The Gloria2 fish farm escapes identification dataset (v1.0)
- Climent-Pérez, Pau 1
- V. Montalt, Adrián 2
- Giménez-Méndez, Aarón 1
- Valero-Rodriguez, J.M. 2
- Azorín-López, Jorge 1
- Fuster-Guilló, Andrés 1
- Toledo-Guedes, Kilian 2
Abstract
This is version 1.0 of the <strong>GLORiA<sup>2</sup> dataset</strong>, which can be used for the training of computer vision models aimed at <strong>detecting fish farm escapes caused by sea storms</strong>. Escaped fish can be recognized based on their appearance from pictures taken in lab conditions, when compared to farmed and wild specimens. Several images of fish specimens raised in <strong>captivity</strong> (C), farm <strong>escapes</strong> (E), and the <strong>sea</strong> (S) are provided for each of the <strong>three</strong> considered commercial <strong>species</strong>: Mediterranean <strong>sea bream</strong> (<em>S. aurata</em>), <strong>sea bass</strong> (<em>D. labrax</em>), and <strong>meagre</strong> (<em>A. regius</em>). The images provided are 224x224 crops of the original images, centred around the fish in the image, as <strong>preprocessed</strong> by the <strong>accompanying Python scripts</strong>. <strong>Acknowledgement: </strong>GLORiA<sup>2</sup> is a project supported by the Biodiversity Foundation of the Ministry for the Ecological Transition, through the FEMP Pleamar Programme. It is also part of the LIFE IP INTEMARES project "Integrated, innovative and participatory management of the Natura 2000 Network in the Spanish marine environment", coordinated by the Ministry, through the Biodiversity Foundation.