Portal de Periódicos da CAPES

Artigo Produção Nacional Revisado por pares

BIBTEX RIS

Deep learning applied in fish reproduction for counting larvae in images captured by smartphone

2022; Elsevier BV; Volume: 97; Linguagem: Inglês

10.1016/j.aquaeng.2022.102225

1873-5614

Celso Soares Costa, Vanda Alice Garcia Zanoni, Lucimar Rodrigues Vieira Curvo, Mário de Araújo Carvalho, Wilson Rogério Boscolo, Altevir Signor, Mauro dos Santos de Arruda, Higor Henrique Picoli Nucci, José Marcato, Wesley Nunes Gonçalves, Odair Diemer, Hemerson Pistori,

Fish biology, ecology, and behavior

We conducted an extensive and robust analysis of 28 convolutional neural networks (CNN) based methods for the detection and counting of tilapia larvae (Oreochromis niloticus niloticus (Linnaeus, 1758)) in Petri dishes. Experiments were carried out in the western region of Paraná, Brazil, using a smartphone, positioned in a prototype developed especially to support this application. A data set comprising 301 images and 6.195 larvae in the fish reproduction phase was built. These images were divided using cross-validation stratified into five folds. Among the evaluated methods considering 140 experiments, Faster R-CNN R50-FPN 2X and Grid R-CNN-X101–32X4d-FPN 2X provided the best results, with a mean average precision (mAP)50 97.30%. Given the wide availability of smartphones, we conclude that the presented procedure can be a valuable tool in detecting and counting tilapia larvae.