SDGD-YOLO: a lightweight detection model for assessing the ripeness of black raspberries in complex greenhouse environments.

In complex greenhouse environments, black raspberries present challenges such as dense clusters, variable fruit sizes, continuous colour changes during ripening, and interference from foliage and uneven lighting. These issues lead to high false positives and false negatives in existing ripeness detection models, limiting their application in intelligent precision harvesting. To address this, this study proposes SDGD-YOLO, a novel ripeness detection model. First, a StarNet architecture is embedded into the feature extraction network to enhance cross-channel interaction and global semantic association, improving the extraction of key ripeness features. Second, a DySample dynamic upsampling module is introduced during multi-scale feature fusion to adapt to variations in fruit size and morphology across ripeness stages. Third, a collaborative optimization mechanism combining Soft-NMS and GIoU is applied in post-processing to reduce redundant bounding boxes and improve localization accuracy, effectively mitigating false positives and negatives under occlusion. Finally, a refined knowledge distillation mechanism via teacher-student joint training enhances detection performance while maintaining lightweight inference. The experimental results show that, compared with the baseline YOLOv13n, SDGD-YOLO achieves a precision of 91.0% (an increase of 3.6%), a recall of 71.8% (an increase of 4.7%), and an F1-score of 80.68% (an increase of 4.69%). with mAP50 and mAP50-95 reaching 81.7% (an increase of 5.7%) and 68.7% (an increase of 6.6%) respectively. Meanwhile, the number of model parameters has been reduced to 1.988 M, and GFLOPs to 5.8 G, achieving an effective balance between improved accuracy and reduced computational complexity. The SDGD-YOLO proposed in this study provides a technical reference for the accurate detection of berry ripeness in complex greenhouse environments.