Image dataset for benchmarking automated fish detection and classification algorithms
Abstract Multiparametric video-cabled marine observatories are becoming strategic to monitor remotely and in real-time the marine ecosystem. Those platforms can achieve continuous, high-frequency and long-lasting image data sets that require automation in order to extract biological time series. The...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-022-01906-1 |
| _version_ | 1797958806813016064 |
|---|---|
| author | Marco Francescangeli Simone Marini Enoc Martínez Joaquín Del Río Daniel M. Toma Marc Nogueras Jacopo Aguzzi |
| author_facet | Marco Francescangeli Simone Marini Enoc Martínez Joaquín Del Río Daniel M. Toma Marc Nogueras Jacopo Aguzzi |
| author_sort | Marco Francescangeli |
| collection | DOAJ |
| description | Abstract Multiparametric video-cabled marine observatories are becoming strategic to monitor remotely and in real-time the marine ecosystem. Those platforms can achieve continuous, high-frequency and long-lasting image data sets that require automation in order to extract biological time series. The OBSEA, located at 4 km from Vilanova i la Geltrú at 20 m depth, was used to produce coastal fish time series continuously over the 24-h during 2013–2014. The image content of the photos was extracted via tagging, resulting in 69917 fish tags of 30 taxa identified. We also provided a meteorological and oceanographic dataset filtered by a quality control procedure to define real-world conditions affecting image quality. The tagged fish dataset can be of great importance to develop Artificial Intelligence routines for the automated identification and classification of fishes in extensive time-lapse image sets. |
| first_indexed | 2024-04-11T00:25:05Z |
| format | Article |
| id | doaj.art-6a5d9d600e3e4c8a92c125f20261eb58 |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-04-11T00:25:05Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-6a5d9d600e3e4c8a92c125f20261eb582023-01-08T12:04:31ZengNature PortfolioScientific Data2052-44632023-01-0110111310.1038/s41597-022-01906-1Image dataset for benchmarking automated fish detection and classification algorithmsMarco Francescangeli0Simone Marini1Enoc Martínez2Joaquín Del Río3Daniel M. Toma4Marc Nogueras5Jacopo Aguzzi6Electronics Department, Polytechnic University of Catalonia (UPC), Vilanova i la GeltrúInstitute of Marine Sciences, National Research Council of ItalyEuropean Multidisciplinary Seafloor and Water Column ObservatoryElectronics Department, Polytechnic University of Catalonia (UPC), Vilanova i la GeltrúElectronics Department, Polytechnic University of Catalonia (UPC), Vilanova i la GeltrúElectronics Department, Polytechnic University of Catalonia (UPC), Vilanova i la GeltrúStazione Zoologica Anton Dohrn (SZN)Abstract Multiparametric video-cabled marine observatories are becoming strategic to monitor remotely and in real-time the marine ecosystem. Those platforms can achieve continuous, high-frequency and long-lasting image data sets that require automation in order to extract biological time series. The OBSEA, located at 4 km from Vilanova i la Geltrú at 20 m depth, was used to produce coastal fish time series continuously over the 24-h during 2013–2014. The image content of the photos was extracted via tagging, resulting in 69917 fish tags of 30 taxa identified. We also provided a meteorological and oceanographic dataset filtered by a quality control procedure to define real-world conditions affecting image quality. The tagged fish dataset can be of great importance to develop Artificial Intelligence routines for the automated identification and classification of fishes in extensive time-lapse image sets.https://doi.org/10.1038/s41597-022-01906-1 |
| spellingShingle | Marco Francescangeli Simone Marini Enoc Martínez Joaquín Del Río Daniel M. Toma Marc Nogueras Jacopo Aguzzi Image dataset for benchmarking automated fish detection and classification algorithms Scientific Data |
| title | Image dataset for benchmarking automated fish detection and classification algorithms |
| title_full | Image dataset for benchmarking automated fish detection and classification algorithms |
| title_fullStr | Image dataset for benchmarking automated fish detection and classification algorithms |
| title_full_unstemmed | Image dataset for benchmarking automated fish detection and classification algorithms |
| title_short | Image dataset for benchmarking automated fish detection and classification algorithms |
| title_sort | image dataset for benchmarking automated fish detection and classification algorithms |
| url | https://doi.org/10.1038/s41597-022-01906-1 |
| work_keys_str_mv | AT marcofrancescangeli imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT simonemarini imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT enocmartinez imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT joaquindelrio imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT danielmtoma imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT marcnogueras imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms AT jacopoaguzzi imagedatasetforbenchmarkingautomatedfishdetectionandclassificationalgorithms |