-Vázquez, Vanesa López-Guede, José Manuel Marini, Simone Fanelli, Emanuela Johnsen, Espen Aguzzi, Jacopo |
author_sort |
López-Vázquez, Vanesa |
title |
Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
title_short |
Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
title_full |
Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
title_fullStr |
Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
title_full_unstemmed |
Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories |
title_sort |
video image enhancement and machine learning pipeline for underwater animal detection and classification at cabled observatories |
publisher |
Molecular Diversity Preservation International |
publishDate |
2020 |
url |
http://hdl.handle.net/10261/201975 https://doi.org/10.3390/s20030726 https://doi.org/10.13039/501100011033 |
geographic |
Barents Sea Lofoten Norway |
geographic_facet |
Barents Sea Lofoten Norway |
genre |
Barents Sea Lofoten |
genre_facet |
Barents Sea Lofoten |
op_relation |
#PLACEHOLDER_PARENT_METADATA_VALUE# TEC2017-87861-R/AEI/10.13039/501100011033 info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TEC2017-87861-R https://doi.org/10.3390/s20030726 Sí issn: 1424-3210 e-issn: 1424-8220 Sensors 20(3): 726 (2020) CEX2019-000928-S http://hdl.handle.net/10261/201975 doi:10.3390/s20030726 http://dx.doi.org/10.13039/501100011033 32012976 |
op_rights |
open |
op_doi |
https://doi.org/10.3390/s2003072610.13039/501100011033 |
container_title |
Sensors |
container_volume |
20 |
container_issue |
3 |
container_start_page |
726 |
_version_ |
1790598417454465024 |