The mechanization of famous tea harvesting is an essential way to develop China’s tea industry. This paper centers on the detection and positioning technologies in famous tea harvesting, systematically reviewing research progress in these domains. In tea detection, traditional methods rely on color space selection and image segmentation, exhibiting limitations such as insufficient accuracy and poor generalization capability. Conversely, deep learning algorithms demonstrate superior detection accuracy and robustness. Current research focuses on enhancing detection accuracy, inference speed, and multi-variety recognition. In picking positioning, depth information measurement technology utilizing RGB-D cameras provides foundational support. Positioning methods have evolved from traditional visual processing techniques to deep learning and point cloud approaches, seeking to overcome challenges including occlusion and irregular growth patterns. Notwithstanding notable technological advancements, existing methods confront three primary limitations: difficulties in adapting to diverse growth stage characteristics, reliance on large-scale annotated datasets, and inadequate occlusion handling. Future research ought to concentrate on three directions: developing highly universal tea bud detection models, refining model training techniques for small-sample scenarios, and improving tea-picking point positioning accuracy under occluded conditions. This review aims to furnish critical references for advancing high-end intelligent tea-picking machinery, thereby facilitating the tea industry’s mechanization and intelligentization.

Tea shoot segmentation is crucial for the automation of high-quality tea plucking. However, accurate segmentation of tea shoots in unstructured and complex environments presents significant challenges due to the small size of the targets and the similarity in color between the shoots and their background. To address these challenges and achieve accurate recognition of tea shoots in complex settings, an advanced tea shoot segmentation network model is proposed based on You Only Look Once version 8 segmentation (YOLOv8-seg) network model. Firstly, to enhance the model’s segmentation capability for small targets, this study designed a feature fusion network that incorporates shallow, large-scale features extracted by the backbone network. Subsequently, the features extracted at different scales by the backbone network are fused to obtain both global and local features, thereby enhancing the overall information representation capability of the features. Furthermore, the Efficient Channel Attention mechanism was integrated into the feature fusion process and combined with a reparameterization technique to refine and improve the efficiency of the fusion process. Finally, Wise-IoU with a dynamic non-monotonic aggregation mechanism was employed to assign varying gradient gains to anchor boxes of differing qualities. Experimental results demonstrate that the improved network model increases the AP50 of box and mask by 4.33% and 4.55%, respectively, while maintaining a smaller parameter count and reduced computational demand. Compared to other classical segmentation algorithms models, the proposed model excels in tea shoot segmentation. Overall, the advancements proposed in this study effectively segment tea shoots in complex environments, offering significant theoretical and practical contributions to the automated plucking of high-quality tea.

In response to the prevailing scarcity of labor and with the aim of augmenting the proportion of premium-quality fruits, a robotic grading end-effector system for harvesting was meticulously designed. The end-effector could measure the soluble solid content (SSC) of peaches during the harvesting process to evaluate the quality of the fruit, thereby facilitating real-time grading during harvesting. As comprising a harvesting component and an information-gathering segment, the end-effector system was optimized with the primary structural parameters of its adaptive fingers using a mathematical model of peach morphology. Also, the buffering materials for mitigating the pressure exerted by the adaptive fingers on the peaches were compared. Furthermore, feasibility analyses of the grasping actions were conducted based on the interaction forces between the adaptive fingers and the peaches. To grade the quality of peaches, SSC was used as an indicator to assess and grade the quality of the peaches. The spectra of peaches within the wavelength range of 590-1100 nm were collected, and a predictive model for SSC was developed. The correlation coefficients for the calibration set and prediction sets of the predictive model were 0.880 and 0.890, with corresponding root mean square errors of 0.370% and 0.357% Brix, respectively. In addition, a robustness and accuracy assessment was conducted using 30 peach samples, yielding a correlation coefficient of 0.936 and a standard error of 0.386% Brix between the predicted and measured values of SSC. The results confirm that the end-effector can measure the SSC of peaches during the collection process, providing novel concepts and theoretical foundations for real-time harvesting and grading.