An Edge-Deployable YOLOv8 System for Real-Time Detection of Health and Behavioural Abnormalities in Poultry Farming

Authors

  • Dr. K. Jayanthi Associate Professor and Head, Department of Computer Science, Government Arts and Science College, Kangeyam Author
  • Mr. S. Dilip kumar Author

DOI:

https://doi.org/10.63300/

Abstract

Poultry farming is an important part of the food industry, but keeping track of the health and behavior of birds can be difficult, especially on large farms. This project presents a real-time object detection system using YOLOv8, a deep learning model known for its speed and accuracy. The system is trained to recognize various conditions in poultry, such as weak legs, abnormal movements, crowding, and feeding habits, by analyzing images taken from the farm environment. With YOLOv8, farmers can monitor their birds continuously through cameras and get instant alerts when something unusual is detected. The model is efficient enough to run on mobile or edge devices, making it practical for real-world farm use. This approach can help farmers detect problems early, reduce losses, and improve overall poultry health and farm productivity.

Downloads

Download data is not yet available.

Author Biographies

  • Dr. K. Jayanthi, Associate Professor and Head, Department of Computer Science, Government Arts and Science College, Kangeyam

    Dr. K. Jayanthi, Associate Professor and Head, Department of Computer Science, Government Arts and Science College, Kangeyam. E-mail: jaysureshlaya@gmail.com

  • Mr. S. Dilip kumar

    Mr. S. Dilip kumar, Assistant Professor, Department of Computer Applications, Nallamuthu Gounder Mahalingam College, Pollachi. E-mail: dilipkumarcontact@gmail.com

References

[1]. Nasirahmadi, A., Edwards, S. A., & Sturm, B. (2017). Automation in animal farming: A review of image processing techniques. Computers and Electronics in Agriculture, 142, 369–383. https://doi.org/10.1016/j.compag.2017.05.017

[2]. Liu, Y., et al. (2024). Multi-Stage YOLO Frameworks for Simultaneous Detection of Avian Diseases and Behavioural Anomalies. Journal of Smart Agriculture Systems, 12(2), 45–58.

[3]. Rahman, M. M., & Tasnim, S. (2022). Detection of Weak Leg Syndrome in Broiler Chickens Using Deep Learning. International Journal of Poultry Science, 21(1), 10–17.

[4]. Sharma, A., et al. (2021). Vision-based monitoring systems for livestock and poultry: A review of the state-of-the-art. Artificial Intelligence in Agriculture, 5, 1–14.

[5]. Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767. https://arxiv.org/abs/1804.02767

[6]. Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934. https://arxiv.org/abs/2004.10934

[7]. Mollah, M. B., et al. (2022). A review on automated poultry disease detection techniques. Computers in Biology and Medicine, 143, 105250. https://doi.org/10.1016/j.compbiomed.2022.105250

[8]. Jocher, G., et al. (2023). YOLOv8: State-of-the-art real-time object detection. Ultralytics Technical Report.

[9]. Ning, Z., Wang, X., Hu, X., & Cheng, J. (2019). Edge computing in intelligent poultry farming: A survey. IEEE Internet of Things Journal, 6(3), 5741–5751. https://doi.org/10.1109/JIOT.2019.2904798

[10]. Deep Learning approach in detecting Marek’s Disease in Poultry chicken using YOLOv10 with Generative Adversarial Networks. (2024). African Journal of Biological Sciences, 6(15). https://doi.org/10.48047/afjbs.6.15.2024.1815-1826

Downloads

Published

2025-08-01

How to Cite

An Edge-Deployable YOLOv8 System for Real-Time Detection of Health and Behavioural Abnormalities in Poultry Farming. (2025). Academic Research Journal of Science and Technology (ARJST), 2(02), 27-36. https://doi.org/10.63300/