BPSOF-YOLO11n: YOLO11n-based method for blueberry maturity detection using boundary protection and small-object features
Abstract
IntroductionBlueberries are small and densely clustered, and their color transitions between different stages of ripeness are relatively gradual, which may lead to detection omissions and confusion with adjacent classes in real-world scenarios.MethodsWe developed the BPSOF-YOLO11n model by adding a high-resolution P2 (the second layer of the feature pyramid, corresponding to a high-resolution feature map with an output stride of 4) detection branch to YOLO11n, inserting a Residual Convolutional Block Attention Module (ResCBAM) with a flexible gating mechanism into the P2 fusion path, and applying a Maturity Boundary Protection (MBP) classification loss during the second-stage fine-tuning process with a low learning rate. MBP combines hard semi-ripe positive sample learning, adjacent-class ranking, and endpoint class protection. We evaluated the model on public and in-house datasets using validation set and held-out test set metrics, matched second-stage control groups, error analysis, and LayerCAM visualizations.ResultsBPSOF-YOLO11n achieved mean average precision (mAP)@0.5 values of 91.92% and 92.72% on the public and self-built validation sets, respectively. On the publicly available test set, compared to the regular second-stage fine-tuning, the three sub-comparisons of the matching improved by an average of 0.126 percentage points on [email protected] and by an average of 0.099 percentage points on [email protected]:0.95. In the self-built seed-0 comparison, MBP improved the semi-mature [email protected] by 0.240 percentage points and reduced the adjacent-stage error from 38 to 35.DiscussionBPSOF-YOLO11n enhances feature retention and ripeness classification capabilities for small fruits, while MBP provides task-specific optimization without increasing inference parameters or computational branches.
Related
- CGW-DETR: a multi-scale feature enhanced RT-DETR Qianxi cherry tomato maturity detection model for dense small targets
- Characterizing fatigue-related neural signatures via multi-band EEG features and a three-stage feature optimization strategy for driver fatigue detection
- Design of a comprehensive protection algorithm for fault detection, classification, and location in high voltage direct current transmission lines connected to wind farms based on local terminal measurements
- Integrated fertilization with brazide-mediated regulation improves stem mechanical strength, yield, and water-use efficiency of blueberry under semi-arid conditions
- Genetic control underlying dynamics of blueberry bioactive compounds during postharvest can drive breeding for functional fruits
BibTeX
@article{chen2026bpsofyolo11n,
title = {{BPSOF-YOLO11n: YOLO11n-based method for blueberry maturity detection using boundary protection and small-object features}},
author = {Lichang Chen and Jie Xie and Zhenya Wang and Junwei Huang and Leyan Chen and Yuxuan Zhang},
journal = {Frontiers in Plant Science},
year = {2026},
month = nov,
doi = {10.3389/fpls.2026.1982212},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1982212},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - BPSOF-YOLO11n: YOLO11n-based method for blueberry maturity detection using boundary protection and small-object features
AU - Lichang Chen
AU - Jie Xie
AU - Zhenya Wang
AU - Junwei Huang
AU - Leyan Chen
AU - Yuxuan Zhang
PY - 2026
DA - 2026/11/05
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1982212
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1982212
AB - IntroductionBlueberries are small and densely clustered, and their color transitions between different stages of ripeness are relatively gradual, which may lead to detection omissions and confusion with adjacent classes in real-world scenarios.MethodsWe developed the BPSOF-YOLO11n model by adding a high-resolution P2 (the second layer of the feature pyramid, corresponding to a high-resolution feature map with an output stride of 4) detection branch to YOLO11n, inserting a Residual Convolutional Block Attention Module (ResCBAM) with a flexible gating mechanism into the P2 fusion path, and applying a Maturity Boundary Protection (MBP) classification loss during the second-stage fine-tuning process with a low learning rate. MBP combines hard semi-ripe positive sample learning, adjacent-class ranking, and endpoint class protection. We evaluated the model on public and in-house datasets using validation set and held-out test set metrics, matched second-stage control groups, error analysis, and LayerCAM visualizations.ResultsBPSOF-YOLO11n achieved mean average precision (mAP)@0.5 values of 91.92% and 92.72% on the public and self-built validation sets, respectively. On the publicly available test set, compared to the regular second-stage fine-tuning, the three sub-comparisons of the matching improved by an average of 0.126 percentage points on [email protected] and by an average of 0.099 percentage points on [email protected]:0.95. In the self-built seed-0 comparison, MBP improved the semi-mature [email protected] by 0.240 percentage points and reduced the adjacent-stage error from 38 to 35.DiscussionBPSOF-YOLO11n enhances feature retention and ripeness classification capabilities for small fruits, while MBP provides task-specific optimization without increasing inference parameters or computational branches.
SN - 1664-462X
ER -