Automated Identification of Oil Palm’s 17th Leaf Using YOLOv12 and Spatial Positioning

Jihad Rahmawan, Herman Yuliansyah, Anton Yudhana, Syahid Al Irfan

Abstract

This study proposes an artificial intelligence–based approach for automatic identification of the 17th leaf in oil-palm trees (Elaeis guineensis), which serves as a key physiological indicator for nutrient monitoring. The method integrates YOLOv12 object detection with a spatial-positioning algorithm that estimates leaf order through vertical sorting of detected fronds. A total of 1,250 annotated field images were collected from farmer-recorded videos to train and evaluate the system. The proposed model achieved a mean average precision (mAP@0.5) of 92.4% and an average positional error of 10.6 pixels in locating the 17th leaf. Compared with manual identification that requires 3–5 minutes per tree, the automated system performs the entire process in under 15 seconds, providing over 95% time efficiency improvement. This work demonstrates a novel fusion of real-time deep-learning detection and spatial reasoning for nutrient-focused precision agriculture and establishes a practical foundation for scalable, automated leaf indexing in plantation management.

Full Text:

PDF (1-12)

References

Namibia Agronomic Board, “Market Intelligence Report: Vegetable Oils,” Windhoek: NAB, Nov. 2023. [Online]. Available: https://www.nab.com.na/

.

M. Kamireddy, R. R. Thimmegowda, A. Ramachandra, and K. C. Nataraju, “Establishing critical leaf nutrient concentrations and identification of yield-limiting nutrients for precise prescriptions in oil palm (Elaeis guineensis),” Agriculture (MDPI), vol. 13, no. 2, p. 453, 2023.

L. S. Woittiez, M. H. van Wijk, M. T. van Noordwijk, J. Giller, and M. E. Tittonell, “Yield gaps in oil palm: A quantitative review of contributing factors,” Eur. J. Agron., vol. 83, pp. 57–77, 2017.

M. A. Istiak, M. Hossain, and M. Al-Amin, “Adoption of UAV imagery in agriculture: Opportunities and challenges,” Comput. Electron. Agric., vol. 208, p. 107695, 2023.

S. Coulibaly, J. Zhao, and P. Li, “Deep learning for precision agriculture: A bibliometric overview,” Comput. Biol. Med., vol. 2, p. 100040, 2022.

I. Pacal, M. Karakose, and F. Ahmed, “A systematic review of deep learning techniques for plant disease detection (2020–2024),” Artif. Intell. Rev., vol. 57, no. 3, pp. 2479–2510, 2024.

C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 1–11, 2023.

G. Jocher, L. Chang, Y. Qin, and T. Tang, “YOLOv12: Innovations in real-time object detection,” J. Comput. Vis., vol. 132, no. 1, pp. 1–15, 2024.

F. Feng, W. Chen, and M. Li, “Improved YOLOv8 algorithms for small-object detection in complex agricultural scenes,” Alexandria Eng. J., vol. 83, pp. 1–15, 2024.

Y. C. Putra, R. Nugroho, and A. Yuliana, “Automatic detection and counting of oil palm trees using object-based deep learning on very-high-resolution images,” Heliyon, vol. 9, no. 4, 2023.

J. Zhang, Y. Wu, and C. Feng, “Spatial positioning technologies in agriculture: A review,” Precision Agric., vol. 20, no. 4, pp. 734–754, 2019.

A. Rehman, A. Mahmud, and I. Mehmood, “GPS and vision-based mapping of agricultural fields using UAVs,” J. Field Robot., vol. 36, no. 4, pp. 784–802, 2019.

M. Breure, “Palm leaf phyllotaxis: Structure and implications for crop management,” J. Oil Palm Res., vol. 31, no. 1, pp. 20–32, 2019.

T. Lu and J. Shen, “Deep learning for plant leaf counting in dense canopies,” Comput. Electron. Agric., vol. 187, p. 106262, 2021.

Z. Chen, H. Wang, and Y. Zhao, “Robust leaf instance segmentation in the wild using graph reasoning and attention,” IEEE Access, vol. 9, pp. 115283–115295, 2021.

W. Wang, J. Xu, and L. Zhang, “Multi-view learning for plant phenotyping in field conditions,” Comput. Electron. Agric., vol. 202, p. 105114, 2023.

Y. Yang, X. Lin, and H. Li, “3D-aware object detection for dense natural scenes,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 13478–13487, 2022.

Z. Liu, Y. Wang, and X. Chen, “A survey of transformer-based object detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 3, pp. 2431–2452, 2023.

D. J. Mulla, “Twenty-five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps,” Biosyst. Eng., vol. 114, no. 4, pp. 358–371, 2017.

P. Lottes, J. Behley, M. Chebrolu, and C. Stachniss, “Advances in precision agriculture using computer vision technologies,” Agric. Syst., vol. 173, pp. 1–11, 2019.

O. Bongomin, J. Mwebaze, and T. Nsubuga, “UAV image acquisition and processing for high-throughput phenotyping,” Plant Phenome J., vol. 7, no. 1, e20096, 2024.

R. Rasool, F. Khan, and S. Aziz, “Vision transformers for crop monitoring under natural lighting,” Agric. Syst., vol. 228, p. 104962, 2024.

J. Li, H. Sun, and L. Qiu, “3D leaf-order estimation using multi-view convolutional networks,” Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 11254–11263, 2024.

Y. Qin, L. Chang, and T. Tang, “AI-enhanced detection for precision agriculture using transformer networks,” Sensors, vol. 24, no. 2, p. 572, 2024.

DOI: https://doi.org/10.37058/innovatics.v7i2.15766

Refbacks

  • There are currently no refbacks.