In response to issues such as low resolution, severe occlusion, and insufficient fine-grained feature extraction in tea plantation disease detection, this study proposes an improved YOLOv10 network based on low-altitude unmanned aerial vehicle remote sensing for the detection of diseases in Yunnan large-leaf tea trees. Through the use of a Shape-IoU optimized loss function, a Wavelet Transform Convolution to enhance the network’s Backbone, and a Histogram Transformer to optimize the network’s Neck, the detection accuracy and localization precision of disease targets were significantly improved. Through testing of common diseases, the research results indicate that, for the improved YOLOv10 network, the Box Loss, Cls Loss, and DFL Loss were reduced by 15.94%, 13.16%, and 8.82%, respectively, in the One-to-Many Head, and by 14.58%, 17.72%, and 8.89%, respectively, in the One-to-One Head. Compared to the original YOLOv10 network, precision, recall, and F1 increased by 3.4%, 10.05%, and 6.75%, respectively. The improved YOLOv10 network not only effectively addresses phenomena such as blurry images, complex backgrounds, strong illumination, and occlusion in disease detection, but also demonstrates high levels of precision and recall, thereby providing robust technological support for precision agriculture and decision-making, and to a certain extent promoting the development of agricultural modernization.

To address the problem of detecting foreign bodies in Pu-erh tea, this study proposes an intelligent detection method based on an improved YOLOv10 network. By introducing the MPDIoU loss function, the YOLOv10 network is optimized to effectively enhance the positioning accuracy of the model in complex background and improve detection of small target foreign objects. Using AssemFormer to optimize the structure, the network’s ability to perceive small target foreign objects and its ability to process global information are improved. By introducing the Rectangular Self-Calibrated Module, the prediction accuracy of the bounding box is effectively optimized, further improving the classification and target-positioning abilities of the model in complex scenes. The results showed that the Box, Cls, and Dfl loss functions of the CV-YOLOv10-AR-M network in the One-to-Many Head task were, respectively, 14.60%, 19.74%, and 20.15% lower than those of the YOLOv10 network. In the One-to-One Head task, they decreased by 10.42%, 29.11%, and 20.15%, respectively. Compared with the original YOLOv10 network, the accuracy, recall rate, and mAP of the CV-YOLOv10-AR-M network were increased by 5.35%, 11.72% and 8.32%, respectively. The CV-YOLOv10-AR-M network effectively improves the model’s attention to small sizes, complex backgrounds, and detailed information, providing effective technical support for intelligent quality control in the agricultural field.

To investigate different contents of pu-erh tea polyphenol affected by abiotic stress, this research determined the contents of tea polyphenol in teas produced by Yuecheng, a Xishuangbanna-based tea producer in Yunnan Province. The study drew a preliminary conclusion that eight factors, namely, altitude, nickel, available cadmium, organic matter, N, P, K, and alkaline hydrolysis nitrogen, had a considerable influence on tea polyphenol content with a combined analysis of specific altitudes and soil composition. The nomogram model constructed with three variables, altitude, organic matter, and P, screened by LASSO regression showed that the AUC of the training group and the validation group were respectively 0.839 and 0.750, and calibration curves were consistent. A visualized prediction system for the content of pu-erh tea polyphenol based on the nomogram model was developed and its accuracy rate, supported by measured data, reached 80.95%. This research explored the change of tea polyphenol content under abiotic stress, laying a solid foundation for further predictions for and studies on the quality of pu-erh tea and providing some theoretical scientific basis.

The 6-DOF Stewart parallel elevation platform serves as the platform for mounting the tea-picking robotic arm, significantly impacting the operational scope, velocity, and harvesting precision of the robotic arm. Utilizing the Stewart setup, a parallel elevation platform with automated lifting and leveling capabilities was devised, ensuring precise halts at designated elevations for seamless harvesting operations. The effectiveness of the platform parameter configuration and the reasonableness of the posture changes were verified. Firstly, the planting mode and growth characteristics of Yunnan large-leaf tea trees were analyzed to determine the preset path, posture changes, and mechanism stroke of the Stewart parallel lifting platform, thereby determining the basic design specifications of the platform. Secondly, a 3D model was established using SolidWorks, a robust adaptive PD control model was built using MATLAB for simulation, and dynamic calculations were carried out through data interaction in Simulink and ADAMS. Finally, the rationality of the lifting platform design requirements was determined based on simulation data, a 6-DOF Stewart parallel lifting platform was manufactured, and a motion control system was built for experimental verification according to the design specifications and simulation data. The results showed that the maximum deviation angle around the X, Y, and Z axes was 10°, the maximum lifting distance was 15 cm, the maximum load capacity was 60 kg, the platform response error was within ±0.1 mm, and the stable motion characteristics reached below the millimeter level, which can meet the requirements of automated operation of the auxiliary picking robotic arm.

To address the challenges of variable target scale, complex background, blurred image, and serious occlusion in the yield detection of Yunnan large-leaf tea tree, this study proposes a deep learning network DE-YOLOv13-S that integrates the visual mechanism of primates. DynamicConv was used to optimize the dynamic adjustment process of the effective receptive field and channel the gain of the primate visual system. Efficient Mixed-pooling Channel Attention was introduced to simulate the observation strategy of ‘global gain control and selective integration parallel’ of the primate visual system. Scale-based Dynamic Loss was used to simulate the foveation mechanism of primates, which significantly improved the positioning accuracy and robustness of Yunnan large-leaf tea tree yield detection. The results show that the Box Loss, Cls Loss, and DFL Loss of the DE-YOLOv13-S network decreased by 18.75%, 3.70%, and 2.54% on the training set, and by 18.48%, 14.29%, and 7.46% on the test set, respectively. Compared with YOLOv13, its parameters and gradients are only increased by 2.06 M, while the computational complexity is reduced by 0.2 G FLOPs, precision, recall, and mAP are increased by 3.78%, 2.04% and 3.35%, respectively. The improved DE-YOLOv13-S network not only provides an efficient and stable yield detection solution for the intelligent management level and high-quality development of tea gardens, but also provides a solid technical support for the deep integration of bionic vision and agricultural remote sensing.

To explore the changes in epigallocatechin gallate (EGCG) content in tea under abiotic stress conditions, we collected tea samples, along with corresponding soil and altitude data, and utilized the measured data for single-factor analysis. At the same time, the LASSO regression method, which is rarely used in agriculture, was employed to screen modeling factors, a prediction model was established, and the Akaike information criterion (AIC) was introduced to compare the goodness of fit. The results show that LASSO screening reduced the AIC value of the model by 13.8%. The average area under the curve of the training set and the validation set was 0.81 and 0.76, respectively, and the calibration curve also showed good consistency. Based on the nomogram model, a visual prediction system was developed, and the content prediction curve was introduced for detailed soil evaluation. The accuracy rate reached 75% after external verification. This study provides a theoretical basis for elucidating the prediction and intervention of Pu’er tea quality under abiotic stress conditions.