Acoustic video cameras multi-species multi-cameras Training Dataset (TD) for Deep Learning applications

• Main Authors: Fernandez Garcia, Guglielmo, Martignac, François
• Format: Dataset
• Language: unknown
• Published: 2021
• Subjects: acoustic camera video; deep learning; training dataset; sonar camera; ARIS; DIDSON; Freshwater fish; Aris; Atlantic salmon; European eel
• Online Access: https://zenodo.org/record/5046708; https://doi.org/10.5281/zenodo.5046708

This images dataset, called also TD (Training Dataset), is designed to train/test/validate 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, formatted in the yolo-darknet format as explained in https://github.com/AlexeyAB/darknet, includes also a large number of images without any fish passage, in order to test the effect of negative data on the trainings.