Poultry Detection on Hooks in Meat Processing Plant Production Lines

Leonardo dos Santos Valejo; Marlon Marcon; André Roberto Ortoncelli

doi:10.22456/2175-2745.150924

Authors

Leonardo dos Santos Valejo Universidade Tecnólogia Federal do Paraná (UTFPR)
Marlon Marcon Universidade Tecnólogia Federal do Paraná (UTFPR) https://orcid.org/0000-0002-3698-8570
André Roberto Ortoncelli Universidade Tecnológica Federal do Paraná (UTFPR) https://orcid.org/0000-0001-9622-8525

DOI:

https://doi.org/10.22456/2175-2745.150924

Keywords:

poultry detection, object detection, deep learning, YOLO

Abstract

This study focuses on automating chicken production monitoring in a meatpacking plant, applying YOLO to detect birds on hooks on production lines. We detect two objects in authentic images: a chicken (birds hanging on the hook) and a hook (the metal support structure). By counting these objects in videos, we can monitor daily production and identify faults on the production line. We annotated 400 images for the experiment and used 320 to train seven YOLO versions, including lightweight variants (nano, tiny, and small) optimized for low-end devices. In testing, YOLOv9-tiny achieved 0.9967 precision but had lower recall than other experimental instances. YOLOv11-nano achieved an F1-score of 0.9924 and a mAP@50 of 0.9947, standing out in detection quality. Despite minor differences, the results were close for the YOLO versions analyzed, demonstrating a considerable ability to predict the analyzed objects.

Downloads

Download data is not yet available.

References

[1] BASSI, N. S. S.; SILVA, C. L. Oportunidades e desafios em PD&I na cadeia produtiva de frangos de corte. Agropensa, Embrapa Suínos e Aves; Universidade Tecnológica Federal do Paraná (UTFPR), 2017.

[2]UMURUNGI, S. N. et al. Leveraging the potential of convolutional neural networks in poultry farming: a 5-year overview. World’s Poultry Science Journal, Taylor & Francis, v. 81, n. 1, p. 3–34, 2025.

[3] YE, C.-W. et al. Broiler stunned state detection based on an improved fast region-based convolutional neural network algorithm. Poultry Science, Elsevier, v. 99, n. 1, p. 637–646, 2020.

[4] SILVA, H. R. D.; WEIZENMAN, G. D. S.; MUTZENBERG, R. Algoritmo para reconhecimento automatizado de defeitos em frangos de linha de produção utilizando visão computacional. In: Congresso Brasileiro de Automática – CBA. [S.l.: s.n.], 2019. v. 1, n. 1.

[5] CHEN, Y. et al. Machine vision on the positioning accuracy evaluation of poultry viscera in the automatic evisceration robot system. International Journal of Food Properties, Taylor & Francis, v. 24, n. 1, p. 933–943, 2021.

[6] JIAN, R. et al. Nondestructive freshness recognition of chicken breast meat based on deep learning. Scientific Reports, Nature Publishing Group UK London, v. 15, n. 1, p. 27538, 2025.

[7] ALI, M. L.; ZHANG, Z. The YOLO framework: a comprehensive review of evolution, applications, and benchmarks in object detection. Computers, MDPI, v. 13, n. 12, p. 336, 2024.

[8] WONG, A. et al. YOLO Nano: a highly compact You Only Look Once convolutional neural network for object detection. In: IEEE Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing – NeurIPS Edition (EMC2-NIPS). [S.l.: s.n.], 2019. p. 22–25.

[9] MOHAMMED, S. Y. Architecture review: two-stage and one-stage object detection. Franklin Open, Elsevier, p. 100322, 2025.

[10] GIRSHICK, R. et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [S.l.: s.n.], 2014. p. 580–587.

[11] PRIYADHARSHINI, G.; DOLLY, D. R. J. Comparative investigations on tomato leaf disease detection and classification using CNN, R-CNN, Fast R-CNN and Faster R-CNN. In: IEEE International Conference on Advanced Computing and Communication Systems (ICACCS). [S.l.: s.n.], 2023. v. 1, p. 1540–1545.

[12] REDMON, J. et al. You Only Look Once: Unified, Real-Time Object Detection. 2016.

[13] HUA, Z. et al. A benchmark review of YOLO algorithm developments for object detection. IEEE Access, IEEE, 2025.

[14] KOIRALA, A. et al. Deep learning – method overview and review of use for fruit detection and yield estimation. Computers and Electronics in Agriculture, Elsevier, v. 162, p. 219–234, 2019.

[15] REDDY, D. J. et al. Wild bird detection on airborne imagery using modified YOLO network. In: SPRINGER International Conference on Information and Management Engineering. [S.l.: s.n.], 2023. p. 9–23.

[16] JIANG, D. et al. Real-time tracker of chicken for poultry based on attention mechanism–enhanced YOLO-Chicken algorithm. Computers and Electronics in Agriculture, Elsevier, v. 237, p. 110640, 2025.

[17] LIMA, I. C. R. et al. Analyzing bee behavior through video tracking using computer vision techniques. In: SBC Workshop de Visão Computacional (WVC). [S.l.: s.n.], 2024. p. 280–286.

[18] LEMOS, D. V. X. et al. YOLO and CNN for cat detection and recognition. Revista de Informática Teórica e Aplicada, v. 32, n. 1, p. 158–165, 2025.

[19] MARTINS, T. M. et al. Detection of cacao trees in orthomosaic images using YOLOv8 and SAHI. In: SBC Workshop de Visão Computacional (WVC). [S.l.: s.n.], 2024. p. 37–41.

[20] SEIDEL, R.; WAIANDT, C. A.; JÚNIOR, H. S. Defect detection in textile manufacturing: improving findings using YOLOv5 versions. In: SBC Workshop de Visão Computacional (WVC). [S.l.: s.n.], 2023. p. 66–71.

[21] RAGAB, M. G. et al. A comprehensive systematic review of YOLO for medical object detection (2018 to 2023). IEEE Access, IEEE, v. 12, p. 57815–57836, 2024.

[22] HUSSAIN, M. YOLOv5, YOLOv8 and YOLOv10: the go-to detectors for real-time vision. arXiv preprint arXiv:2407.02988, 2024.

[23] SOHAN, M.; RAM, T. S.; REDDY, C. V. R. A review on YOLOv8 and its advancements. In: SPRINGER International Conference on Data Intelligence and Cognitive Informatics. [S.l.: s.n.], 2024. p. 529–545.

[24] YASEEN, M. What is YOLOv9: an in-depth exploration of the internal features of the next-generation object detector. arXiv preprint arXiv:2409.07813, 2024.

[25] WANG, A. et al. YOLOv10: real-time end-to-end object detection. Advances in Neural Information Processing Systems, v. 37, p. 107984–108011, 2024.

[26] KHANAM, R.; HUSSAIN, M. YOLOv11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725, 2024.

[27] TIAN, Y.; YE, Q.; DOERMANN, D. YOLOv12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524, 2025.

[28] SUBRAMANI, T.; JEGANATHAN, V.; BALASUBRAMANIAN, S. K. Machine learning and deep learning techniques for poultry tasks management: a review. Multimedia Tools and Applications, Springer, v. 84, n. 2, p. 603–645, 2025.

[29] AZIZ, N. S. N. A. et al. A review on computer vision technology for monitoring poultry farm—application, hardware, and software. IEEE Access, IEEE, v. 9, p. 12431–12445, 2020.

[30] CHAO, K. et al. Hyperspectral–multispectral line-scan imaging system for automated poultry carcass inspection applications for food safety. Poultry Science, Elsevier, v. 86, n. 11, p. 2450–2460, 2007.

[31] LI, Z. et al. Channel pruned YOLOv5-based deep learning approach for rapid and accurate outdoor obstacles detection. arXiv preprint arXiv:2204.13699, 2022.

[32] LYU, Z. et al. A survey of model compression strategies for object detection. Multimedia Tools and Applications, Springer, v. 83, n. 16, p. 48165–48236, 2024.