Object detection method for kiwifruit (Actinidia deliciosa) based on improved YOLO11x-mod
Keywords:
Yolo11x-mod, kiwifruit detection, hyperparameter optimization, object detection, precision farming, robotic systemsAbstract
Kiwi is one of the most important agricultural products in Turkey, and its maturity directly determines the quality and market value of the product. Therefore, there is a need for an accurate and reliable detection system that can minimize post-harvest losses while increasing productivity. In this study, a dataset of 420 images taken under different environmental conditions was expanded to 928 images using data augmentation techniques, and a total of 22 750 kiwi samples were labeled. In the study, the latest deep learning architectures, YOLOv8, YOLOv10, and YOLO11, were systematically compared under identical conditions. As a result of these comparisons, the YOLO11x-mod model showed the highest performance when optimized with hyperparameter strategies such as AdamW optimization, low weight decay, appropriate learning rate, and dropout-mosaic augmentation techniques. This model achieved 81.76% accuracy, 83.97% recognition rate, 86.19% mAP@50, and 66.80% mAP@50:95, delivering excellent results, especially in challenging scenarios such as dense foliage, object overlap, and variable lighting conditions. In addition, the model’s operation with 72.5 million parameters, 272 GFLOPs, and 42 fps was found to be suitable for real-time applications, balancing accuracy and speed. The insights gained from the study establish the YOLO11x-mod model as a new reference point for kiwi detection and directly address limitations in the literature regarding insufficient detection of small or overlapping fruits. In this respect, the results of this study not only contribute to science but also show great potential for the integration of the model into robotic harvesting systems and precision agriculture applications.
Key words: YOLO11x-mod; kiwifruit detection; hyperparameter optimization; object detection; precision farming; robotic systems
DOI: 10.25165/j.ijabe.20261904.10188
Citation: Kahya E. Object detection method for kiwifruit (Actinidia deliciosa) based on improved YOLO11x-mod. Int J Agric
& Biol Eng, 2026; 19(4): 214–226.
References
[1] Zhang Z Y, Zeng S C, Ji T K, Cao M K, Guo W C. Generation of fruit’s spectra with hundreds of wavelengths from obtained multi-spectra and spectral application using deep learning. Computers and Electronics in Agriculture, 2023; 210: 107882.
[2] Wu K, Jia Z C, Duan Q F. The detection of kiwifruit sunscald using spectral reflectance data combined with machine learning and CNNs. Agronomy, 2023; 13(8): 2137.
[3] Wan C, Yue R, Li Z F, Fan K, Chen X K, Li F L. Prediction of kiwifruit sweetness with Vis/NIR spectroscopy based on scatter correction and feature selection techniques. Applied Sciences, 2024; 14(10): 4145.
[4] Wang L. Improve yield prediction with UAS-based leaf area index estimation and a hybrid machine learning-and process-based model. PhD dissertation. Lincoln: The University of Nebraska-Lincoln. 2022; 114p.
[5] Wang L Z, Gao R, Li C C, Wang J, Liu Y, Hu J Y, Yue J B. Mapping soybean maturity and biochemical traits using UAV-based hyperspectral images. Remote Sensing, 2023; 15(19): 4807.
[6] Liu J F, Liu Z B. YOLOv5s-BC: an improved YOLOv5s-based method for real-time apple detection. Journal of Real-Time Image Processing, 2024; 21(3): 88.
[7] Zhang J L, Su W H, Zhang H Y, Peng Y. SE-YOLOv5x: An optimized model based on transfer learning and visual attention mechanism for identifying and localizing weeds and vegetables. Agronomy, 2022; 12(9): 2061.
[8] Yang W J, Ma X X, Hu W C, Tang P J. Lightweight blueberry fruit recognition based on multi-scale and attention fusion NCBAM. Agronomy, 2022; 12(10): 2354.
[9] Su F, Zhao Y P, Shi Y X, Zhao D, Wang, G H, Yan Y F, et al. Tree trunk and obstacle detection in apple orchard based on improved YOLOv5s model. Agronomy, 2022; 12(10): 2427.
[10] Wu Y Q, Sun Y B, Zhang S Q, Liu X, Zhou K, Hou J L. A size-grading method of antler mushrooms using YOLOv5 and PSPNet. Agronomy, 2022; 12(11): 2601.
[11] Rong J C, Fu J, Zhang Z Q, Yin J L, Tan Y Z, Yuan T, et al. Development and evaluation of a watermelon-harvesting robot prototype: Vision system and end-effector. Agronomy, 2022; 12(11): 2836.
[12] Xie J X, Peng J J, Wang J X, Chen B H, Jing T W, Sun D Z, et al. Litchi detection in a complex natural environment using the YOLOv5-Litchi model. Agronomy, 2022; 12(12): 3054.
[13] Fu X, Li A, Meng Z, Yin X, Zhang C, Zhang W, et al. A dynamic detection method for phenotyping pods in a soybean population based on an improved YOLO-v5 Network. Agronomy, 2022; 12(12): 3209.
[14] Wang C, Wang H, Han Q Y, Zhang Z G, Kong D D, Zou X J. Strawberry detection and ripeness classification using YOLOv8+ model and image processing method. Agriculture, 2024; 14(5): 751.
[15] Wang Y, Rong Q, Hu C. Ripe tomato detection algorithm based on improved YOLOv9. Plants, 2024; 13(22): 3253.
[16] Zhou Z X, Song Z Z, Fu L S, Gao F F, Li R, Cui Y J. Real-time kiwifruit detection in orchard using deep learning on android™ smartphones for yield estimation. Computers and Electronics in Agriculture, 2020; 179: 105856.
[17] Lim J, Ahn H S, Nejati M, Bell J, Williams H, MacDonald B A. Deep neural network-based real-time kiwi fruit flower detection in an orchard environment. arXiv preprint, 2020; arXiv: 2006.04343. doi: 10.48550/arXiv.2006.04343.
[18] Ulutas E G, Altın C. Kiwi fruit detection with deep learning methods. International Journal of Advanced Natural Sciences and Engineering Researches, 2023; 7(7): 39–45.
[19] Pawar S E, Surana A V, Sharma P, Pujeri R. Fruit disease detection and classification using machine learning and deep learning techniques. International Journal of Intelligent Systems and Applications in Engineering, 2024; 12(4s): 440–453.
[20] Xia Y, Nguyen M, Yan W Q. A real-time kiwifruit detection based on improved YOLOv7. In: Image and Vision Computing. IVCN 2022. Lecture Notes in Computer Science, 2023; pp.48–61. doi: 10.1007/978-3-031-25825-1_4.
[21] Dewi C, Thiruvady D, Zaidi N. Fruit classification system with deep learning and neural architecture search. arXiv preprint, 2024; arXiv: 2406.01869. doi: 10.48550/arXiv.2406.01869.
[22] Selva Kumari R S, Gomathy V. Fruit shop tool: Fruit classification and recognition using deep learning. Agricultural Engineering International: CIGR Journal, 2023; 25(2): 312–321.
[23] Ma L, He Z, Zhu Y T, Jia L S, Wang Y C, Ding X T, et al. A method of grasping detection for kiwifruit harvesting robot based on deep learning. Agronomy, 2022; 12(12): 3096.
[24] Banerjee D, Kukreja V, Hariharan S, Sharma V. Fast and accurate multi-classification of kiwi fruit disease in leaves using deep learning approach. In: 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), Uttarakhand: IEEE, 2023; pp.131–137. doi: 10.1109/ICIDCA56705.2023.10099755.
[25] Ebrahimi S, Pourdarbani R, Sabzi S, Rohban M H, Arribas J I. From harvest to market: Non-destructive bruise detection in kiwifruit using convolutional neural networks and hyperspectral imaging. Horticulturae, 2023; 9(8): 936.
[26] Elsayed S, Gala H, Abd El-baki M S, Maher M, Elbeltagi A, Salem A, et al. Hyperspectral technology and machine learning models to estimate the fruit quality parameters of mango and strawberry crops. PloS One, 2025; 20(2): e0313397.
[27] Niu Z J, Deng J T, Zhang X., Zhang J, Pan S J, Mu H T. Identifying the branch of kiwifruit based on unmanned aerial vehicle (UAV) images using deep learning method. Sensors, 2021; 21(13): 4442.
[28] Song Z Z, Zhou Z X, Wang W Q, Gao F F, Fu L S, Li R, et al. Canopy segmentation and wire reconstruction for kiwifruit robotic harvesting. Computers and Electronics in Agriculture, 2021; 181: 105933.
[29] Yang Y, Su L J, Zong A Y, Tao W H, Xu X P, Chai Y X, et al. A new kiwi fruit detection algorithm based on an improved lightweight network. Agriculture, 2024; 14(10): 1823.
[30] Zhao G R, Dong S, Wen J, Ban Y C, Zhang, X W. Selective fruit harvesting prediction and 6D pose estimation based on YOLOv7 multi-parameter recognition. Computers and Electronics in Agriculture, 2025; 229: 109815.
[31] Rodríguez-Álvarez J L, García-Alcaraz J L, Vidal R P, Cuevas-Jacques R, Díaz-Reza J R. Noninvasive system for weight estimation in cactus crops: A YOLOv5-decision tree approach based on interval type-2 fuzzy sets. Chemometrics and Intelligent Laboratory Systems, 2024; 245: 105064.
[32] Pesce L. Machine learning for predicting grape quality using spectral imaging techniques. PhD dissertation, Politecnico di Torino, 2024; 101p.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
