Identification and picking point positioning of tender tea shoots based on MR3P-TS model

Abstract

Tea is one of the most common beverages in the world. In order to reduce the cost of artificial tea picking and improve the competitiveness of tea production, this paper proposes a new model, termed the Mask R-CNN Positioning of Picking Point for Tea Shoots (MR3P-TS) model, for the identification of the contour of each tea shoot and the location of picking points. In this study, a dataset of tender tea shoot images taken in a real, complex scene was constructed. Subsequently, an improved Mask R-CNN model (the MR3P-TS model) was built that extended the mask branch in the network design. By calculating the area of multiple connected domains of the mask, the main part of the shoot was identified. Then, the minimum circumscribed rectangle of the main part is calculated to determine the tea shoot axis, and to finally obtain the position coordinates of the picking point. The MR3P-TS model proposed in this paper achieved an mAP of 0.449 and an F2 value of 0.313 in shoot identification, and achieved a precision of 0.949 and a recall of 0.910 in the localization of the picking points. Compared with the mainstream object detection algorithms YOLOv3 and Faster R-CNN, the MR3P-TS algorithm had a good recognition effect on the overlapping shoots in an unstructured environment, which was stronger in both versatility and robustness. The proposed method can accurately detect and segment tea bud regions in real complex scenes at the pixel level, and provide precise location coordinates of suggested picking points, which should support the further development of automated tea picking machines.

Etiological and epidemiological features of acute respiratory infections in China

“…mIoU, a standard metric in deep learning for semantic classification, evaluates the agreement between predicted classifications and actual ground-truth labels (Zhang et al, 2023). For each class, the Intersection over Union (IoU) evaluates the overlap between predicted and actual bounding areas relative to their total combined area.…”

Continuous identification of the tea shoot tip and accurate positioning of picking points for a harvesting from standard plantations

“…Meanwhile, some researchers have utilized robotic arms to pick tea shoots individually, which is not an efficient method. Previously, a tea shoot can be picked in 2 s–3 s ( Yan et al., 2022 ). In this study, the picking of a tea shoot occurs in less than 1 s.…”

T‐YOLO: a lightweight and efficient detection model for nutrient buds in complex tea‐plantation environments

“…5 Yan et al proposed a novel algorithm, MR3P-TS, to localize the plucking point of tea buds; the primary goal of this model is to extract the features of each tea bud individually and determine the precise location for plucking, ultimately facilitating the advancement of automated tea-plucking machines. 6 Chen et al detected the plucking locations of tea seedlings based on computer vision techniques, built a Faster R-CNN (Faster Regionbased Convolutional Neural Network) model to detect the region between two tea leaves in an image, and then trained an FCN (Fully Convolutional Network) model to capture the plucking locations between the two tea-leaf regions. 7 Li et al applied the enhanced YOLOv5 model with the SE (Squeeze and Excitation) attention module to detect tea shoots with a mean average precision of 91.88%.…”

“…The dataset was captured at a horizontal angle to the tea buds, and their models are mainly applied to intelligent automation equipment for tea harvesting. [5][6][7][8][9][10][11][12][13] However, the detection of tea nutrient buds is still in the gap stage, and no research has been conducted to train detection models to identify tea nutrient buds (single buds) for tea garden management based on datasets that are at an overhead angle. The detection of nutrient buds in tea plays a powerful role in the smart management of tea gardens.…”