Journal of Applied Science and Engineering

Published by Tamkang University Press

ESCI jase impact factor scopus logo open access rate of Scopus journal

MMD-YOLO: A Multi-scale Maturity Detection Model for Occluded apples in Complex Environments

 2026

 Volume 33

Yuehua Zhang1, Xinguang Zhao2, and Fengting Liu1

1School of Information Engineering Shandong Huayu University of Technology, De Zhou, China, 253034

2Finance Department, Huarui International Engineering Consulting Group Co., Ltd.

Received: March 30, 2026
Accepted: May 13, 2026
Publication Date: June 25, 2026

上傳圖片

Proposed MMD-YOLO Workflow 

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation:  BibTeX | http://dx.doi.org/10.6180/jase.202610_33.006  

Download PDF

Apple production is vital to global horticulture, with precision agriculture increasingly using computer vision and deep learning. This study evaluates apple detection and maturity classification using the AppleBBCH76 and AppleBBCH81 datasets, comprising 5,007 annotated orchard images. You Only Look Once (YOLO) models support fruit detection, yield prediction, and maturity analysis, yet orchard challenges like occlusion, overlap,
variable sizes, and lighting reduce accuracy. To address this, a Multi-scale Maturity Detection-YOLO (MMD YOLO) model integrates multi-scale feature extraction with a fine-tuned YOLOv11. Pre-processing included resizing, median filtering, Contrast Limited Adaptive Histogram Equalization (CLAHE), and normalization, with Bayesian optimization. Results show 93.40% mAP@0.5,94.60% precision, 93.50% recall, and 94% F1-score, surpassing earlier YOLO versions.

Keywords: Apple maturity detection; YOLOv11; multi-scale feature extraction; Occluded apple detection; Orchard monitoring; Precision agriculture

  1. [1] H. Tang, X. Zhai, and X. Xu, (2025) “Flowering variation induces apple maturity variation at harvest” Frontiers in Agronomy 7: 1545070. DOI: 10.3389/fagro.2025.1545070.
  2. [2] J.-C. Lee, Y.-S. Park, H.-N. Jeong, J.-H. Kim, and J.-Y. Heo, (2023) “Temperature Changes Affected Spring Phenology and Fruit Quality of Apples Grown in High-Latitude Region of South Korea” Horticulturae 9(7): 794. DOI: 10.3390/horticulturae9070794.
  3. [3] M. Lv, Y.-X. Xu, Y.-H. Miao, and W.-H. Su, (2025) “A comprehensive review of deep learning in computer vision for monitoring apple tree growth and fruit production” Sensors 25(8): 2433. DOI: 10.3390/s25082433.
  4. [4] Y. Pan, Y. Chen, X. Tong, M. Liu, A. Huang, M. Zhou, and Y. Hu, (2026) “YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments” Agronomy 16(3): 390. DOI: 10.3390/agronomy16030390.
  5. [5] B. Xiao, M. Nguyen, and W. Q. Yan. “Apple ripeness identification using deep learning”. In: International symposium on geometry and vision. Springer. 2021, 53–67. DOI: 10.1007/978-3-030-72073-5_5.
  6. [6] Z. Yan, Y. Wu, W. Zhao, S. Zhang, and X. Li, (2025) “Research on an Apple Recognition and Yield Estimation Model Based on the Fusion of Improved YOLOv11 and DeepSORT” Agriculture 15(7): 765. DOI: 10.3390/agriculture15070765.
  7. [7] L. Sun, G. Hu, C. Chen, H. Cai, C. Li, S. Zhang, and J. Chen, (2022) “Lightweight apple detection in complex orchards using YOLOv5-PRE” Horticulturae 8(12): 1169. DOI: 10.3390/horticulturae8121169.
  8. [8] Y. Huang, S. Xu, H. Chen, G. Li, H. Dong, J. Yu, X. Zhang, and R. Chen, (2025) “A review of visual perception technology for intelligent fruit harvesting robots” Frontiers in Plant Science 16: 1646871. DOI: 10.3389/fpls.2025.1646871.
  9. [9] D. Wang and D. He, (2022) “Apple detection and instance segmentation in natural environments using an improved Mask Scoring R-CNN Model” Frontiers in Plant Science 13: 1016470. DOI: 10.3389/fpls.2022.1016470.
  10. [10] T. Hu, W. Wang, J. Gu, Z. Xia, J. Zhang, and B. Wang, (2023) “Research on Apple Object Detection and Localization Method Based on Improved YOLOX and RGB-D Images” Agronomy 13(7): 1816. DOI: 10.3390/agronomy13071816.
  11. [11] X. Wang, Y. Huang, S. Wei, W. Xu, X. Zhu, J. Mu, and X. Chen, (2025) “Eld-yolo: A lightweight framework for detecting occluded mandarin fruits in plant research” Plants 14(11): 1729. DOI: 10.3390/plants14111729.
  12. [12] P. Chu, Z. Li, K. Zhang, D. Chen, K. Lammers, and R. Lu, (2023) “O2RNet: Occluder-occludee relational network for robust apple detection in clustered orchard environments” Smart Agricultural Technology 5: 100284. DOI: 10.1016/j.atech.2023.100284.
  13. [13] T. Li, Q. Feng, Q. Qiu, F. Xie, and C. Zhao, (2022) “Occluded Apple Fruit Detection and Localization with a Frustum-Based Point-Cloud-Processing Approach for Robotic Harvesting” Remote Sensing 14(3): 482. DOI: 10.3390/rs14030482.
  14. [14] H. Fu, Z. Guo, Q. Feng, F. Xie, Y. Zuo, and T. Li, (2024) “MSOAR-YOLOv10: Multi-Scale Occluded Apple Detection for Enhanced Harvest Robotics” Horticulturae 10(12): 1246. DOI: 10.3390/horticulturae10121246.
  15. [15] X. Liu, C. Hu, X. Huang, C. Sun, R. Zhu, C. Wang, Y. Zhang, Q. Shen, H. Zhou, and C. Ruan, (2025) “The apple detection method based on multimodal features” PLoS One 20(10): e0334911. DOI: 10.1371/journal.pone.0334911.
  16. [16] RTA & LatHort projects. AppleBBCH76. https://www.kaggle.com/datasets/projectlzp201910094/applebbch76 [Accessed: 2026-04-11]. 2026.
  17. [17] RTA & LatHort projects. AppleBBCH81. https://www.kaggle.com/datasets/projectlzp201910094/applebbch81 [Accessed: 2026-04-11]. 2026.