Enhancing multilevel tea leaf recognition based on improved YOLOv8n

In the tea industry, automated tea picking plays a vital role in improving efficiency and ensuring quality. Tea leaf recognition significantly impacts the precision and success of automated operations. In recent years, deep learning has achieved notable advancements in tea detection, yet research on multilevel composite features remains insufficient. To meet the diverse demands of automated tea picking, this study aims to enhance the recognition of different tea leaf categories. A novel method for generating overlapping-labeled tea category datasets is proposed. Additionally, the Tea-You Only Look Once v8n (T-YOLOv8n) model is introduced for multilevel composite tea leaf detection. By incorporating the Convolutional Block Attention Module (CBAM) and the Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature fusion, the improved T-YOLOv8n model demonstrates superior performance in detecting small and overlapping targets. Moreover, integrating the CIOU and Focal Loss functions further optimizes the accuracy and stability of bounding box predictions. Experimental results highlight that the proposed T-YOLOv8n surpasses YOLOv8, YOLOv5, and YOLOv9 in mAP50, achieving a notable precision increase from 70.5% to 74.4% and recall from 73.3% to 75.4%. Additionally, computational costs are reduced by up to 19.3%, confirming its robustness and suitability for complex tea garden environment. The proposed model demonstrates improved detection accuracy while maintaining computationally efficient operations, facilitating practical deployment in resource-constrained edge computing environments. By integrating advanced feature fusion and data augmentation techniques, the model demonstrates enhanced adaptability to diverse lighting conditions and background variations, improving its robustness in practical scenarios. Moreover, this study contributes to the development of smart agricultural technologies, including intelligent tea leaf classification, automated picking, and real-time tea garden monitoring, providing new opportunities to enhance the efficiency and sustainability of tea production.