Image dataset for benchmarking automated fish detection and classification algorithms

• Published in: Scientific data 2023-01, Vol.10 (1), p.5-5, Article 5
• Main Authors: Francescangeli, Marco, Marini, Simone, Martínez, Enoc, Del Río, Joaquín, Toma, Daniel M., Nogueras, Marc, Aguzzi, Jacopo
• Format: Article
• Language: English
• Subjects: 631/158/2445; 631/1647/245/2186; 704/158/1745; 704/829/826; Algorithms; Animals; Artificial Intelligence; Automation; Benchmarking; Cameras; Classification; Climate change; Coasts; Commercial fishing; Data Descriptor; Datasets; Ecosystem; Environmental conditions; Fish; Fishes; Humanities and Social Sciences; Marine ecosystems; multidisciplinary; Observatories; Quality control; Salinity; Science; Science (multidisciplinary); Time series
• ISSN: 2052-4463; 2052-4463
• DOI: 10.1038/s41597-022-01906-1

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.