Efficient instance segmentation using deep learning for species identification in fish markets
Nahuel García-D’Urso, Alejandro Galán-Cuenca, Pau Climent-Pérez, Marcelo Saval-Calvo, Jorge Azorín-López, Andrés Fuster-Guilló
Abstract
The overexploitation of seas and oceans is a major problem that affects the world's fisheries. One of the main consequences is the loss of marine biodiversity that affects not only the ecosystem themselves but also the fishing industries. Nowadays, the fishing sector is immersed in a crucial process of digitization, as it is a traditional sector that lacks, among other things, complete, accurate, and reliable information on fish catches. Being able to know the species that arrive at fish markets can give stakeholders a detailed picture of the general health of the fisheries, as well as that of the populations of particular species of interest, to take appropriate actions. This paper presents an automated monitoring system of fish catches in fish markets based on computer vision and deep learning methods. Specifically, the system can identify instances of fish species based on Yolact models. Experiments have been performed comparing different network backbone architectures using the newly introduced DeepFish dataset for direct in-tray recognition,