Deep learning based citrus tree detection from low resolution satellite images: A case study of Tarsus

Abstract

The escalating global population, industrialization, and climate change are increasing pressure on agricultural lands. In this context, sustainable agricultural land management is critically important, particularly for high-value crops such as citrus, which plays critical role in economic and food security. Accurate detection and enumeration of citrus trees are essential for ensuring the sustainability and effective monitoring of citrus cultivation. This study employs deep learning methods for object detection of citrus trees in the Tarsus district of Mersin, comparing the performance of Mask R-CNN, YOLOv8, and YOLO11 models using low-resolution satellite imagery. Additionally, the impact of super-resolution (SR) techniques on model accuracy is examined. Results demonstrate that integrating SR techniques significantly improves object detection accuracy, with the YOLO11 model achieving the highest performance. In the raw dataset, the YOLO11 model obtained mAP50 (45.39%) and mAP50-95 (22.15%) values; in the SR applied dataset, these metrics were 85.93% and 67.66%, respectively. This research underscores the potential of deep learning-based approaches to enhance citrus tree monitoring, yield estimation, and agricultural management practices, offering actionable insights for sustainable agriculture.

Keywords

• Deep Learning
• satellite image
• citrus tree
• object-detection

References

1. Akkurt, R., Kahveci, S., Yetgin, Z., Avaroğlu, E., & Keleş, H. (2024, September 21-22). Detecting red pine seedlings with YOLOv8: A labeling method comparison. [Paper presentation]. 8th International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Türkiye.
2. Al Riza, D. F., Musahada, L. C., Aufa, R. I., Hermanto, M. B., Nugroho, H., & Hendrawan, Y. (2025). Comparative study of citrus fruits (Citrus reticulata Blanco cv. Batu 55) detection and counting with single and double labels based on convolutional neural network using YOLOv7. Smart Agricultural Technology, 10. https://doi.org/10.1016/j.atech.2024.100763
3. Cheang, E. K., Cheang, T. K., & Tay, Y. H. (2017). Using convolutional neural networks to count palm trees in satellite images. arXiv. https://doi.org/10.48550/arXiv.1701.06462
4. Csillik, O., Cherbini, J., Johnson, R., Lyons, A., & Kelly, M. (2018). Identification of citrus trees from unmanned aerial vehicle imagery using convolutional neural networks. Drones, 2(4), 39. https://doi.org/10.3390/drones2040039
5. Donmez, C., Villi, O., Berberoglu, S., & Cilek, A. (2021). Computer vision-based citrus tree detection in a cultivated environment using UAV imagery. Computers and Electronics in Agriculture, 187, 106273. https://doi.org/10.1016/j.compag.2021.106273
6. El Akrouchi, M., Mhada, M., Bayad, M., Hawkesford, M. J., & Gérard, B. (2025). AI-Based Framework for Early Detection and Segmentation of Green Citrus fruits in Orchards. Smart Agricultural Technology, 100834. https://doi.org/10.1016/j.atech.2025.100834
7. Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88, 303-338.
8. Fan, Z., Lu, J., Gong, M., Xie, H., & Goodman, E. D. (2018). Automatic tobacco plant detection in UAV images via deep neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(3), pp. 876-887. https://doi.org/10.1109/10.1109/JSTARS.2018.2793849

9. FAO. (2025a). Retrieved March 10, 2025, from https://www.fao.org/faostat/en/#data/RL/visualize
10. FAO. (2025b). Retrieved March 10, 2025, from https://www.fao.org/faostat/en/#data/QC/visualize
11. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE international conference on computer vision, 2961-2969.
12. Hunt Jr, E. R., & Daughtry, C. S. (2018). What good are unmanned aircraft systems for agricultural remote sensing and precision agriculture? International journal of remote sensing, 39(15-16), 5345-5376. https://doi.org/10.1080/01431161.2017.1410300
13. Hussain, M. H., & Mehdi, S. A. (2024, October 15-16). Spatial recognition of citrus trees, seedlings, and gaps: A deep learning and geometric approach on satellite-based RGB imagery [Paper presentation]. Horizons of Information Technology and Engineering (HITE), Lahore, Pakistan. https://doi.org/10.1109/HITE63532.2024.10777150
14. Khanam, R., & Hussain, M. (2024). Yolov11: An overview of the key architectural enhancements. arXiv. https://doi.org/10.48550/arXiv.2410.17725
15. Kouvaras, L., & Petropoulos, G. P. (2024). A Novel technique based on machine learning for detecting and segmenting trees in very high resolution digital images from unmanned aerial vehicles. Drones, 8(2), 43. https://doi.org/10.3390/drones8020043
16. Li, D., Guo, H., Wang, C., Li, W., Chen, H., & Zuo, Z. (2016). Individual tree delineation in windbreaks using airborne-laser-scanning data and unmanned aerial vehicle stereo images. IEEE Geoscience and Remote Sensing Letters, 13(9), pp. 1330-1334. https://doi.org/10.1109/LGRS.2016.2584109
17. Liao, Y., Li, L., Xiao, H., Xu, F., Shan, B., & Yin, H. (2025). YOLO-MECD: Citrus detection algorithm based on YOLO11. Agronomy, 15(3), 687. https://doi.org/10.3390/agronomy15030687
18. Marín-Buzón, C., Pérez-Romero, A., Tucci-Álvarez, F., & Manzano-Agugliaro, F. (2020). Assessing the orange tree crown volumes using google maps as a low-cost photogrammetric alternative. Agronomy, 10(6), 893. https://doi.org/10.3390/agronomy10060893
19. MGM. (2025). Retrieved March 22, 2025, from https://www.mgm.gov.tr/veridegerlendirme/il-ve-ilceler-istatistik.aspx?k=A&m=MERSIN
20. Nasrollahi, K., & Moeslund, T. B. (2014). Super-resolution: a comprehensive survey. Machine vision and applications, 25, pp. 1423-1468. https://doi.org/10.1007/s00138-014-0623-4
21. Orhan, O. (2021). Land suitability determination for citrus cultivation using a GIS-based multi-criteria analysis in Mersin, Turkey. Computers and Electronics in Agriculture, 190, 106433. https://doi.org/10.1016/j.compag.2021.106433
22. Osco, L. P., De Arruda, M. D. S., Junior, J. M., Da Silva, N. B., Ramos, A. P. M., Moryia, É. A. S., Imai, N. N., Pereira, D. R., Creste, É. A. S. Matsubara, E. T., Li, J., & Gonçalves, W. N. (2020). A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 160, 97-106. https://doi.org/10.1016/j.isprsjprs.2019.12.010
23. Oussaoui, S., Boudhar, A., Hadri, A., Lebrini, Y., Houmma, I. H., Karaoui, I., El Khalki E. M., Ouzemou J. E., & Kinnard, C. (2025). Mapping drought severity impact on arboriculture systems over Tadla and lower Tassaout plains in Morocco using Sentinel-2 data and machine learning approaches. Geocarto International, 40(1), 2471104. https://doi.org/10.1080/10106049.2025.2471104
24. Ozdarici-Ok, A. S. L. I. (2015). Automatic detection and delineation of citrus trees from VHR satellite imagery. International Journal of Remote Sensing, 36(17), pp. 4275-4296. https://doi.org/10.1080/01431161.2015.1079663
25. Padilla, R., Passos, W. L., Dias, T. L., Netto, S. L., & Da Silva, E. A. (2021). A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics, 10(3), 279.
26. Qu, H., Du, H., Tang, X., & Zhai, S. (2025). Citrus fruit diameter estimation in the field using monocular camera. Biosystems Engineering, 252, pp. 47-60. https://doi.org/10.1016/j.biosystemseng.2025.02.012
27. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 658-666).
28. Sapkota, R., Ahmed, D., & Karkee, M. (2024). Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments. Artificial Intelligence in Agriculture, 13, pp. 84-99. https://doi.org/10.1016/j.aiia.2024.07.001
29. 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
30. Tian, H., Fang, X., Lan, Y., Ma, C., Huang, H., Lu, X., Zhao, D., Liu, H., & Zhang, Y. (2022). Extraction of citrus trees from UAV remote sensing imagery using YOLOv5s and coordinate transformation. Remote Sensing, 14(17), 4208. https://doi.org/10.3390/rs14174208
31. Toosi, A., Javan, F. D., Samadzadegan, F., Mehravar, S., Kurban, A., & Azadi, H. (2022). Citrus orchard mapping in Juybar, Iran: Analysis of NDVI time series and feature fusion of multi-source satellite imageries. Ecological Informatics, 70, 101733. https://doi.org/10.1016/j.ecoinf.2022.101733
32. TÜİK. (2025). Retrieved March 10, 2025, from https://biruni.tuik.gov.tr/medas/?locale=tr
33. Ultralytics. (2023). Retrieved March 10, 2025, from https://github.com/ultralytics/ultralytics
34. Uyar, N. (2024). Monitoring and analysis of air quality in Zonguldak Province by remote sensing. Turkish Journal of Remote Sensing, 6(1), 57-67. https://doi.org/10.51489/tuzal.1484324
35. Wang, X., Xie, L., Dong, C., & Shan, Y. (2021, March 10). Real-esrgan: Training real-world blind super-resolution with pure synthetic data [Paper presentation]. International conference on computer vision (ICCV 2021).
36. Wang, Y., Bashir, S. M. A., Khan, M., Ullah, Q., Wang, R., Song, Y., Guo, Z., & Niu, Y. (2022). Remote sensing image super-resolution and object detection: Benchmark and state of the art. Expert Systems with Applications, 197, 116793. https://doi.org/10.1016/j.eswa.2022.116793
37. Weinstein, B. G., Marconi, S., Bohlman, S., Zare, A., & White, E. (2019). Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks. Remote Sensing, 11(11), 1309.
38. Weather Spark. (2025). Retrieved March 10, 2025, from https://tr.weatherspark.com/y/98265/Tarsus-T%C3%BCrkiye-Ortalama-Hava-Durumu-Y%C4%B1l-Boyunca
39. Yang, M., Mou, Y., Liu, S., Meng, Y., Liu, Z., Li, P., Xiang, W., Zhou, X., & Peng, C. (2022). Detecting and mapping tree crowns based on convolutional neural network and Google Earth images. International Journal of Applied Earth Observation and Geoinformation, 108, 102764. https://doi.org/10.1016/j.jag.2022.102764
40. Yu, K., Hao, Z., Post, C. J., Mikhailova, E. A., Lin, L., Zhao, G., Tian, S., & Liu, J. (2022). Comparison of classical methods and mask R-CNN for automatic tree detection and mapping using UAV imagery. Remote Sensing, 14(2), 295. https://doi.org/10.3390/rs14020295
41. Yu, G., Zhang, L., Luo, L., Liu, G., Chen, Z., & Xiong, S. (2023). Mapping Insect-Proof Screened Citrus Orchards Using Sentinel-2 MSl Time-Series Images. Remote Sensing, 15(11), 2867. https://doi.org/10.3390/rs15112867
42. Zhang, L., Zhang, L., & Du, B. (2016). Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geoscience and remote sensing magazine, 4(2), 22-40.
43. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020, April). Distance-IoU loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 07, pp. 12993-13000).
44. Zortea, M., Macedo, M. M., Mattos, A. B., Ruga, B. C., & Gemignani, B. H. (2018, October 29, November 1). Automatic citrus tree detection from UAV images based on convolutional neural networks [Paper presentation]. Proceedings of the 31th Sibgrap/WIA—Conference on Graphics, Patterns and Images, SIBGRAPI. 18. Paraná, Brazil.