Livestock Fish Larvae Counting using DETR and YOLO based Deep Networks
DOI:
https://doi.org/10.22456/2175-2745.150926Keywords:
machine learning, transformers, convolutional neural networks, fish larvae, fish countingAbstract
Counting fish larvae is an important yet demanding task in aquaculture. In this work, we evaluate four neural networks, including convolutional and transformer-based architectures, in different sizes, in this counting task. We present a new annotated image dataset with less data collection requirements than preceding works, with images of spotted sorubim and dourado larvae. We also combined the neural networks with a tiling technique, in order to improve the counting performance, and performed a comprehensive experimental evaluation on the methods. 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. The results indicate the feasibility of using deep learning to count spotted sorubim and dourado larvae, which may become an important tool to enhance the efficiency of aquaculture farms that deal with these species.
Downloads
References
[1] BARBEDO, J. G. A. A review on the use of computer vision and artificial intelligence for fish recognition, monitoring, and management. Fishes, MDPI, v. 7, n. 6, p. 335, 2022.
[2] ZHAO, S. et al. Application of machine learning in intelligent fish aquaculture: A review. Aquaculture, Elsevier, v. 540, p. 736724, 2021.
[3] GONÇALVES, D. N. et al. Using a convolutional neural network for fingerling counting: A multi-task learning approach. Aquaculture, Elsevier, v. 557, p. 738334, 2022.
[4] COSTA, C. S. et al. Counting tilapia larvae using images captured by smartphones. Smart Agricultural Technology, Elsevier, v. 4, p. 100160, 2023.
[5] KHAI, T. H. et al. Underwater Fish Detection and Counting Using Mask Regional Convolutional Neural Network. Water, v. 14, n. 2, p. 222, 2022.
[6] YU, X. et al. Counting method for cultured fishes based on multi-modules and attention mechanism. Aquacultural Engineering, Elsevier, v. 96, p. 102215, 2022.
[7] LI, W. et al. A lightweight network for portable fry counting devices. Applied Soft Computing, Elsevier, v. 136, p. 110140, 2023.
[8] KAKEHI, S. et al. Identification and counting of pacific oyster Crassostrea gigas larvae by object detection using deep learning. Aquacultural Engineering, v. 95, p. 102197, 2021. ISSN 0144-8609.
[9] HU, W.-C. et al. A deep-learning-based fast counting methodology using density estimation for counting shrimp larvae. IEEE Sensors Journal, v. 23, n. 1, p. 527–535, 2023.
[10] LIU, D. et al. Shrimpseed net: Counting of shrimp seed using deep learning on smartphones for aquaculture. IEEE Access, v. 11, p. 85441–85450, 2023.
[11] ROTHSCHILD, C. et al. Computer vision system for counting crustacean larvae by detection. Smart Agricultural Technology, v. 5, p. 100289, 2023. ISSN 2772-3755.
[12] FERNANDES, M. P. et al. Convolutional neural networks in the inspection of serrasalmids (Characiformes) fingerlings. Animals, v. 14, n. 4, 2024. ISSN 2076-2615.
[13] BABU, K. M. et al. Computer vision in aquaculture: a case study of juvenile fish counting. Journal of the Royal Society of New Zealand, Taylor & Francis, v. 53, n. 1, p. 52–68, 2023.
[14] COSTA, C. S. et al. Deep learning applied in fish reproduction for counting larvae in images captured by smartphone. Aquacultural Engineering, v. 97, p. 102225, 2022. ISSN 0144-8609.
[15] JOCHER, G.; CHAURASIA, A.; QIU, J. YOLO by Ultralytics. 2023. URL: https://github.com/ultralytics/ultralytics.
[16] CARION, N. et al. End-to-end object detection with transformers. In: European Conference on Computer Vision. Springer, [S.l.], 2020.
[17] VASWANI, A. et al. Attention is all you need. Advances in Neural Information Processing Systems, v. 30, 2017.
[18] DOSOVITSKIY, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
[19] ZHU, X. et al. Deformable DETR: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159, 2020.
[20] LV, W. et al. DETRs Beat YOLOs on Real-time Object Detection. 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Daniel Ortega de Carvalho, Luiz Felipe Teodoro Monteiro, Fernanda Marques Bazilio, Gabriel Toshio Hirokawa Higa, Hemerson Pistori
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autorizo aos editores a publicação de meu artigo, caso seja aceito, em meio eletrônico de acordo com as regras do Public Knowledge Project.
