Journals / Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi / 2026 / Cilt: 28 Sayı: 84

A U-Net–Based Segmentation Approach for Honeybee Pollen Detection Using Deep Learning

rin Öğrenmeyi Kullanarak Bal Arısı Poleninin Tespiti için U-Net Tabanlı Segmentasyon Yaklaşımı

Esra Yılmaz(MARMARA ÜNİVERSİTESİ)0000-0003-2411-4937
Ali Sarıkaş(MARMARA ÜNİVERSİTESİ)0000-0002-3016-0369
Pages
443–448
Publication Date
2026-09-30
🏛️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)

Experimental results show that the proposed model achieved a successful performance with an F1 score of 99.4%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Pollen is the most important food source for maintaining both colony development and honey production in bee populations.
📊
Key Findings & Data:Experimental results show that the proposed model achieved a successful performance with an F1 score of 99.4%.
💡
Conclusion & Impact:Overall, the findings indicate that advances in deep learning-based image analysis for pollen detection represent an important step towards promoting both environmental sustainability and agricultural resilience.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Arı Poleni Tespiti · Derin Öğrenme · Anlamsal Segmentasyon

Abstract

Pollen is the most important food source for maintaining both colony development and honey production in bee populations. Therefore, the presence of pollen in bee colonies is one of the biggest determinants of hive health. In this context, this study contributes to animal and agricultural sustainability by presenting a deep learning-based image analysis approach for the automatic detection of pollen carried by bees. The bee pollen recognition study was performed using the U-Net deep learning architecture applied to the Pollen Dataset. The U-Net model was selected due to its ability to preserve high-resolution spatial information between input images and corresponding segmentation maps, thereby improving detection accuracy. Experimental results show that the proposed model achieved a successful performance with an F1 score of 99.4%. In addition to technical performance, the study also highlights the potential applications of bee pollen detection in agriculture, particularly in supporting farmers, researchers, and policymakers with more informed decision-making processes. Overall, the findings indicate that advances in deep learning-based image analysis for pollen detection represent an important step towards promoting both environmental sustainability and agricultural resilience.

Özet

Polen, arı popülasyonlarında hem koloni gelişiminin hem de bal üretiminin sürdürülmesinde en önemli besin kaynağıdır. Bu nedenle arı kolonilerinde, polenin varlığı, kovan sağlığının en büyük belirleyicilerinden birisidir. Bu bağlamda, bu çalışma, arıların taşıdığı polenin otomatik tespiti için derin öğrenmeye dayalı bir görüntü analizi yaklaşımı sunarak hayvansal ve tarımsal sürdürülebilirliğe yeni bir katkı sağlamaktadır. Arı poleni tanıma çalışması, Polen Veri Kümesine uygulanan U-Net derin öğrenme mimarisi kullanılarak yapıldı. U-Net modeli, giriş görüntüleri ile ilgili segmentasyon haritaları arasındaki yüksek çözünürlüklü mekansal bilgileri koruyabilme ve böylece tespit doğruluğunu artırma becerisi nedeniyle seçilmiştir. Deneysel sonuçlar, önerilen modelin %99,4'lük bir F1 puanı ile başarılı bir performans elde ettiğini göstermektedir. Teknik performansın yanı sıra, çalışma ayrıca arı poleni tespitinin tarımda, özellikle çiftçileri, araştırmacıları ve politika yapıcıları daha bilinçli karar alma süreçleriyle ilgili desteklemedeki potansiyel uygulamaları da vurgular. Genel olarak bulgular, polen tespiti için derin öğrenme odaklı görüntü analizindeki ilerlemelerin hem çevresel sürdürülebilirliği hem de tarımsal dayanıklılığı teşvik etme yönünde önemli bir adım teşkil ettiğini göstermektedir.

🔖

Cite This Article

Yılmaz, E., Sarıkaş, A. (2026). A U-Net–Based Segmentation Approach for Honeybee Pollen Detection Using Deep Learning. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, Cilt: 28 Sayı: 84, 443–448. https://doi.org/10.21205/deufmd.2026288411

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (15)

  1. Stoner K, Hendriksma H, Tosi S. Pollen as food for bees: Diversity, nutrition, and contamination. Frontiers in Sustainable Food Systems 2023;6:1129358. doi:10.3389/fsufs.2022.1129358.
  2. TEPGE. Beekeeping Product Report. 2023. Available from: https://arastirma.tarimorman.gov.tr/tepge [Accessed 1 October 2024].
  3. Narcia-Macias C, Guardado J, Rodriguez J, Park J, Rampersad-Ammons J, Enriquez E, et al. Intellibeehive: An automated honey bee, pollen, and varroa destructor monitoring system. In: 2024 International Conference on Machine Learning and Applications (ICMLA); 2024, p. 845-850.
  4. Ngo T, Rustia D, Yang EC, Lin TT. Automated monitoring and analyses of honey bee pollen foraging behavior using a deep learning-based imaging system. Computers and Electronics in Agriculture 2021;187:106239. doi:10.1016/j.compag.2021.106239.
  5. Silva D, Bomfim I, Braga A, Gomes D. Applying Computer Vision Models to Detect in Real Time the Pollen Flow at the Input of Honeybee Hives (Apis mellifera L.). In: Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais (WCAMA); 2023, p. 21-30.
  6. Benahmed H, Bensaad M, Chaib N. Detection and tracking of honeybees using YOLO and StrongSORT. In: 2nd International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS); 2022, p. 18-23.
  7. Le TN, Thi-Thu-Hong P, Nguyen HD, Thi-Lan L, et al. A Novel Convolutional Neural Network Architecture for Pollen-Bearing Honeybee Recognition. International Journal of Advanced Computer Science and Applications 2023;14(8). doi:10.14569/IJACSA.2023.01408112.
  8. Yang C, Collins J. Deep learning for pollen sac detection and measurement on honeybee monitoring video. In: International Conference on Image and Vision Computing New Zealand (IVCNZ); 2019, p. 1-6. doi:10.1109/IVCNZ48456.2019.8961011.
  9. Rodriguez IF, Megret R, Acuna E, Agosto-Rivera J, Giray T. Recognition of pollen-bearing bees from video using convolutional neural network. In: IEEE Winter Conference on Applications of Computer Vision (WACV); 2018, p. 314-322. doi:10.1109/WACV.2018.00041.
  10. Yang C, Collins J, Beckerleg M. A model for pollen measurement using video monitoring of honey bees. Sensing and Imaging 2018;19:1-29. doi:10.1007/s11220-017-0185-4.
  11. Monteiro F, Pinto C, Rufino J. Towards precise recognition of pollen bearing bees by convolutional neural networks. In: Iberoamerican Congress on Pattern Recognition; 2021, p. 217-226. doi:10.1007/978-3-030-93420-0_21.
  12. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III; 2015, p. 234-241. doi:10.1007/978-3-319-24574-4_28.
  13. Berkaya S, Gunal E, Gunal S. Deep learning-based classification models for beehive monitoring. Ecological Informatics 2021;64:101353. doi:10.1016/j.ecoinf.2021.101353.
  14. Yoo J, Siddiqua R, Liu X, Ahmed K, Hossain M. BeeNet: An End-To-End Deep Network For Bee Surveillance. Procedia Computer Science 2023;222:415-424. doi:10.1016/j.procs.2023.08.180.
  15. Schurischuster S, Kampel M. Image-based classification of honeybees. In: Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA); 2020, p. 1-6. doi:10.1109/IPTA50016.2020.9286673.