- Plant Surface Properties and Treatments
- Smart Agriculture and AI
- Electrohydrodynamics and Fluid Dynamics
- Aerosol Filtration and Electrostatic Precipitation
- Plant Water Relations and Carbon Dynamics
- Advanced Sensor and Control Systems
- Cyclone Separators and Fluid Dynamics
- Embedded Systems and FPGA Design
- Fluid Dynamics and Heat Transfer
- Remote Sensing and LiDAR Applications
- Plant Disease Management Techniques
- Water Quality Monitoring Technologies
- Plant responses to water stress
- Spectroscopy and Chemometric Analyses
- Advanced Computational Techniques and Applications
- Interactive and Immersive Displays
- Innovative Human-Technology Interaction
- Soil Mechanics and Vehicle Dynamics
- Environmental and Agricultural Sciences
- Online Learning and Analytics
- Forest ecology and management
- Artificial Intelligence in Healthcare
- Advanced Technologies in Various Fields
- Leaf Properties and Growth Measurement
- Phytoplasmas and Hemiptera pathogens
South China Agricultural University
2009-2025
Agricultural Product Processing Research Institute
2018-2025
Key Laboratory of Guangdong Province
2023-2024
Guangdong Province Environmental Monitoring Center
2019-2024
Ministry of Education of the People's Republic of China
2024
Ministry of Agriculture and Rural Affairs
2024
Ministry of Finance of the People's Republic of China
2024
Guangdong Machinery Research Institute
2018-2020
The rapid and accurate identification of citrus leaf diseases is crucial for the sustainable development industry. Because disease samples are small, unevenly distributed, difficult to collect, we redesigned generator structure FastGAN added small batch standard deviations discriminator produce an enhanced model called FastGAN2, which was used generating nutritional deficiency (zinc magnesium deficiency) images. performance existing degrades significantly when training test data exhibit...
With growing consumer concerns about food safety, developing methods for the field-based, non-destructive, and rapid detection of pesticide residues is becoming increasingly critical. This study introduces a method detecting on kumquat surfaces. Initially, spectral data from visible/near-infrared (VNIR) light bands were collected using handheld spectrometer kumquats treated with three pesticides at various gradient concentrations water. The then preprocessed analyzed machine learning...
The accurate and rapid acquisition of fruit tree canopy parameters is fundamental for achieving precision operations in orchard robotics, including spraying precise fertilization. In response to the issue inaccurate citrus segmentation complex backgrounds, this paper proposes an improved DeepLabv3+ model segmentation, facilitating parameter calculation. takes RGB-D (Red, Green, Blue, Depth) image segmented foreground as input, introducing Dilated Spatial Convolution Atrous Pyramid Pooling...
Predicting student performance is a crucial research area in educational data mining. Student grades are influenced by various factors such as past academic performance, family background, and personal achievements. However, it difficult to collect many relevant other than not ideal predict using records alone. Therefore, reducing the difficulty of collection while maintaining timeliness prediction accuracy remains pressing issue. To address this challenge, study proposes novel model for...
In this article, a variable rate liquid fertilizer applicator for deep-fertilization based on ZigBee technology was elaborated. A host computer with remote control software and STM32F103RET6 microcontroller were combined to measure the output: monitoring level collection flow information by meter, an incremental PID algorithm used dynamically adjust converter frequency reaching set accurately. Through field test, influence of parameters, such as fertilization depth, inverter, pressure...
Backgrounds UAVs for crop protection hold significant potential application in mountainous orchard areas China. However, certain issues pertaining to UAV spraying need be addressed further technological advancement, aimed at enhancing efficiency and reducing pesticide usage. These challenges include the droplet drift, limited capacity solution. Consequently, efforts are required overcome these limitations optimize technology. Methods In order balance high deposition low drift plant spraying,...
This study investigates the impact of varying side wind velocities and nozzle inclination angles on droplet penetration during plant protection spraying operations, focusing citrus trees. Experiments were conducted across four speed levels (0, 1, 2, 3 m/s) perpendicular to direction seven (0°, 8°, 15°, 23°, 30°, 38°, 45°) evaluate distribution under different parameters. A baseline condition with 0 m/s a 0° angle served as control. Utilizing Computational Fluid Dynamics (CFD) regression...
In order to study the motion law of droplet flow under airflow action long-range air-blast sprayers, a CFD-based 3D model was established for sprayer duct and its external field, discrete phase introduced simulate in airflow. The simulation data trajectory, parameters deposition were obtained by establishing monitoring sections bilateral coupling calculation field. Results showed that gravity had an obvious effect on droplets large settled faster. Some larger formed polymerization motion....
Paper is a cheap, recyclable, and clean material that often used to make practical tools. Traditional tool design either relies on simulation or physical analysis, which inaccurate time-consuming. In this paper, we propose PaperBot, an approach directly learns use in the real world using paper without human intervention. We demonstrated effectiveness efficiency of PaperBot two tasks: 1. learning fold throw airplanes for maximum travel distance 2. cut into grippers exert gripping force....
Existing deep learning models for detecting citrus diseases and nutritional deficiencies grapple with issues related to recognition accuracy, complex backgrounds, occlusions, the need lightweight architecture. In response, we developed an improved YOLOv8-GABNet model designed specifically disease deficiency detection, which effectively addresses these challenges. This incorporates several key enhancements: A ADown subsampled convolutional block is utilized reduce both model’s parameter count...
Pipeline spraying can be adopted for greatly improving efficiency in hillside orchard operations. However, residual phytosanitary product still remains the pipeline after completion of Currently, liquid is handled according to following general method: flushing with fresh water. The method easily lead pesticide waste and environment pollution. On-line mixing technology reducing environmental on-line not applied Therefore, principle jet-mixing apparatus as a reference paper designing basic...
To discuss the effects of pesticide viscosity on atomisation characteristics an agricultural nozzle, glycerite with different mass fractions was prepared to replace pesticide. First, region nozzle meshed and sized. Second, speed kinetic energy droplets at positions in were measured by Phase Doppler Anemometry. The results demonstrated that Sauter mean diameter, volume diameter arithmetic first decreased then increased gradually axial direction region. Surface waves a certain pattern formed...
Citrus orchards in Southeast Asia are commonly grown hilly areas, where the terrain is unsuitable for operation of crop protection machinery. Conventional spraying equipment used have a poor deposition effect. In this paper, new air-assisted electrostatic sprayer was designed citrus orchards. The orthogonal method conducted to determine optimal spray parameters sprayer. To evaluate performance optimized sprayer, field tests were carried out on orchard with various cultivation patterns. Based...
Target detection technology and variable-rate spraying are key technologies for achieving precise efficient pesticide application. To address the issues of low efficiency high working environment requirements in detecting tree information during variable orchards, this study has designed a control system. The system employed Kinect sensor to real-time detect canopy volume citrus trees adjusted duty cycle solenoid valves by pulse width modulation A calculation method was proposed, precision...
To address the lack of effective monitoring, evaluation, and prediction methods for water stress in citrus seedlings, we conducted 10 sets gradient experiments. Based on experimental dataset, constructed, trained, improved an MLP classification model seedling stress. In addition, developed a system based this model. The experiments demonstrated that 7 days slight can induce changes overall root wilting growth stagnation, chlorophyll content leaves decrease by up to 11.78%. Furthermore,...
We introduce UMI-on-Legs, a new framework that combines real-world and simulation data for quadruped manipulation systems. scale task-centric collection in the real world using hand-held gripper (UMI), providing cheap way to demonstrate task-relevant skills without robot. Simultaneously, we robot-centric by training whole-body controller task-tracking task setups. The interface between these two policies is end-effector trajectories frame, inferred policy passed tracking. evaluate...
This study examines the impact of canopy density, side wind speed, nozzle tilt angle, and droplet size on penetration during plant protection spraying operations. Experiments conducted in citrus orchards evaluated how speed angle influence across various densities. A Phase Doppler Analyzer (PDA) was used to assess variations under different angles speeds, yielding a multiple linear regression equation (R
This paper addresses the issue of pesticide waste and low utilization rates resulting from traditional plant protection via spraying operations, which apply equal dosages to different targets or parts same target. To tackle this problem, we designed a variable fruit tree system based on ExG-AABB (excess green axis-aligned bounding box) algorithm. We used Kinect depth camera capture information about canopy constructed spray flow model using pulse width modulation control technology. Variable...