SavedAdd your journal

Journals / Gaziosmanpaşa Bilimsel Araştırma Dergisi / 2026 / Cilt: 15 Sayı: 2

Real-Time Egg Counting Based on Line-Crossing Using Deep Learning

Derin Öğrenme ile Hat Geçişi Tabanlı Gerçek Zamanlı Yumurta Sayımı

İsmail Hakkı Özdemir(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, LİSANSÜSTÜ EĞİTİM ENSTİTÜSÜ, MEKATRONİK MÜHENDİSLİĞİ (DR))0000-0003-1011-5293
Levent Gökrem(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ)
Pages
41–54
Publication Date
2026-09-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results indicate that the proposed approach delivers reliable egg counting under industrial conditions with a simple setup.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study presents an end-to-end visual perception system for real-time and direction-aware (Left→Right, Right→Left) counting of chicken eggs on a production line.
📊
Key Findings & Data:The proposed system integrates YOLOv8-based object detection with the ByteTrack multi-object tracker to perform precise count and direction tracking based on line-crossing logic.
💡
Conclusion & Impact:The results indicate that the proposed approach delivers reliable egg counting under industrial conditions with a simple setup.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Yumurta Sayımı · Nesne tespiti · YOLOv8

Abstract

This study presents an end-to-end visual perception system for real-time and direction-aware (Left→Right, Right→Left) counting of chicken eggs on a production line. The proposed system integrates YOLOv8-based object detection with the ByteTrack multi-object tracker to perform precise count and direction tracking based on line-crossing logic. The application offers an operator-friendly solution with a fixed-scale monitoring interface, an upper-left counter panel, and a lower-right FPS display. All generated counts are logged daily in CSV files; additionally, a Flask-based web panel/REST API delivers real-time totals, time series for selected days, and date-range reports using Chart.js line graphs. Over a five-day period, a total of 25,112 eggs were recorded, with a calculated daily average of 5,022.4 eggs. This figure demonstrates that the system can be effectively utilized on a production line operating at a consistent rate of approximately 5,000 eggs per day. The maximum difference between daily counts was 112 (5082 – 4970), corresponding to a deviation rate of only 2.23% relative to the total average. The results indicate that the proposed approach delivers reliable egg counting under industrial conditions with a simple setup.

Özet

Bu çalışma, tavuk yumurtalarının üretim hattı üzerinde gerçek zamanlı ve yön bilgili (Sol→Sağ, Sağ→Sol) sayımını gerçekleştiren uçtan uca bir görsel algı sistemini sunmaktadır. Önerilen sistem, YOLOv8 tabanlı nesne tespitini ByteTrack çoklu-nesne izleyici ile bütünleştirerek çizgi geçişine dayalı olarak net adet ve yön sayımı yapar. Uygulama; sabit ölçekli bir görüntüleme arayüzü, üst sol sayaç paneli, sağ alt FPS göstergesi ile operatör dostu bir çözüm sağlar. Üretilen tüm sayımlar günlük CSV loglarına yazılır; ayrıca Flask tabanlı web panel/REST API ile anlık toplamlar, seçili güne ait zaman serisi ve tarih aralığı raporları Chart.js çizgisel grafiklerle sunulur. Beş gün boyunca kaydedilen yumurta sayısı 25.112 adet olup, günlük ortalama yumurta geçiş sayısı 5022.4 adet olarak hesaplanmıştır. Bu değer, sistemin istikrarlı bir şekilde günde yaklaşık 5000 adet kapasitede çalışan bir üretim hattında etkin biçimde kullanılabileceğini göstermektedir. Ölçüm sonuçları arasındaki farkın maksimum değeri 112 (5082 – 4970) olup, bu sapma oranı toplam ortalamaya göre %2,23 gibi düşük bir seviyededir. Sonuçlar, önerilen yaklaşımın endüstriyel koşullarda basit kurulumla güvenilir yumurta sayımı ürettiğini göstermektedir.

🔖

Cite This Article

Özdemir, İ. H., Gökrem, L. (2026). Real-Time Egg Counting Based on Line-Crossing Using Deep Learning. Gaziosmanpaşa Bilimsel Araştırma Dergisi, Cilt: 15 Sayı: 2, 41–54. https://ajindex.com/articles/1487536

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. Abd Aziz, N. S. N., Daud, S. M., Dziyauddin, R. A., Adam, M. Z., & Azizan, A. (2020). A review on computer vision technology for monitoring poultry farm—application, hardware, and software. IEEE access, 9, 12431-12445.
  2. Ahmed, M. W., Hossainy, S. J., Khaliduzzaman, A., Emmert, J. L., & Kamruzzaman, M. (2023). Non‐destructive optical sensing technologies for advancing the egg industry toward Industry 4.0: A review. Comprehensive Reviews in Food Science and Food Safety, 22(6), 4378-4403.
  3. Akkoyun, F., Ozcelik, A., Arpaci, I., Erçetin, A., & Gucluer, S. (2022). A multi-flow production line for sorting of eggs using image processing. Sensors, 23(1), 117.
  4. Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016, September). Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP) (pp. 3464-3468). Ieee.
  5. Guerra, J. P., & Cuevas, F. (2024). Application of Digital Image Processing Techniques for Agriculture: A Review. Digital Image Processing-Latest Advances and Applications.
  6. Hadjisavvas, N., Nicolaou, N., & Stavrakis, E. (2024, Kasım). Real Time Egg Detection Using Edge Computer Vision. In Proceedings of the First International Conference on Accessible Digital Agriculture Technologies (CADAT2024) (s. 16–22). Valencia, İspanya: IARIA.
  7. Hsieh, J. W., Yu, S. H., Chen, Y. S., & Hu, W. F. (2006). Automatic traffic surveillance system for vehicle tracking and classification. IEEE Transactions on intelligent transportation systems, 7(2), 175-187.
  8. Jiang, T., Zhou, J., Xie, B., Liu, L., Ji, C., Liu, Y.,. & Zhang, B. (2024). Improved YOLOv8 model for lightweight pigeon egg detection. Animals, 14(8), 1226.
  9. Jocher, G., Chaurasia, A., & Qiu, J. (2023). “YOLO by Ultralytics.” https://github.com/ultralytics/ultralytics. (Erişim tarihi: 25.10.2023).
  10. Li, Z., Luo, S., Xiang, J., Chen, Y., & Luo, Q. (2024). Improved Chinese Giant Salamander Parental Care Behavior Detection Based on YOLOv8. Animals, 14(14), 2089.
  11. Neethirajan, S. (2022). Automated tracking systems for the assessment of farmed poultry. Animals, 12(3), 232.
  12. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. arXiv. https://arxiv.org/abs/1506.02640
  13. 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 (pp. 529-545). Springer, Singapore.
  14. Türkoğlu, M. (2021). Faster Region-Based Multi-Layer Convolutional Neural Networks for Cracked Detection in Eggshell Images. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 9(1).
  15. Ultralytics. (2023–2025). YOLOv8 Documentation. Erişim: https://docs.ultralytics.com
  16. Yabanova, İ., & Yumurtacı, M. (2021). Hareketli Ürünlerin Sayımı için Kızılötesi Tabanlı Sensör Dizaynı ve Yumurta Sayma Uygulaması. Journal of Materials and Mechatronics: A, 2(2), 141-149.
  17. Yang, X., Bist, R. B., Subedi, S., & Chai, L. (2023). A computer vision-based automatic system for egg grading and defect detection. Animals, 13(14), 2354.
  18. Zalhan, M. Z., Syarmila, S. S., Nazri, I. M., & Taha, I. M. (2016, May). Vision-based egg grade classifier. In 2016 International Conference on Information and Communication Technology (ICICTM) (pp. 31-35). IEEE.
  19. Zhang, Y., Sun, P., Jiang, Y., Yu, J., Yuan, Z., Weng, X., & Yuan, J. (2022). ByteTrack: Multi Object Tracking by Associating Every Detection Box. arXiv:2110.06864.
  20. Zhang, Y., Su, J., Wang, T., Xu, C., & Yu, A. (2024). Intelligent detection method of microparticle virus in silkworm based on YOLOv8 improved algorithm. The Journal of Supercomputing, 80(12), 18118-18141.
  21. Wu, Z., Yang, J., Zhang, H., & Fang, C. (2025). Enhanced Methodology and Experimental Research for Caged Chicken Counting Based on YOLOv8. Animals, 15(6), 853.
  22. Jiang, T., Zhou, J., Xie, B., Liu, L., Ji, C., Liu, Y.,. & Zhang, B. (2024). Improved YOLOv8 model for lightweight pigeon egg detection. Animals, 14(8), 1226.