Application of the deep learning transformer architecture (RF-DETR) for monitoring pollinator trees in orchard rows

Relevance. Accurate monitoring of pollinizer trees is essential for optimizing pollination and increasing the yield of apple orchards. Existing remote sensing methods lack the necessary detail for recognizing individual trees by cultivar within densely planted linear rows. This paper proposes an automated method for monitoring pollinizer trees in orchard rows, based on the advanced RF-DETR deep learning transformer architecture.

Methods.The method relies on analyzing imagery from aerial and ground-based platforms and enables the recognition of pollinizers based on the presence of persistent fruits. A labeled dataset (2500 images), verified by expert agronomists, was used for training, ensuring high data quality. Training and comparative analysis of model configurations (Nano, Small, Medium, Large) on the labeled dataset demonstrated that the RF-DETR Medium model achieves high recognition accuracy (mAP@50:95 = 0.658) and enables real-time data processing (5.9 FPS). This combination of features allows the model to be used both on onboard computers of robotic systems and for data processing on server hardware. Field testing of the method in a control row successfully identified a deficit of pollinizer trees and precisely localized problematic sections of the orchard.

Results. The obtained results confirm that the use of transformer models allows for moving away from subjective and labor-intensive monitoring methods while ensuring scalable analysis.

1. Gilpin A.-M., Kobel C., Brettell L.E., O’Brien C., Cook J.M., Power S.A. Co-Flowering Species Richness Increases Pollinator Visitation to Apple Flowers. Agriculture. 2022; 12(8): 1246. https://doi.org/10.3390/agriculture12081246

2. Meissle M., Waldburger M., Jeanneret P., Broggini G.A.L., Patocchi A., Romeis J. Insect Pollinator Monitoring in and around a Netted Plot of Apple Trees—Biosafety Implications for Genetically Engineered Fruit Trees. Agronomy. 2023; 13(1): 84. https://doi.org/10.3390/agronomy13010084

3. Elsysy M., Ebrahimi A., Einhorn T. Wind Pollination of Apple Flowers Under Insect Exclusion Nets Questions the Insect-Dependent Pollination Model of Modern Apple Plantations. Plants. 2025; 14(8): 1196. https://doi.org/10.3390/plants14081196

4. Roeder S., Serra S., Musacchi S. Effective Pollination Period and Parentage Effect on Pollen Tube Growth in Apple. Plants. 2021; 10(8): 1618. https://doi.org/10.3390/plants10081618

5. Zhu Y. et al. Identification of Apple Orchard Planting Year Based on Spatiotemporally Fused Satellite Images and Clustering Analysis of Foliage Phenophase. Remote Sensing. 2020; 12(7): 1199. https://doi.org/10.3390/rs12071199

6. Li H., Tan B., Sun L., Liu H., Zhang H., Liu B. Multi-Source Image Fusion Based Regional Classification Method for Apple Diseases and Pests. Applied Sciences. 2024; 14(17): 7695. https://doi.org/10.3390/app14177695

7. Fedorov D.E., Bykov S.N. Monitoring of pea crops with neural network processing of images obtained using UAVs. Agrarian science. 2025; (8): 122–128 (in Russian). https://doi.org/10.32634/0869-8155-2025-397-08-122-128

8. Khort D.O., Kutyrev A.I., Smirnov I.G., Filippov R.A., V ershinin R.V. Developing algorithms for a berry recognition system used in robotized harvesting of garden strawberry. Electrical technology and equipment in the agro-industrial complex. 2020; 67(1): 133–141 (in Russian). https://doi.org/10.22314/2658-4859-2020-67-1-133-141

9. Liu Q., Meng H., Zhao R., Ma X., Zhang T., Jia W. Green Apple Detector Based on Optimized Deformable Detection Transformer. Agriculture. 2025; 15(1): 75. https://doi.org/10.3390/agriculture15010075

10. Robinson I., Robicheaux P., Popov M., Ramanan D., Peri N. RF-DETR: Neural Architecture Search for Real-Time Detection Transformers. arXiv. 2025; 2511.09554. https://doi.org/10.48550/arXiv.2511.09554

11. Kutyrev A.I., Smirnov I.G., Andriyanov N.A. Neural network models of apple fruit identification in tree crowns: comparative analysis. Horticulture and viticulture. 2023; (5): 56–63 (in Russian). https://doi.org/10.31676/0235-2591-2023-5-56-63

12. Liu Z., Wu D., Xu F., Du Z., Luo R., Li C. MSHLB-DETR: Transformer-Based Multi-Scale Citrus Huanglongbing Detection in Orchards with Aggregation Enhancement. Horticulturae. 2025; 11(10): 1225. https://doi.org/10.3390/horticulturae11101225

13. Kaviani M., Leblon B., Akilan T., Amishev D., LaRocque A., Haddadi A. Tree Health Assessment Using Mask R-CNN on UAV Multispectral Imagery over Apple Orchards. Remote Sensing. 2025; 17(19): 3369. https://doi.org/10.3390/rs17193369

14. Wang M., Li F. Real-Time Accurate Apple Detection Based on Improved YOLOv8n in Complex Natural Environments. Plants. 2025; 14(3): 365. https://doi.org/10.3390/plants14030365

15. Lee S., Lee S. Efficient Data Augmentation Methods for Crop Disease Recognition in Sustainable Environmental Systems. Big Data and Cognitive Computing. 2025; 9(1): 8. https://doi.org/10.3390/bdcc9010008

16. Maxwell A.E., Warner T.A., Guillén L.A. Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review. Remote Sensing. 2021; 13(13): 2450. https://doi.org/10.3390/rs13132450

17. Khort D.O., Kutyrev A.I., Smirnov I.G., Voronkov I.V. Development of an Automated Management System for Agricultural Technologies in Horticulture. Agricultural Machinery and Technologies. 2021; 15(2): 61–68 (in Russian). https://doi.org/10.22314/2073-7599-2021-15-2-61-68