Animal Bioscience

Asian Australasian Association of Animal Production Societies (아세아태평양축산학회)
권호 표지
DOI QR코드

DOI QR Code

Computer vision in precision livestock farming: artificial intelligence-driven technologies and applications for sustainable animal production

  • Thi Thi Zin (Graduate School of Engineering, University of Miyazaki) ;
  • Pyke Tin (Graduate School of Engineering, University of Miyazaki)
  • Received : 2026.03.04
  • Accepted : 2026.03.16
  • Published : 2026.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

The growing global demand for animal-derived food products is placing unprecedented pressure on livestock production systems to improve efficiency while also assuring animal welfare, environmental sustainability and economic viability. Precision livestock farming (PLF) has emerged as a transformative paradigm that integrates advanced sensing technologies, computer vision, internet of things infrastructures and artificial intelligence (AI) to enable continuous, automated and individualized animal monitoring. This paper explores the evolution of livestock management from conventional observation-based practices to sophisticated, data-driven architecture. It also synthesizes recent advancements in PLF emphasizing its system architecture, key applications in cattle production, cross-sector expansion and emerging challenges. The core architecture of PLF is structured into three functional layers: (i) data acquisition through multi-modal sensors, with a primary emphasis in this review on visual and environmental monitoring system; (ii) data analytics employing machine learning and deep learning techniques to establish behavioral and physiological baselines; and (iii) decision-support mechanisms that translate analytics into actionable farm management interventions. Major applications, including individual animal identification, body condition score estimation, lameness detection, calving time prediction and AI-powered health monitoring, are critically discussed. The extension of PLF principles to aquaculture and other livestock sectors is also discussed. By shifting from herd-level to individual-animal management, PLF provides a scalable, noninvasive approach for early disease detection, optimized resource utilization, improved welfare standards and long-term economic sustainability. The current limitations, including high capital investment, data interoperability challenges and model generalizability constraints, have been analyzed and future research directions emphasizing explainable AI and welfare-oriented system design have been proposed. Overall, PLF represents a systemic transformation of animal agriculture, allowing for data-driven, sustainable and welfare-centered production systems.

Keywords

Acknowledgement

We extend our heartfelt thanks to Associate Professor Dr. Ikuo Kobayashi from the Faculty of Agriculture at the University of Miyazaki for his invaluable guidance throughout this work. We are also grateful to K. Honkawa, D.V.M., for his full support during the study at the ranch and for his valuable advice. Our deepest gratitude goes to all the staff and members at the Kunneppu Demonstration Farm for their generous assistance and the outstanding support they provided for our research.

References

  1. Kaur U, Malacco VMR, Bai H, et al. Invited review: integration of technologies and systems for precision animal agriculture: a case study on precision dairy farming. J Anim Sci 2023;101:skad206. https://doi.org/10.1093/jas/skad206
  2. Schillings J, Bennett R, Rose DC. Exploring the potential of precision livestock farming technologies to help address farm animal welfare. Front Anim Sci 2021;2:639678. https://doi.org/10.3389/fanim.2021.639678
  3. Bernabucci G, Evangelista C, Girotti P, et al. Precision livestock farming: an overview on the application in extensive systems. Ital J Anim Sci 2025;24:859-84. https://doi.org/10.1080/1828051X.2025.2480821
  4. Neethirajan S, Kemp B. Digital livestock farming. Sens Biosens Res 2021;32:100408. https://doi.org/10.1016/j.sbsr.2021.100408
  5. Schaefer L. An emerging era of artificial intelligence research in agriculture. J Robot Spectr 2023;1:36-46. https://doi.org/10.53759/9852/JRS202301004
  6. Berckmans D. Precision livestock farming technologies for welfare management in intensive livestock systems. Rev Sci Tech 2014;33:189-96. https://doi.org/10.20506/rst.33.1.2273
  7. Papakonstantinou GI, Voulgarakis N, Terzidou G, Fotos L, Giamouri E, Papatsiros VG. Precision livestock farming technology: applications and challenges of animal welfare and climate change. Agriculture 2024;14:620. https://doi.org/10.3390/agriculture14040620
  8. Neethirajan S, Scott S, Mancini C, Boivin X, Strand E. Human-computer interactions with farm animals: enhancing welfare through precision livestock farming and artificial intelligence. Front Vet Sci 2024;11:1490851. https://doi.org/10.3389/fvets.2024.1490851
  9. Banhazi TM, Black JL. Precision livestock farming: a suite of electronic systems to ensure the application of best practice management on livestock farms. Aust J Multi-Discip Eng 2009;7:1-14. https://doi.org/10.1080/14488388.2009.11464794
  10. Zin TT, Pwint MZ, Seint PT, et al. Automatic cow location tracking system using ear tag visual analysis. Sensors 2020;20:3564. https://doi.org/10.3390/s20123564
  11. Kawagoe Y, Kobayashi I, Zin TT. Facial region analysis for individual identification of cows and feeding time estimation. Agriculture 2023;13:1016. https://doi.org/10.3390/agriculture13051016
  12. Mon SL, Onizuka T, Tin P, Aikawa M, Kobayashi I, Zin TT. AI-enhanced real-time cattle identification system through tracking across various environments. Sci Rep 2024;14:17779. https://doi.org/10.1038/s41598-024-68418-3
  13. Zin TT, Phyo CN, Tin P, Hama H, Kobayashi I. Image technology based cow identification system using deep learning. In: Proceedings of the International MultiConference of Engineers and Computer Scientists; 2018 Mar 14-16; Hong Kong. International MultiConference of Engineers and Computer Scientists; 2018. pp. 320-3.
  14. Kyaw PP, Tin P, Aikawa M, Kobayashi I, Zin TT. Automatic cattle identification system based on color point cloud using hybrid PointNet++ Siamese network. Sci Rep 2025;15:21938. https://doi.org/10.1038/s41598-025-08277-8
  15. Zin TT, Seint PT, Tin P, Horii Y, Kobayashi I. Body condition score estimation based on regression analysis using a 3D camera. Sensors 2020;20:3705. https://doi.org/10.3390/s20133705
  16. Imamura S, Zin TT, Kobayashi I, Horii Y. Automatic evaluation of cow's body-condition-score using 3D camera. In: Proceedings of the 2017 IEEE 6th Global Conference on Consumer Electronics (GCCE 2017); 2017 Oct 24-27; Nagoya, Japan. GCCE; 2017. pp. 104-5.
  17. Van Nuffel A, Zwertvaegher I, Pluym L, et al. Lameness detection in dairy cows: part 1. How to distinguish between non-lame and lame cows based on differences in locomotion or behavior. Animals 2015;5:838-60. https://doi.org/10.3390/ani5030387
  18. Meseret S. A review of poultry welfare in conventional production system [Internet]. Livestock Research for Rural Development; 2016. Available from: http://www.lrrd.org/lrrd28/12/mese28234.html
  19. Jiang B, Song H, Wang H, Li C. Dairy cow lameness detection using a back curvature feature. Comput Electron Agric 2022;194:106729. https://doi.org/10.1016/j.compag.2022.106729
  20. Arazo E, Aly R, McGuinness K. Segmentation enhanced lameness detection in dairy cows from RGB and depth video. arXiv:2206.04449 [Preprint]. 2022 [cited 2025 Mar 1]. https://doi.org/10.48550/arXiv.2206.04449
  21. Tun SC, Onizuka T, Tin P, Aikawa M, Kobayashi I, Zin TT. Revolutionizing cow welfare monitoring: a novel top-view perspective with depth camera-based lameness classification. J Imaging 2024;10:67. https://doi.org/10.3390/jimaging10030067
  22. Zin TT, Tin P. Quantifying body movement variability for cattle lameness detection using depth imaging. ICIC Express Lett B Appl 2023;14:735-45. https://doi.org/10.24507/icicelb.14.07.735
  23. Onizuka T, Zin TT, Kobayashi I. A non-invasive method for lameness detection in dairy cows using RGB cameras. ICIC Express Lett B Appl 2023;14:1107-14. https://doi.org/10.24507/icicelb.14.10.1107
  24. Mee JF. Why do so many calves die on modern dairy farms and what can we do about calf welfare in the future. Animal 2013;3:1036-57. https://doi.org/10.3390/ani3041036
  25. Streyl D, Sauter-Louis C, Braunert A, Lange D, Weber F, Zerbe H. Establishment of a standard operating procedure for predicting the time of calving in cattle. J Vet Sci 2011;12:177-85. https://doi.org/10.4142/jvs.2011.12.2.177
  26. Mee JF, Berry DP, Cromie AR. Risk factors for calving assistance and dystocia in pasture-based Holstein–Friesian heifers and cows in Ireland. Vet J 2011;187:189-94. https://doi.org/10.1016/j.tvjl.2009.11.018
  27. Jensen MB. Behaviour around the time of calving in dairy cows. Appl Anim Behav Sci 2012;139:195-202. https://doi.org/10.1016/j.applanim.2012.04.002
  28. Maw SZ, Zin TT, Tin P, Kobayashi I, Horii Y. An absorbing Markov chain model to predict dairy cow calving time. Sensors 2021;21:6490. https://doi.org/10.3390/s21196490
  29. Sumi K, Zin TT, Kobayashi I, Horii Y. Framework of cow calving monitoring system using a single depth camera. In: Proceedings of the 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ); 2018 Nov 19-21; Auckland, New Zealand. IVCNZ; 2018. pp. 1-7.
  30. Sumi K, Maw SZ, Zin TT, Tin P, Kobayashi I, Horii Y. Activity-integrated hidden Markov model to predict calving time. Animals 2021;11:385. https://doi.org/10.3390/ani11020385
  31. Khin MP, Tin P, Horii Y, Zin TT. Predictive modeling of cattle calving time emphasizing abnormal and normal cases by using posture analysis. Sci Rep 2024;14:31871. https://doi.org/10.1038/s41598-024-83279-6
  32. Mg WHE, Zin TT, Tin P, Aikawa M, Honkawa K, Horii Y. Automated system for calving time prediction and cattle classification utilizing trajectory data and movement features. Sci Rep 2025;15:2378. https://doi.org/10.1038/s41598-025-85932-0
  33. Mg WHE, Zin TT, Tin P, Aikawa M, Honkawa K, Horii Y. Automated cattle monitoring system for calving time prediction using trajectory data embedded time series analysis. IEEE Open J Ind Electron Soc 2025;6:216-34. https://doi.org/10.1109/OJIES.2025.3533663
  34. Mg WHE, Tin P, Aikawa M, Honkawa K, Horii Y, Zin TT. Signal-based feature analysis of behavioral trajectories for predicting calving time and classifying assistance needs. Comput Electron Agric 2026;243:111301. https://doi.org/10.1016/j.compag.2025.111301
  35. Moe AST, Tin P, Aikawa M, Kobayashi I, Zin TT. AI-powered visual E-monitoring system for cattle health and wealth. Smart Agric Technol 2025;12:101300. https://doi.org/10.1016/j.atech.2025.101300