Accurate bud detection is a prerequisite for automatic tea picking and yield statistics; however, current research suffers from missed detection due to the variety of singleness and false detection under complex backgrounds. Traditional target detection models are mainly based on CNN, but CNN can only achieve the extraction of local feature information, which is a lack of advantages for the accurate identification of targets in complex environments, and Transformer can be a good solution to the problem. Therefore, based on a multi-variety tea bud dataset, this study proposes RT-DETR-Tea, an improved object detection model under the real-time detection Transformer (RT-DETR) framework. This model uses cascaded group attention to replace the multi-head self-attention (MHSA) mechanism in the attention-based intra-scale feature interaction (AIFI) module, effectively optimizing deep features and enriching the semantic information of features. The original cross-scale feature-fusion module (CCFM) mechanism is improved to establish the gather-and-distribute-Tea (GD-Tea) mechanism for multi-level feature fusion, which can effectively fuse low-level and high-level semantic information and large and small tea bud features in natural environments. The submodule of DilatedReparamBlock in UniRepLKNet was employed to improve RepC3 to achieve an efficient fusion of tea bud feature information and ensure the accuracy of the detection head. Ablation experiments show that the precision and mean average precision of the proposed RT-DETR-Tea model are 96.1% and 79.7%, respectively, which are increased by 5.2% and 2.4% compared to those of the original model, indicating the model’s effectiveness. The model also shows good detection performance on the newly constructed tea bud dataset. Compared with other detection algorithms, the improved RT-DETR-Tea model demonstrates superior tea bud detection performance, providing effective technical support for smart tea garden management and production.

This study addresses two key challenges in tea nutrient analysis: the limited range of detectable nutrient elements in tea gardens and the interference caused by moisture in fresh tea leaves during spectral data acquisition. To overcome these issues, hyperspectral technology combined with effective spectral intelligent processing algorithms was used to develop quantitative, non-destructive prediction models for four essential nutrients—nitrogen, phosphorus, potassium and carbon—in fresh tea leaves. This study utilises EPO to address the issue of moisture interference in the spectra of fresh tea leaves, and combines it with SG for spectral data processing, namely SG-EPO. Through comparative analysis with traditional pre-processing algorithms, this method was found to effectively reduce moisture interference in fresh tea leaves and enhance prediction accuracy (R²). Finally, based on a multi-stage feature selection strategy involving SG-EPO-VCPA-IRIV-SVM_RFE and SG-EPO-BOSS-SVM_RFE, and in combination with three machine learning models—XGBoost, BP and SVR—quantitative prediction models were developed. The results indicated that the R² for nitrogen is 0.896; phosphorus, 0.954; potassium, 0.913; and carbon, 0.928. The RMSEP values for N, P, K, and C were 0.062, 0.075, 0.438, and 0.157, respectively. Using this model, nitrogen, phosphorus, potassium and carbon contents were rapidly predicted in tea leaves after the exogenous application of GABA at different concentrations, enabling an assessment of the effects of exogenous GABA application on these nutrient levels. Furthermore, the Shapley Additive Explanation method was employed to identify the feature wavelengths that had the greatest contribution to the XGBoost model, effectively explaining the information underlying the improved model predictions regarding the correlation between spectral and chemical values. Finally, the accuracy of the predictions was confirmed using 20 samples from independent data, demonstrating that the proposed model can achieve rapid, non-destructive detection of multiple nutrient elements in fresh tea leaves under in situ conditions in tea plantations.

Real-time measurement of tea bud phenotypes via mobile devices is constrained by model lightweighting challenges, and research on non-contact measurement of tea bud phenotypes based on key points remains largely unexplored. Information on the growth posture of tea buds is an important basis for determining tea maturity grades, quality monitoring, and tea breeding. Therefore, this work develops a deep learning-enabled YOLOv8p-Tea model to estimate key point information of tea bud posture and automatically obtain three-dimensional point cloud information of tea buds by integrating depth information, thereby achieving in situ measurement of tea bud phenotypic parameters. Meanwhile, the model is trained and validated using a tea bud (one-bud-three-leaf) image dataset, and its effectiveness is demonstrated through experiments. Compared to the YOLOv8p-pose model, the model achieves a mAP50 of 98.3%, a P of 97%, and parameters of 0.72 M, with mAP50 and P improved by 1.5% and 1.9%, respectively, and the parameter count is reduced by 25%. To validate the accuracy of phenotypic extraction, the model was deployed on edge devices, and 30 tea buds with one bud and three leaves were randomly selected in a tea garden. The final in situ measurement results showed an MRE of 6.63%. Experimental findings indicate that the developed method is capable of not only effectively estimate tea bud posture but also accurately achieves in situ measurement of tea bud phenotypes, which holds potential applications for meeting the construction needs of smart tea gardens and optimizing tea breeding.