Previous Article in Journal
Identifying Optimal Parts of Oriental Lily Bulbs for Large-Scale Propagation Using Tissue Culture Bulb Induction
Previous Article in Special Issue
A Vision-Based Information Processing Framework for Vineyard Grape Picking Using Two-Stage Segmentation and Morphological Perception
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

BMDNet-YOLO: A Lightweight and Robust Model for High-Precision Real-Time Recognition of Blueberry Maturity

1
School of Mechanical and Electrical Engineering, Huainan Normal University, Huainan 232038, China
2
Department of Crop and Soil Sciences, College of Agriculture and Environmental Sciences, University of Georgia, Tifton, GA 31793, USA
*
Author to whom correspondence should be addressed.
Horticulturae 2025, 11(10), 1202; https://doi.org/10.3390/horticulturae11101202 (registering DOI)
Submission received: 2 September 2025 / Revised: 30 September 2025 / Accepted: 4 October 2025 / Published: 5 October 2025

Abstract

Accurate real-time detection of blueberry maturity is vital for automated harvesting. However, existing methods often fail under occlusion, variable lighting, and dense fruit distribution, leading to reduced accuracy and efficiency. To address these challenges, we designed a lightweight deep learning framework that integrates improved feature extraction, attention-based fusion, and progressive transfer learning to enhance robustness and adaptability To overcome these challenges, we propose BMDNet-YOLO, a lightweight model based on an enhanced YOLOv8n. The backbone incorporates a FasterPW module with parallel convolution and point-wise weighting to improve feature extraction efficiency and robustness. A coordinate attention (CA) mechanism in the neck enhances spatial-channel feature selection, while adaptive weighted concatenation ensures efficient multi-scale fusion. The detection head employs a heterogeneous lightweight structure combining group and depthwise separable convolutions to minimize parameter redundancy and boost inference speed. Additionally, a three-stage transfer learning framework (source-domain pretraining, cross-domain adaptation, and target-domain fine-tuning) improves generalization. Experiments on 8,250 field-collected and augmented images show BMDNet-YOLO achieves 95.6% mAP@0.5, 98.27% precision, and 94.36% recall, surpassing existing baselines. This work offers a robust solution for deploying automated blueberry harvesting systems.
Keywords: blueberry fruit; maturity detection; transfer learning; YOLOv8; light weight model blueberry fruit; maturity detection; transfer learning; YOLOv8; light weight model

Share and Cite

MDPI and ACS Style

Sun, H.; Wang, R.-F. BMDNet-YOLO: A Lightweight and Robust Model for High-Precision Real-Time Recognition of Blueberry Maturity. Horticulturae 2025, 11, 1202. https://doi.org/10.3390/horticulturae11101202

AMA Style

Sun H, Wang R-F. BMDNet-YOLO: A Lightweight and Robust Model for High-Precision Real-Time Recognition of Blueberry Maturity. Horticulturae. 2025; 11(10):1202. https://doi.org/10.3390/horticulturae11101202

Chicago/Turabian Style

Sun, Huihui, and Rui-Feng Wang. 2025. "BMDNet-YOLO: A Lightweight and Robust Model for High-Precision Real-Time Recognition of Blueberry Maturity" Horticulturae 11, no. 10: 1202. https://doi.org/10.3390/horticulturae11101202

APA Style

Sun, H., & Wang, R.-F. (2025). BMDNet-YOLO: A Lightweight and Robust Model for High-Precision Real-Time Recognition of Blueberry Maturity. Horticulturae, 11(10), 1202. https://doi.org/10.3390/horticulturae11101202

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop