Counting fish larvae is an important, yet demanding and time consuming, task in aquaculture. In order to address this problem, in this work, we evaluate four neural network architectures, including convolutional neural networks and transformers, in different sizes, in the task of fish larvae counting. For the evaluation, we present a new annotated image dataset with less data collection requirements than preceding works, with images of spotted sorubim and dourado larvae. By using image tiling techniques, we achieve a MAPE of 4.46% (±4.70) with an extra large real time detection transformer, and 4.71% (±4.98) with a medium-sized YOLOv8.
Cite
@article{arxiv.2408.05032,
title = {Livestock Fish Larvae Counting using DETR and YOLO based Deep Networks},
author = {Daniel Ortega de Carvalho and Luiz Felipe Teodoro Monteiro and Fernanda Marques Bazilio and Gabriel Toshio Hirokawa Higa and Hemerson Pistori},
journal= {arXiv preprint arXiv:2408.05032},
year = {2024}
}