Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.05032 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914906529333248 |
|---|---|
| author | de Carvalho, Daniel Ortega Monteiro, Luiz Felipe Teodoro Bazilio, Fernanda Marques Higa, Gabriel Toshio Hirokawa Pistori, Hemerson |
| author_facet | de Carvalho, Daniel Ortega Monteiro, Luiz Felipe Teodoro Bazilio, Fernanda Marques Higa, Gabriel Toshio Hirokawa Pistori, Hemerson |
| contents | 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% ($\pm 4.70$) with an extra large real time detection transformer, and 4.71% ($\pm 4.98$) with a medium-sized YOLOv8. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05032 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Livestock Fish Larvae Counting using DETR and YOLO based Deep Networks de Carvalho, Daniel Ortega Monteiro, Luiz Felipe Teodoro Bazilio, Fernanda Marques Higa, Gabriel Toshio Hirokawa Pistori, Hemerson Computer Vision and Pattern Recognition 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% ($\pm 4.70$) with an extra large real time detection transformer, and 4.71% ($\pm 4.98$) with a medium-sized YOLOv8. |
| title | Livestock Fish Larvae Counting using DETR and YOLO based Deep Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.05032 |