Implementation of YOLOv8 and DETR for Multi-Level Tomato Ripeness Detection with Real-Time Bounding Boxes
Abstract
Tomato ripeness detection is an essential component in the development of automated agricultural systems, enabling improvements in harvesting accuracy, sorting consistency, and supply chain standardization. Conventional grading processes rely heavily on manual observation, which is subjective, labor-intensive, and unsuitable for large-scale operations. Recent advancements in deep learning enable automated recognition of visual maturity indicators through object detection frameworks, offering a more reliable and scalable solution. This study examines the implementation of two modern detection models, YOLO and DETR, for multi-level tomato ripeness classification involving four distinct maturity stages. The research workflow includes dataset collection, annotation, preprocessing, model training, threshold calibration, and systematic evaluation to assess detection stability and classification behavior under real-world variability.Analysis of model outputs demonstrates that both architectures are capable of identifying multiple ripeness stages with useful levels of consistency, although each model exhibits strengths under different operational conditions. YOLO provides advantages in scenarios requiring real-time responsiveness and deployment on resource-limited hardware, making it suitable for mobile automation and field-based harvesting systems. DETR shows improved interpretive behavior in visually complex environments, particularly when samples exhibit subtle maturity differences or appear in overlapping cluster formations. The findings indicate that no single model is universally optimal and that deployment choice should be based on application requirements, environmental constraints, and operational objectives. This research contributes practical insight to the integration of artificial intelligence in agriculture and provides a foundation for future work exploring model fusion, advanced feature learning, or multispectral input integration to further enhance maturity classification performance.
Downloads
References
. Technologie, U. De and Parakou, U. De (2023) ‘Deep learning-based approach for tomato classification in complex scenes’.
. Technologie, U. De and Parakou, U. De (2023) ‘Deep learning-based approach for tomato classification in complex scenes’.
. Megantara, A. and Utami, E. (2025) ‘DeteObjectction Using YOLOv8 : A Systematic Review’, 14, pp. 1186–1193.
. Aeni, K. and Millah, A.S. (2025) ‘Implementasi Deteksi Objek Dengan Model YOLOV8 pada Pengenalan Bahasa Isyarat Implementation of Object Detection with YOLOV8 Model in Sign Language Recognition’, 14(105).
. Sun, H. et al. (2025) ‘An Improved YOLOv8 Model for Detecting Four Stages of Tomato Ripening and Its Application Deployment in a Greenhouse Environment’, pp. 1–33.
. Li, R. et al. (2023) ‘Tomato Maturity Recognition Model Based on Improved YOLOv5 in Greenhouse’.
. Yang, G. et al. (2023) ‘A Lightweight YOLOv8 Tomato Detection Algorithm Combining Feature Enhancement and Attention’.
. Abdullah, A. et al. (2024) ‘A Deep-Learning-Based Model for the Detection of Diseased’.
. Gao, X. et al. (2025) ‘YOLOv8n-CA : Improved YOLOv8n Model for Tomato Fruit Recognition at Different Stages of Ripeness’.
. Hanum, H.F. and Fathurahman, M. (2025) ‘Analisis Realisasi Sistem Identifikasi Tingkat Kematangan Buah Tomat Ceri dengan Model YOLOv8 di BBPP Lembang’, 6(April), pp. 311–316.
. Wang, S. et al. (2024) ‘Lightweight tomato ripeness detection algorithm based on the improved RT-DETR’, (July), pp. 1–19. Available at: https://doi.org/10.3389/fpls.2024.1415297.
. Fu, Y. et al. (2024) ‘Multi-stage tomato fruit recognition method based on improved YOLOv8’, (September), pp. 1–14. Available at: https://doi.org/10.3389/fpls.2024.1447263.
. Wu, M. et al. (2025) ‘Improved RT-DETR and its application to fruit ripeness detection’, (February), pp. 1–12. Available at: https://doi.org/10.3389/fpls.2025.1423682.
. Wei, J. et al. (2025) ‘Tomato ripeness detection and fruit segmentation based on instance segmentation’, (May), pp. 1–19. Available at: https://doi.org/10.3389/fpls.2025.1503256.
. Sun, H. et al. (2025) ‘ToRLNet : A Lightweight Deep Learning Model for Tomato Detection and Quality Assessment Across Ripeness Stages’, pp. 1–21.
. Yao, J. et al. (2025) ‘Edge-Guided DETR Model for Intelligent Sensing of Tomato Ripeness Under Complex Environments’, pp. 1–17.
. Le, A.T. (2024) ‘Lightweight CNN-RNN model for tomato leaf disease detection’.
. Giacomo, M. Di et al. (2023) ‘An Integrative Transcriptomics and Proteomics Approach to Identify Putative Genes Underlying Fruit Ripening in Tomato near Isogenic Lines with Long Shelf Life’.
. Meng, X., Chen, C. and Dong, W. (2025) ‘Tomato Leaf Disease Detection Method Based on Multi-Scale Feature Fusion’, pp. 1–22.
. Hermens, F. (2024) ‘Automatic object detection for behavioural research using YOLOv8’, pp. 7307–7330. Available at: https://doi.org/10.3758/s13428-024-02420-5.
. Moldvai, L. and Nyéki, A. (2025) ‘Innovative computer vision methods for tomato ( Solanum Lycopersicon ) detection and cultivation : a review’.
. Wu, J. et al. (2019) ‘Automatic Recognition of Ripening Tomatoes by Combining Multi-Feature Fusion with a Bi-Layer’. Available at: https://doi.org/10.3390/s19030612.
. Mu, Y., Chen, T. and Ninomiya, S. (2020) ‘Intact Detection of Highly Occluded Immature’, pp. 1–16.
. Environments, N. (2025) ‘GPC-YOLO : An Improved Lightweight YOLOv8n Network for’, pp. 1–20.
. Zhao, M. et al. (2025) ‘Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS’, pp. 1–17.
. Song, K. et al. (2025) ‘Research on High-Precision Target Detection Technology for Tomato-Picking Robots in Sustainable Agriculture’.
. Wang, M. and Li, F. (2025) ‘Real-Time Accurate Apple Detection Based on Improved YOLOv8n in Complex Natural Environments’.
. Wu, M. et al. (2024) ‘MTS-YOLO : A Multi-Task Lightweight and Efficient Model for Tomato Fruit Bunch Maturity and Stem Detection’, pp. 1–25.
. Wang, Y., Rong, Q. and Hu, C. (2024) ‘Ripe Tomato Detection Algorithm Based on Improved YOLOv9’.
. Mu, D. et al. (2025) ‘URT-YOLOv11 : A Large Receptive Field Algorithm for Detecting Tomato Ripening Under Different Field Conditions’, pp. 1–29.
Copyright (c) 2025 Muhammad Rizky Heriadi Putra, Deni Setiawan, Ahnaf putra hafezi, Rachmat Adi Purnama, Veti Apriana, Rame Santoso
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License which permits unrestricted use, distribution, and reproduction in any medium. Users are allowed to read, download, copy, distribute, search, or link to full-text articles in this journal without asking by giving appropriate credit, provide a link to the license, and indicate if changes were made. All of the remix, transform, or build upon the material must distribute the contributions under the same license as the original.
