RT-DETR-Based Computer Vision System for Real-Time Detection and Classification of Oil Palm Fruit Maturity Levels in Plantations
DOI:
https://doi.org/10.61255/decoding.v4i2.1281Keywords:
Computer vision, Deep learning, Oil palm fruit maturity, RT-DETR, Smart agricultureAbstract
Purpose – This study aimed to develop an automated oil palm fruit maturity level detection system using the real-time detection transformer (RT-DETR) algorithm to overcome the limitations of conventional visual inspection methods, which are often subjective and inconsistent. This study evaluated the effectiveness of the RT-DETR in detecting and classifying oil palm fruit maturity levels to support quality control processes in plantation operations.
Method – A computer vision-based approach was implemented using the RT-DETR-L object detection model. The dataset consisted of 14,620 annotated oil palm fruit images categorized into four maturity levels: unripe, underripe, ripe, and overripe. The research process included data collection, image annotation, preprocessing, model training, and evaluation of the model. The model performance was assessed using precision, recall, mean Average Precision (mAP@50), and inference speed metrics.
Findings – The experimental results show that the RT-DETR-L model achieved a precision of 93.2%, 95.6%, and mAP@50 of 96.9%, respectively. The model successfully detected and classified oil palm fruit maturity levels across all categories with high accuracy. Furthermore, the model achieved an inference time of 25–28 ms per image and a processing speed of 10–14 FPS on an NVIDIA RTX 3050 4GB GPU, demonstrating its capability for real-time applications.
Research Implications – The findings indicate that RT-DETR-L can improve the efficiency, consistency, and accuracy of oil palm fruit sorting and quality control processes. However, this study was limited to the available datasets and testing scenarios used. Future research should evaluate the model under diverse environmental conditions, lighting variations, and field deployment settings to improve its generalizability and robustness.
Originality – Unlike previous studies that primarily employed CNN-based detectors or focused on binary maturity classification, this study investigated the application of a transformer-based RT-DETR-L architecture for detecting four oil palm fruit maturity categories. The results demonstrate that RT-DETR-L can provide high detection accuracy while maintaining real-time performance in smart agriculture applications.
Abstract views: 13
, 
PDF downloads: 2
Downloads
References
Direktorat Jenderal Perkebunan Kementerian Pertanian Republik Indonesia, “Direktorat Jenderal Perkebunan Kementerian Pertanian Republik Indonesia,” in Statistik Perkebunan Jilid 1 2023-2025, 2024, p. 90.
Kementerian Pertanian Republik Indonesia, “Outlook Komoditas Perkebunan Kelapa Sawit,” Pusat Data dan Sistem Informasi Pertanian Sekretariat Jenderal Kementerian Pertanian, pp. 1–78, 2024.
R. A. Sirait, G. Supriyanto, and Priyambada, “Pengaruh Kematangan Buah terhadap FFA dan Besarnya Kandungan Minyak di Dalamnya Di Pabrik Kelapa Sawit,” Journal Agroforetech, vol. 1, no. 1, 2023, [Online]. Available: https://jurnal.instiperjogja.ac.id/index.php/JOM/article/view/394
R. Triyogi, R. Magdalena, and B. Hidayat, “Mendeteksi Kematangan Buah Kelapa Sawit Menggunakan Convolution Neural Network Deep Learning,” vol. 1, no. 1, pp. 22–27, 2023, doi: doi:http://doi.org/10.25124/logic.v1i1.6732.
R. Kurniawan and Nurahman, “Klasifikasi Tingkat Kematangan Buah Sawit Berdasarkan Ekstraksi Fitur RGB dan GLCM Menggunakan Algoritma K-NN,” vol. 22, pp. 457–466, 2023, doi: https://doi.org/10.32409/jikstik.22.4.3402.
Z. Genoveva and R. D. Syah, “MODEL MACHINE LEARNING UNTUK DETEKSI TINGKAT KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN METODE YOLOV8 Machine,” vol. 8, pp. 121–136, 2024.
M. Y. M. A. Mansour, K. D. Dambul, and K. Y. Choo, “Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch,” International Journal of Technology, vol. 13, no. 6, pp. 1326–1335, 2022, doi: 10.14716/ijtech.v13i6.5932.
R. R. Dewi, I. Hermawan, and D. Abera, “Evaluation of YOLOv11 and RF-DETR Architectures for UAV-Based Detection of Healthy Oil Palm Trees,” in 2025 8th International Conference of Computer and Informatics Engineering (IC2IE), IEEE, Sep. 2025, pp. 1–8. doi: 10.1109/IC2IE67206.2025.11283417.
H. M. Hutajulu, A. Yanie, L. Adriana, and D. Safitri, “Rancang Bangun Deteksi Kematangan Buah Kelapa Sawit Dan Peringatan Berbasis Telegram,” Prosiding Seminar Nasional Teknik (Semnastek) UISU 2023: Peran Teknologi Berkelanjutan dalam Era Disrupsi, pp. 207–213, 2023.
D. S. Prasvita, A. M. Arymurthy, and D. Chahyati, “Deep Learning Model for Automatic Detection of Oil Palm Trees in Indonesia with YOLO-V5,” in Proceedings of the 8th International Conference on Sustainable Information Engineering and Technology, New York, NY, USA: ACM, Oct. 2023, pp. 39–44. doi: 10.1145/3626641.3626924.
D. N. Huda, M. R. Romdoni, L. Safitri, A. Winarni, and A. Rahman, “Real-time Detection Transformer ( RT-DETR ) of Ornamental Fish Diseases with YOLOv9 using CNN ( Convolutional Neural Network ) Algorithm,” vol. 8, no. 2, pp. 463–471, 2024, doi: https://doi.org/10.30871/jaic.v8i2.8561.
N. R. R. Wati, A. Abdullah, and Sucipto, “Klasifikasi Tingkat Kematangan Buah Kelapa Sawit Menggunakan Metode Convolutional Neural Network,” vol. 4, no. September, 2025, doi: https://doi.org/10.55606/jupti.v4i3.5841.
S. I. Guslianto and S. ‘Uyun, “Klasifikasi Kematangan Buah Sawit Berdasarkan Fitur Warna, Bentuk dan Tekstur Menggunakan Algoritma K-NN,” vol. 9, no. 3, pp. 407–414, 2023, doi: https://doi.org/10.26418/jp.v9i3.64877.
A. Elumalai and V. Jeganathan, “Real-Time Classifications of Pests from Agriculture Industry Based on Their Color and Texture Features by Using Machine Learning Models,” vol. 5, no. 2, pp. 9–16, 2024, Accessed: Jun. 10, 2026. [Online]. Available: https://journal.ijprse.com/index.php/ijprse/article/view/1013
R. P. Putra, J. Jumadi, and D. Lianda, “Pengolahan Citra Digital Untuk Mengidentifikasi Tingkat Kematangan Buah Kelapa Sawit Berdasarkan Warna Rgb Dan Hsv Dengan Menggunakan Metode Self Organizing Map ( SOM ),” vol. 20, no. 1, pp. 98–105, 2024.
M. Shiddiq, R. Salambue, F. Wardana, V. V. Dasta, and I. Okta, “Multispectral imaging and deep learning for oil palm fruit bunch ripeness detection,” vol. 13, no. 6, pp. 4168–4181, 2024, doi: 10.11591/eei.v13i6.8120.
Q. P. Ramadhani and F. Dewanta, “Palm Fruit Ripeness and Quality Detection System Using YOLOv11,” Proceedings of the National Conference on Electrical Engineering, Informatics, Industrial Technology, and Creative Media, vol. 2025, no. 1, pp. 163–168, Jan. 2026, doi: 10.20895/centive.v2025i1.537.
Y. Zhao et al., “DETRs Beat YOLOs on Real-time Object Detection,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 16965–16974, 2024, doi: 10.1109/CVPR52733.2024.01605.
S. Wang, C. Xia, F. Lv, and Y. Shi, “RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision”, doi: https://doi.org/10.48550/arXiv.2409.08475.
L. A. Bustamante and J. C. Gutierrez, “Enhancing Real-Time Detection Transformer ( RT-DETR ) for Handgun Detection on Nvidia Jetson,” vol. 28, no. 3, pp. 1–19, 2025, doi: 10.1109/CLEI64178.2024.10700426.
B. Ath Thariq Syams, R. Mutiara Siregar, and M. Akbar Syahbana Pane, “Classification of Plant Pests Using the Real-Time Detection Transformer (RT-DETR) Algorithm in Oil Palm Plants,” Sisfo: Jurnal Ilmiah Sistem Informasi, vol. 10, no. 1, pp. 198–204, May 2026, doi: 10.29103/sisfo.v10i1.27029.
T. Selvakumar, M. N. A. H. Sha‘abani, M. S. M. Aras, and M. B. Bahar, “Development of a YOLOv11-Based Deep Learning System for Insect Pest Detection and Classification in Oil Palm Plantation,” Mod. Appl. Sci., vol. 19, no. 2, p. 32, Oct. 2025, doi: 10.5539/mas.v19n2p32.
K. H. Ghazali, S. Riyadi, A. D. Andriyani, R. Muda, A. Lubis, and S. Yan, “RT-DETR-Palm A Transformer Based Approach for Oil Palm Tree Detection Using UAV Imagery,” in 2025 International Conference on Advanced Technologies in Energy and Informatic (ICATEI), IEEE, Oct. 2025, pp. 447–452. doi: 10.1109/ICATEI67676.2025.11404965.
E. Bagus Nugroho, F. Akhyar, and L. Novamizanti, “Metode Deteksi Obyek Berbasis Computer Vision dan Deep Learning untuk Sistem Inspeksi Cacat pada Permukaan Printed Circuit Board (PCB) ,” e-Proceeding of Engineering, vol. 11, no. 2, p. 801, 2024.
Rizky Delianngi, Ratu Mutiara Siregar, Nurliana, Muhammad Akbar Syahbana Pane, Phaklen Ehkan, and Andi Prayogi, “Performance Evaluation of YOLOv9, YOLOv10, and YOLOv11 for Real-Time Early Detection of Ganoderma Boninense in Oil Palm,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 10, no. 2, pp. 429–440, Apr. 2026, doi: 10.29207/resti.v10i2.7479.
Y. Chen et al., “YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 6, pp. 4240–4252, Jun. 2025, doi: 10.1109/TPAMI.2025.3538473.
