Bagging is a crucial step in the full cycle management of pear cultivation, with increasing labor costs annually, driving research on intelligent bagging equipment. We describe an intelligent bagging end-effector for pears, which employs the Yolov8 algorithm for fruitlets detection and the Semi-Global Block Matching (SGBM) algorithm to acquire three-dimensional spatial information of the targets. To address the computational limitations of embedded devices in agricultural intelligent equipment, we improved the YOLOv8 model by replacing its neck component with the Asymptotic Feature Pyramid Network (AFPN) and incorporating Context Guided (CG) blocks into the C2f module. These improvements significantly reduce the model’s parameters and size while enhancing detection accuracy. To provide accurate three-dimensional information to the end-effector, we use the SGBM algorithm to obtain depth information of the targets. We constrained the matching process based on the model’s detected candidate bounding boxes and binocular prior knowledge, which improved the matching accuracy of the model while reducing the computational load. Finally, we deployed the model and matching algorithm on a Jetson Nano, which serves as the controller for the bagging end-effector based on the vacuum negative pressure principle. Experimental results show that the improved model achieves a precision of 96%, an increase of 1.4% over YOLOv8, with the size reduced from 6.2M to 5.0M. The depth information accuracy obtained by the algorithm is within 3cm. The improved model, combined with SGBM, runs at 11.5 fps on the Jetson Nano embedded device, meeting real-time performance requirements.

The issue of pesticide and chemical residue in food has drawn increasing public attention, making effective control of plant pests and diseases a critical research focus in agriculture. Monitoring of pest populations is a key factor constraining the precision of pest management strategies. Low-cost and high-efficiency monitoring devices are highly desirable. To address these challenges, we focus on Cacopsylla chinensis and design a portable, AI-based detection device, along with an integrated online monitoring and forecasting system. First, to enhance the model’s capability for detecting small targets, we developed a backbone network based on the RepVit block and its variants. Additionally, we introduced a Dynamic Position Encoder module to improve feature position encoding. To further enhance detection performance, we adopt a Context Guide Fusion Module, which enables context-driven information guidance and adaptive feature adjustment. Second, a framework facilitates the development of an online monitoring system centered on Cacopsylla chinensis detection. The system incorporates a hybrid neural network model to establish the relationship between multiple environmental parameters and the Cacopsylla chinensis population, enabling trend prediction. We conduct feasibility validation experiments by comparing detection results with a manual survey. The experimental results show that the detection model achieves an accuracy of 87.4% for both test samples and edge devices. Furthermore, the population dynamics model yields a mean absolute error of 1.94% for the test dataset. These performance indicators fully meet the requirements of practical agricultural applications.

The intelligent harvesting technology for jujube leaf branches presents a novel avenue for enhancing both the quantity and quality of jujube leaf tea, whereas the precise detection technology for jujube leaf branches emerges as a pivotal factor constraining its development. The precise identification and localization of jujube leaf branches using real-time object detection technology are crucial steps toward achieving intelligent harvesting. When integrated into real-world scenarios, issues such as the background noise introduced by tags, occlusions, and variations in jujube leaf morphology constrain the accuracy of detection and the precision of localization. To address these issues, we describe a jujube leaf branch object detection network based on YOLOv7. First, the Polarized Self-Attention module is embedded into the convolutional layer, and the Gather-Excite module is embedded into the concat layer to incorporate spatial information, thus achieving the suppression of irrelevant information such as background noise. Second, we incorporate implicit knowledge into the Efficient Decoupled Head and replace the original detection head, enhancing the network’s capability to extract deep features. Third, to address the issue of imbalanced jujube leaf samples, we employ Focal-EIoU as the bounding box loss function to expedite the regression prediction and enhance the localization accuracy of the model’s bounding boxes. Experiments show that the precision of our model is 85%, which is increased by 3.5% compared to that of YOLOv7-tiny. The mAP@0.5 value is 83.7%. Our model’s recognition rate, recall and mean average precision are superior to those of other models. Our method could provide technical support for yield estimation in the intelligent management of jujube orchards.