Broiler Live Weight Estimation through Image Processing and YOLO-based Deep Learning

Year 2026, Volume: 32 Issue: 2, 317 - 335, 24.03.2026

Hamza Kuzu , Ali Aybek , Hayrettin Karadöl , Adem Tekerek

https://doi.org/10.15832/ankutbd.1761039

https://izlik.org/JA36NS74YX

Abstract

This study aims to estimate the live weight of broilers using image processing and deep learning techniques. The proposed method is designed to optimize management processes in broiler production systems, reduce labor requirements and operational costs, minimize animal stress caused by direct human contact, and serve as an effective alternative to traditional manual weighing practices. The study was conducted at a commercial broiler farm located in Kahramanmaraş, in the Mediterranean region of Türkiye. An automatically controlled measurement enclosure was constructed to capture broiler images with minimal human intervention. Digital cameras mounted at the top of the enclosure recorded images of broilers that spontaneously entered the enclosure. By using these images, live weight estimation was carried out in two stages: the first stage involved morphological image processing in the MATLAB environment, while the second stage focused on deep learning-based modeling for prediction. During the image processing stage, multiple regression analysis was performed using the actual weights obtained through manual weighing and the estimated weights derived from image-based measurements. The analysis resulted in an adjusted R² value of 0.97 and a standard error of ± 131 g (P<0.01). The mean absolute error (MAE) was calculated as 84.4 g, while the mean relative error (MRE) was found to be 7.6%. In the deep learning stage, the YOLOv8 model was trained for 150 and 500 epochs. Notable improvements in both accuracy and generalization capability were observed after 500 epochs. Under these conditions, the model achieved a high mean Average Precision (mAP) of 0.969, with substantial increases in precision, recall, and F1-score across all 17 predefined broiler live weight classes. Furthermore, regression-based performance indicators were approximated from the class-based predictions to enable a quantitative assessment of weight estimation accuracy. Based on this indirect evaluation, the proposed model achieved an estimated MAE of 37.0 g and MRE of 4.43%. Overall, the findings suggest that the proposed framework has strong potential for adaptation to live weight prediction in other livestock species. 

Keywords

Broiler , live weight estimation , image processing , YOLO

Project Number

2020/9-26D

References

• Alkan A (2024). Predicting students' performance in exams with machine learning techniques. Osmaniye Korkut Ata University Journal of the Institute of Science and Technology 7(3): 1116-1128 (In Turkish). https://doi.org/10.47495/okufbed.1420959.
• Amraei S, Mehdizadeh S A & Nääs I D A (2018). Development of a transfer function for weight prediction of live broiler chicken using machine vision. Engenharia Agrícola 38(5): 776-782. https://doi.org/10.1590/1809-4430-Eng.Agric.v38n5p776-782/2018.
• Amraei S, Mehdizadeh S A & Salari S (2017a). Broiler weight estimation based on machine vision and artificial neural network. British Poultry Science 58(2): 200-205. https://doi.org/10.1080/00071668.2016.1259530.
• Amraei S, Mehdizadeh S A & Sallary S (2017b). Application of computer vision and support vector regression for weight prediction of live broiler chicken. Engineering in Agriculture, Environment and Food 10(4): 266-271. https://doi.org/10.1016/j.eaef.2017.04.003.
• Blokhuis H J, Van Der Haar J W & Fuchs J M M (1988). Do weighing figures represent the flock average? Poultry International 4(5): 17-19. https://doi.org/doi/full/10.5555/19882437712.
• Buda M, Maki A & Mazurowski M A (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks 106: 249-259. https://doi.org/10.1016/j.neunet.2018.07.0111.
• Campbell M, Miller P, Díaz-Chito K, Irvine S & Baxter M (2025). Automated precision weighing: leveraging 2D video feature analysis and machine learning for live body weight estimation of broiler chickens. Smart Agricultural Technology 10: 100793. https://doi.org/10.1016/j.atech.2025.100793.
• Chedad A, Aerts J M, Vranken E, Lippens M & Zoons J (2003). Do heavy broiler chickens visit automatic weighing systems less than lighter birds? British Poultry Science 44(5): 663-668. https://doi.org/10.1080/00071660310001643633.
• De Wet L, Vranken E, Chedad A, Aerts J M & Ceunen J (2003). Computer-assisted image analysis to quantify daily growth rates of broiler chickens. British Poultry Science 44 (4): 524-532. https://doi.org/10.1080/00071660310001616192.
• Doyle I & Leeson S (1989). Automatic weighing of poultry reared on a litter floor. Canadian Journal of Animal Science 69(4): 1075-1081. https://doi.org/10.4141/cjas89-122.
• Electra J, Ajidarma P & Isnaini M M (2022). Broiler chicken weight estimation model design using image processing approach. In: 3rd Asia Pacific International Conference on Industrial Engineering and Operations Management; Johor Bahru, Malaysia. pp. 13-15. https://doi.org/10.46254/AP03.20220329.
• Elmessery W M, Gutiérrez J, Abd El-Wahhab G G, Elkhaiat I A & El-Soaly I S (2023). YOLO-Based Model for Automatic Detection of Broiler Pathological Phenomena through Visual and Thermal Images in Intensive Poultry Houses. Agriculture, 13(8): 1527. https://doi.org/10.3390/agriculture13081527.
• Erdoğan M (2023). Machine learning classification models [online]. Website https://medium.com/academy team/makine-%C3%B6%C4%9Frenmesi-s%C4%B1n%C4%B1fland%C4%B1rma-modelleri-accuracy-precission-recall-f1-score-log loss-and-e2c37fbcf285 (In Turkish) [accessed 26 November 2024].
• Feighner S D, Godowsky E F & Miller B M (1986). Portable microcomputer based weighing systems: applications in poultry science. Poultry Science 65 (5): 868-873. https://doi.org/10.3382/ps.0650868.
• Flood C A, Koon J L, Trumbull R D & Brewer R N (1992). Broiler growth data: 1986-1991. Transactions of the ASAE 35(2): 703-709. https://doi.org/10.13031/2013.28652.
• GHI (2014). Global revolutions in agriculture: the challenge and promise of 2050. Global Agricultural Productivity Report. Global Harvest Initiative [online]. Website https://globalagriculturalproductivity.org/wp-content/uploads/2019/01/2014_GAP_Report.pdf [accessed 20 February 2025].
• Goodfellow I, Bengio Y & Courville A (2016). Deep learning. The MIT Press, Cambridge, MA, USA. http://www.deeplearningbook.org. HSUS (2010). The welfare of animals in the pig industry. The Humane Society of the United States [online]. Website https://www.humaneworld.org/sites/default/files/docs/hsus-report-pig-industry-welfare.pdf [accessed 23 February 2025].
• Jocher G, Chaurasia A & Qiu J (2023). YOLO by ultralytics. GitHub repository. https://github.com/ultralytics/ultralytics.
• Johnson J M & Khoshgoftaar T M (2019). Survey on deep learning with class imbalance. Journal of Big Data 6(1): 1-54. https://doi.org/10.1186/s40537-019-0192-5.
• Jorgensen A, Dueholm J V, Fagertun J & Moeslund T B (2019). Weight estimation of broilers in images using 3D prior knowledge. Lecture Notes in Computer Science 11482: 221-232. https://doi.org/10.1007/978-3-030-20205-7_19.
• Khan A, Sohail A, Zahoora U & Qureshi A S (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review 53(8): 5455-5516. https://doi.org/10.1007/s10462-018-9633-3.
• LeCun, Y, Bengio Y & Hinton G (2015). Deep learning. Nature 521: 436-444. https://doi.org/10.1038/nature14539.
• Li X, Wu J, Zhao Z, Zhuang Y & Sun S (2023). An improved method for broiler weight estimation integrating multi-feature with gradient boosting decision tree. Animals 13(23): 3721. https://doi.org/10.3390/ani13233721.
• Lott B D, Reece F N & McNaughton J L (1982). An automated weighing systemic for use in poultry research. Poultry Science 61(2): 236-238. https://doi.org/10.3382/ps.0610236. MathWorks (2024). Matlab [online]. Website https://www.mathworks.com/help/matlab/ (accessed 10 November 2024).
• Mollah M B R, Hasan M A, Salam M A & Ali M A (2010). Digital image analysis to estimate the live weight of broiler. Computers and Electronics in Agriculture 72(1): 48-52. https://doi.org/10.1016/j.compag.2010.02.002.
• Mortensen A K, Lisouski P & Ahrendt P (2016). Weight prediction of broiler chickens using 3D computer vision. Computers and Electronics in Agriculture 123: 319-326. https://doi.org/10.1016/j.compag.2016.03.011.
• Newberry R C, Hunt J R & Gardiner E E (1985). Behaviour of roaster chickens towards an automatick weighing perch. British Poultry Science 26(2): 229-237. https://doi.org/10.1080/00071668508416808.
• Otsu N (1979). A threshold selection method from gray-level histogram. IEEE Transactions on Systems, Man, and Cybernetics 9(1): 62-66. https://doi.org/10.1109/TSMC.1979.4310076.
• Pan S J & Yang Q (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22(10): 1345. https://doi.org/10.1109/TKDE.2009.191.
• Prechelt L (1998). Early stopping-but when? Lecture Notes in Computer Science 7700: 53-67. https://doi.org/10.1007/978-3-642-35289-8_5.
• Redmon J & Farhadi A (2018). YOLOv3: an incremental improvement. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; Utah, USA, pp. 1-6. https://doi.org/10.48550/arXiv.1804.02767.
• C Rohan A, Rafaq M S, Hasan M J, Asghar F & Bashir A K (2024). Application of deep learning for livestock behaviour recognition: a systematic literature review. Computers and Electronics in Agriculture 224: 109115. https://doi.org/10.1016/j.compag.2024.109115.
• Ross C & Davis N (1990). Sensors in poultry housing. Poultry International 29(2): 26-30. https://www.cabidigitallibrary.org/doi/full/10.5555/19902445123.
• Shams M Y, Elmessery W M, Oraiath A A T, Elbeltagi A & Salem A (2025). Automated on-site broiler live weight estimation through YOLO based segmentation. Smart Agricultural Technology 10: 100828. https://doi.org/10.1016/j.atech.2025.100828.
• Shorten C & Khoshgoftaar T M (2019). A survey on image data augmentation for deep learning. Journal of Big Data 6(1): 1-48. https://doi.org/10.1186/s40537-019-0197-0.
• Sohan M, Sai Ram T & Rami Reddy C V (2024). A review on YOLOv8 and its advancements. In International Conference on Data Intelligence and Cognitive Informatics; Springer, Singapore. pp. 529-545. https://doi.org/10.1007/978-981-99-7962-2_39.
• Srivastava N, Hinton G, Krizhevsky A, Sutskever I & Salakhutdinov R (2014). Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15 (1): 1929-1958. https://dl.acm.org/doi/10.5555/2627435.2670313.
• Turner M J B, Gurney P & Belyavin C G (1983). Automatic weighing of layer replacement pullets housed on litter or in cages. British Poultry Science 24 (1): 33-45. https://doi.org/10.1080/00071668308416711.
• Turner M J B, Gurney P, Crowther J S W & Sharp J R (1984). An automatic weighing system for poultry. Journal of Agricultural Engineering Research 29(1): 17-24. https://doi.org/10.1016/0021-8634(84)90056-8. of Ultralytics (2024). Ultralytics YOLO Documentation [online]. Website https://docs.ultralytics.com [accessed 6 November 2025].
• Wang C Y, Bochkovskiy A & Liao H Y M (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings the IEEE/CVF conference on computer vision and pattern recognition 7464-7475. https://doi.org/10.48550/arXiv.2207.02696.
• Wongsriworaphon A, Arnonkijpanich B & Pathumnakul S (2015). An approach based on digital image analysis to estimate the live weights of pigs in farm environments. Computers and Electronics in Agriculture 115: 26-33. https://doi.org/10.1016/j.compag.2015.05.004.
• Zhang J, Zhuang Y, Ji H & Teng G (2021). Pig weight and body size estimation using a multiple output regression convolutional neural network: A fast and fully automatic method. Sensors, 21(9): 3218. https://doi.org/10.3390/s21093218.