Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories
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 info...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/s20030726 https://doaj.org/article/8c2f848e69994718b5dbcb4904a14e7c |
id |
ftdoajarticles:oai:doaj.org/article:8c2f848e69994718b5dbcb4904a14e7c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:8c2f848e69994718b5dbcb4904a14e7c 2023-05-15T15:39:05+02:00 Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories Vanesa Lopez-Vazquez Jose Manuel Lopez-Guede Simone Marini Emanuela Fanelli Espen Johnsen Jacopo Aguzzi 2020-01-01T00:00:00Z https://doi.org/10.3390/s20030726 https://doaj.org/article/8c2f848e69994718b5dbcb4904a14e7c EN eng MDPI AG https://www.mdpi.com/1424-8220/20/3/726 https://doaj.org/toc/1424-8220 1424-8220 doi:10.3390/s20030726 https://doaj.org/article/8c2f848e69994718b5dbcb4904a14e7c Sensors, Vol 20, Iss 3, p 726 (2020) cabled observatories artificial intelligence deep learning machine learning deep-sea fauna Chemical technology TP1-1185 article 2020 ftdoajarticles https://doi.org/10.3390/s20030726 2022-12-30T20:04:45Z 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%. Article in Journal/Newspaper Barents Sea Lofoten Directory of Open Access Journals: DOAJ Articles Barents Sea Lofoten Norway Sensors 20 3 726 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
cabled observatories artificial intelligence deep learning machine learning deep-sea fauna Chemical technology TP1-1185 |
spellingShingle |
cabled observatories artificial intelligence deep learning machine learning deep-sea fauna Chemical technology TP1-1185 Vanesa Lopez-Vazquez Jose Manuel Lopez-Guede Simone Marini Emanuela Fanelli Espen Johnsen Jacopo Aguzzi 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 Chemical technology TP1-1185 |
description |
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%. |
format |
Article in Journal/Newspaper |
author |
Vanesa Lopez-Vazquez Jose Manuel Lopez-Guede Simone Marini Emanuela Fanelli Espen Johnsen Jacopo Aguzzi |
author_facet |
Vanesa Lopez-Vazquez Jose Manuel Lopez-Guede Simone Marini Emanuela Fanelli Espen Johnsen Jacopo Aguzzi |
author_sort |
Vanesa Lopez-Vazquez |
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 |
MDPI AG |
publishDate |
2020 |
url |
https://doi.org/10.3390/s20030726 https://doaj.org/article/8c2f848e69994718b5dbcb4904a14e7c |
geographic |
Barents Sea Lofoten Norway |
geographic_facet |
Barents Sea Lofoten Norway |
genre |
Barents Sea Lofoten |
genre_facet |
Barents Sea Lofoten |
op_source |
Sensors, Vol 20, Iss 3, p 726 (2020) |
op_relation |
https://www.mdpi.com/1424-8220/20/3/726 https://doaj.org/toc/1424-8220 1424-8220 doi:10.3390/s20030726 https://doaj.org/article/8c2f848e69994718b5dbcb4904a14e7c |
op_doi |
https://doi.org/10.3390/s20030726 |
container_title |
Sensors |
container_volume |
20 |
container_issue |
3 |
container_start_page |
726 |
_version_ |
1766370524091383808 |