Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications
This video dataset, called also VD (Validation Dataset), is designed to test/validate, on a real-world case, deep learning models to identify fish species in sonar camers video flux. It includes data from two different type of cameras (ARIS and DIDSON), two sites (Touques and Selune rivers in Norman...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Zenodo
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.5281/zenodo.5092009 https://zenodo.org/record/5092009 |
id |
ftdatacite:10.5281/zenodo.5092009 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.5281/zenodo.5092009 2023-05-15T15:32:07+02:00 Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications Fernandez Garcia, Guglielmo Martignac, Fraçois 2021 https://dx.doi.org/10.5281/zenodo.5092009 https://zenodo.org/record/5092009 unknown Zenodo https://dx.doi.org/10.5281/zenodo.5092010 Open Access Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 info:eu-repo/semantics/openAccess CC-BY deep learning ARIS DIDSON sonar camera acoustic camera video freshwater fish MediaObject article Audiovisual 2021 ftdatacite https://doi.org/10.5281/zenodo.5092009 https://doi.org/10.5281/zenodo.5092010 2021-11-05T12:55:41Z This video dataset, called also VD (Validation Dataset), is designed to test/validate, on a real-world case, deep learning models to identify fish species in sonar camers video flux. It includes data from two different type of cameras (ARIS and DIDSON), two sites (Touques and Selune rivers in Normandy, France), 6 different fishes classes (Atlantic Salmon, European Eel, Sea Lamprey, Allis Shad, European Catfish and generic unidentified fish). This dataset is composed by around 40h of videos, to test the efficiency of the models in the frame of ecological studies and to assess their real-applicability on monitoring sites data. Two sheets are given as the ground truth in which all fish passages (for fish sizes larger than 20 cm) are annotated. No bounding boxes are given. Article in Journal/Newspaper Atlantic salmon European eel DataCite Metadata Store (German National Library of Science and Technology) Aris ENVELOPE(-61.400,-61.400,-70.633,-70.633) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
deep learning ARIS DIDSON sonar camera acoustic camera video freshwater fish |
spellingShingle |
deep learning ARIS DIDSON sonar camera acoustic camera video freshwater fish Fernandez Garcia, Guglielmo Martignac, Fraçois Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
topic_facet |
deep learning ARIS DIDSON sonar camera acoustic camera video freshwater fish |
description |
This video dataset, called also VD (Validation Dataset), is designed to test/validate, on a real-world case, deep learning models to identify fish species in sonar camers video flux. It includes data from two different type of cameras (ARIS and DIDSON), two sites (Touques and Selune rivers in Normandy, France), 6 different fishes classes (Atlantic Salmon, European Eel, Sea Lamprey, Allis Shad, European Catfish and generic unidentified fish). This dataset is composed by around 40h of videos, to test the efficiency of the models in the frame of ecological studies and to assess their real-applicability on monitoring sites data. Two sheets are given as the ground truth in which all fish passages (for fish sizes larger than 20 cm) are annotated. No bounding boxes are given. |
format |
Article in Journal/Newspaper |
author |
Fernandez Garcia, Guglielmo Martignac, Fraçois |
author_facet |
Fernandez Garcia, Guglielmo Martignac, Fraçois |
author_sort |
Fernandez Garcia, Guglielmo |
title |
Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
title_short |
Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
title_full |
Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
title_fullStr |
Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
title_full_unstemmed |
Acoustic video cameras multi-species multi-cameras Validation Dataset (VD) for Deep Learning applications |
title_sort |
acoustic video cameras multi-species multi-cameras validation dataset (vd) for deep learning applications |
publisher |
Zenodo |
publishDate |
2021 |
url |
https://dx.doi.org/10.5281/zenodo.5092009 https://zenodo.org/record/5092009 |
long_lat |
ENVELOPE(-61.400,-61.400,-70.633,-70.633) |
geographic |
Aris |
geographic_facet |
Aris |
genre |
Atlantic salmon European eel |
genre_facet |
Atlantic salmon European eel |
op_relation |
https://dx.doi.org/10.5281/zenodo.5092010 |
op_rights |
Open Access Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.5281/zenodo.5092009 https://doi.org/10.5281/zenodo.5092010 |
_version_ |
1766362623758041088 |