Pemanfaatan Yolo11 dan Bytetrack untuk Penghitungan Telur Berbasis Visi Komputer pada Konveyor Secara Real-time
DOI:
https://doi.org/10.30865/jurikom.v13i3.9664Keywords:
Bytrack, Computer Vision, Conveyor, Object Detection, Yolo11Abstract
Egg counting is an important stage in the laying hen farming industry because it directly affects productivity and the efficiency of production management. Manual counting methods still have several limitations, including relatively long processing time, the need for a large workforce, and a fairly high error rate due to human factors. These conditions indicate the need for the implementation of automated technology capable of improving speed, accuracy, and consistency in the egg counting process. This study aims to develop an automatic egg counting system based on computer vision by integrating YOLO11 as the object detection method and ByteTrack as the object tracking method. The egg dataset was collected through image acquisition under various conditions, followed by annotation and data augmentation processes before being used in the model training stage using Google Colab.The test results show that the developed system is capable of detecting and counting eggs with a high level of accuracy, where precision and recall values exceed 0.90, and the average counting accuracy reaches 94.4% under various testing conditions. The main factors affecting system errors are high conveyor speed, which causes motion blur, and lighting variations that can lead to false positives and false negatives. The main contribution of this research is the development of a camera-based counting system design, thereby reducing errors in counting the number of eggs. The results of this study indicate that the integration of YOLO11 and ByteTrack has the potential to improve the efficiency of automated egg counting processes and contribute to the advancement of computer vision technology in the modern poultry industry.
References
[1] A. Vinod, D. Mohanty, A. John, and B. Depuru, “Application of Artificial Intelligence in Poultry Farming - Advancing Efficiency in Poultry Farming By Automating The Egg Counting Using Computer Vision System,” 2023. doi: 10.21203/rs.3.rs-3266412/v1.
[2] Advantech, “Revolutionizing Egg Production: An AI-Based Optical Inspection System.” [Online]. Available: https://www.advantech.com/en/resources/case-study/revolutionizing-egg-production-an-ai-based-optical-inspection-system
[3] S. P. Fraher et al., “A comparison of three automated root-knot nematode egg counting approaches using machine learning, image analysis, and a hybrid model,” Plant Dis., vol. 108, no. 9, pp. 2625–2629, 2024.
[4] D. S. Smith and G. H. Hoggard, “Counting Eggs With AI,” 2022. [Online]. Available: https://www.sfmagazine.com/articles/2022/february/counting-eggs-with-ai/
[5] I. Kanjanasurat, W. Krungseanmuang, V. Chaowalittawin, and B. Purahong, “Egg-Counting System Using Image Processing and a Website for Monitoring,” in 2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST), 2021, pp. 101–104. doi: 10.1109/ICEAST52143.2021.9426295.
[6] J. B. Ajewole et al., “Development of A Digital Egg Counting System for Eggs on A Conveyor Belt Using Sensor,” in 2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG), 2024, pp. 1–10. doi: 10.1109/SEB4SDG60871.2024.10629932.
[7] O. Geffen, Y. Yitzhaky, N. Barchilon, S. Druyan, and I. Halachmi, “A machine vision system to detect and count laying hens in battery cages,” animal, vol. 14, no. 12, pp. 2628–2634, 2020, doi: 10.1017/S1751731120001676.
[8] X. Wang, X. Yue, H. Li, and L. Meng, “A high-efficiency dirty-egg detection system based on YOLOv4 and TensorRT,” in 2021 International Conference on Advanced Mechatronic Systems (ICAMechS), 2021, pp. 75–80. doi: 10.1109/ICAMechS54019.2021.9661509.
[9] S. Ogurtsov, E. Karikov, and D. Bushuev, “DEVELOPMENT OF AN AUTOMATIC EGG COUNTING SYSTEM BASED ON LOCAL MAXIMUM SEARCH FOR EGGS TRANSPORTED ON A CONVEYOR,” Acad. J. Manuf. Eng., vol. 22, pp. 29–33, 2024.
[10] T. Jiang et al., “Improved YOLOv8 model for lightweight pigeon egg detection,” Animals, vol. 14, no. 8, p. 1226, 2024.
[11] C. Lika, M. Sandy, A. Husna, and R. A. Rizal, “Real Time Chicken Egg Size Classification Using Yolov4 Algorithm,” vol. 4, no. 2, pp. 577–584, 2024.
[12] Y. Luo, Y. Huang, Q. Wang, K. Yuan, Z. Zhao, and Y. Li, “An improved YOLOv5 model: Application to leaky eggs detection,” LWT, vol. 187, p. 115313, 2023, doi: 10.1016/j.lwt.2023.115313.
[13] M. Ulaszewski, R. Janowski, and A. Janowski, “Application of computer vision to egg detection on a production line in real time.,” ELCVIA Electron. Lett. Comput. Vis. Image Anal., vol. 20, pp. 113–143, Feb. 2022, doi: 10.5565/rev/elcvia.1390.
[14] S. Xie, Y. Zhou, I. Zhong, W. Yan, and Q. Zhang, “A package auto-counting model based on tailored YOLO and DeepSort techniques,” MATEC Web Conf., vol. 355, p. 2054, Jan. 2022, doi: 10.1051/matecconf/202235502054.
[15] R. J. Xavier, C. F. O. Viegas, B. C. Costa, and R. P. Ishii, “A Deep Learning Approach for Automatic Counting of Bales and Product Boxes in Industrial Production Lines,” in International Conference on Computational Science and Its Applications, 2022, pp. 619–633.
[16] F. L. Afriansyah, F. E. Purnomo, and B. Prasetyo, “Sistem Hitung Cepat Aplikasi Smart Egg Counting Untuk Mengoptimalkan Produksi Telur Dan Mengetahui Recording Hen Day Pada Peternakan Ayam Petelur: Quick Counting System Smart Egg Counting Application To Optimize Egg Production And Knowing Hen Day Recordin,” J-Dinamika J. Pengabdi. Masy., vol. 7, no. 3, pp. 398–403, 2022.
[17] S. Suryanto, E. Priatna, and F. M. S. Nursuwars, “Sistem Penghitungan Jumlah Telur Ayam Berbasis Internet Of Things,” J. Energy Electr. Eng., vol. 3, no. 2, 2022.
[18] A. Vina, “All You Need to Know About Ultralytics YOLO11 and Its Applications.” [Online]. Available: https://www.ultralytics.com/blog/all-you-need-to-know-about-ultralytics-yolo11-and-its-applications
[19] M. Abouelyazid, “Comparative Evaluation of SORT, DeepSORT, and ByteTrack for Multiple Object Tracking in Highway Videos,” nternational J. Sustain. Infrastruct. Cities Soc., vol. 8, no. 11, pp. 42–52, 2023.
[20] E. Barroga and G. J. Matanguihan, “A practical guide to writing quantitative and qualitative research questions and hypotheses in scholarly articles,” J. Korean Med. Sci., vol. 37, no. 16, 2022.
[21] Y. Roh, G. Heo, and S. E. Whang, “A survey on data collection for machine learning: a big data-ai integration perspective,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 4, pp. 1328–1347, 2019.
[22] H. Zhang, Y. Wang, F. Li, and H. Wang, “Motion Blur Robust Wheat Pest Damage Detection with Dynamic Fuzzy Feature Fusion,” arXiv Prepr. arXiv2601.03046, 2026.
[23] T. Schlosser, M. Friedrich, T. Meyer, and D. Kowerko, “A consolidated overview of evaluation and performance metrics for machine learning and computer vision,” Tobias Schlosser, Michael Friedrich, Trixy Meyer, Danny Kowerko--Junior Profr. Media Comput. Chemnitz Univ. Technol., vol. 9107, 2024.
[24] J. ROMERO RIVEROS, “A metric evaluation framework for object detection,” 2018.
[25] Z. Cai and N. Vasconcelos, “Cascade R-CNN: High quality object detection and instance segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 5, pp. 1483–1498, 2019.
[26] B. Ghojogh and M. Crowley, “The theory behind overfitting, cross validation, regularization, bagging, and boosting: tutorial,” arXiv Prepr. arXiv1905.12787, 2019.
[27] M. Sayed and G. Brostow, “Improved handling of motion blur in online object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 1706–1716.
[28] S. Yoon and J. Cho, “Low-light image contrast enhancement with adaptive noise attenuator for augmented vehicle detection,” Electronics, vol. 12, no. 16, p. 3517, 2023.
