TYTongchuan Yi

Tongchuan Yi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tongchuan Yi has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Algorithm for Detecting Trees Affected by Pine Wilt Disease in Complex Scenes Based on CNN-Transformer

    by Qiangjia Wu, Meixiang Chen, Hao Shi, Tongchuan Yi, Gang Xu, Weijia Wang, Chunjiang Zhao, Ruirui Zhang

    Pine wilt disease, a highly destructive forest disease with rapid spread, currently has no effective treatments. Infected pine trees usually die within a few months, causing severe damage to forest ecosystems. A rapid and accurate detection algorithm for diseased trees is crucial for curbing the spread of this disease. In recent years, the combination of drone remote sensing and deep learning has become the main methods of detecting and locating diseased trees. Previous studies have shown that increasing network depth cannot improve accuracy in this task. Therefore, a lightweight semantic segmentation model based on a CNN-Transformer hybrid architecture was designed in this study, named EVitNet. This segmentation model reduces network parameters while improving recognition accuracy, outperforming mainstream models. The segmentation IoU for discolored trees reached 0.713, with only 1.195 M parameters. Furthermore, considering the diverse and complex terrain where diseased trees are distributed, a fine-tuning model approach was adopted. After a small amount of training, the IoU on new samples increased from 0.321 to 0.735, greatly enhancing the practicality of the algorithm. The model’s segmentation speed in the task of discolored trees identification meets the requirements of real-time performance, and its accuracy exceeds that of mainstream semantic segmentation models. In the future, it is expected to be deployed on drones for real-time recognition, accelerating the entire process of discovering and locating infected trees.


  • Open Access

    Adaptive Tracking and Cutting Control System for Tea Canopy: Design and Experimental Evaluation

    by Danzhu Zhang, Ruirui Zhang, Liping Chen, Linhuan Zhang, Tongchuan Yi, Quan Feng

    Combined with the characteristic that tea is generally planted in hilly and mountainous areas and considering the existing problems of harvesting with current tea pickers, such as the inability to adjust their posture in real time, poor adaptability to the terrain, insufficient stability, and large differences in the harvesting lengths of tea. To address these issues, an adaptive canopy-following cutting control system has been designed for self-propelled tea harvesters in this study. Specifically, we developed a height-following control algorithm for tea canopy tracking and an adaptive header tilt angle control algorithm based on incremental PID control. Field experiments demonstrated that when the vehicle speed was 0.4 m/s, the height tracking errors for three harvesting lengths (20 mm, 30 mm, and 40 mm) remained within ±5 mm, with correlation coefficients exceeding 0.99. When the height differences between the two sides of the tea ridge were 10 cm, 15 cm, and 20 cm, the maximum uphill roll angles were measured at 1.7°, 2.3°, and 3.0°, respectively, and the time taken for the harvester to return to a horizontal position was around 1.7 s. During downhill movement, the maximum roll angles of the harvester were 1.3°, 2.0°, and 2.6°, respectively, and the time for the harvester to return to a horizontal position was around 2.1 s, demonstrating significant correction effectiveness. Quality assessments revealed that at the 30 mm harvesting length specification, the integrity rate of tea harvesting exceeded 79%, while the missed harvesting rate was below 1.1%. This system effectively enhances harvesting stability and quality, offering novel insights for efficient, high-volume tea production.


  • Open Access

    Tea Harvest Robot Navigation Path Generation Algorithm Based on Semantic Segmentation Using a Visual Sensor

    by Houqi Tao, Ruirui Zhang, Linhuan Zhang, Danzhu Zhang, Tongchuan Yi, Mingqi Wu

    During the process of autonomous tea harvesting, it is essential for the tea-harvesting robots to navigate along the tea canopy while obtaining real-time and precise information about these tea canopies. Considering that most tea gardens are located in hilly and mountainous areas, GNSS signals often encounter disturbances, and laser sensors provide insufficient information, which fails to meet the navigation requirements of tea-harvesting robots. This study develops a vision-based semantic segmentation method for the identification of tea canopies and the generation of navigation paths. The proposed CDSC-Deeplabv3+ model integrates a Convnext backbone network with the DenseASP_SP module for feature fusion and a CFF module for enhanced semantic segmentation. The experimental results demonstrate that our proposed CDSC-Deeplabv3+ model achieves mAP, mIoU, F1-score, and FPS metrics of 96.99%, 94.71%, 98.66%, and 5.0, respectively; both the accuracy and speed performance indicators meet the practical requirements outlined in this study. Among the three compared methods for fitting the navigation central line, RANSAC shows superior performance, with minimum average angle deviations of 2.02°, 0.36°, and 0.46° at camera tilt angles of 50°, 45°, and 40°, respectively, validating the effectiveness of our approach in extracting stable tea canopy information and generating navigation paths.


  • Open Access

    Predicting spray drift reduction classification of flat-fan nozzles based on droplet size spectrum

    by Li Longlong, Zhang Ruirui, Tang Qing, Yan Wenlong, Ding Chenchen, Xu Gang, Yi Tongchuan

    Predicting spray drift reduction classification of flat-fan nozzles based on droplet size spectrum


  • Open Access

    Optimization Design and Experimental Study of Solid Particle Spreader for Unmanned Aerial Vehicle

    by Linhuan Zhang, Ruirui Zhang, Tongchuan Yi, Danzhu Zhang, Chenchen Ding, Mingqi Wu, Ryozo Noguchi

    This study designed and investigated a solid particle spreader, as well as parameter optimization and experimental for a groove wheel, to mitigate the problems of low uniformity and poor control accuracy of solid particulate material UAV spreading. The discrete element method was used to simulate and analyze the displacement range and stability of each grooved wheel at low speeds. Furthermore, orthogonal regression and response surface analyses were used to analyze the influence of each factor on the stability of the discharge rate and pulsation amplitude. The results showed that the helix angle, sharpness, and length of the groove significantly influenced the application performance, whereas the number of grooves had no significant influence. The groove shape was eccentric, the helix angle was 50°, the length was 35 mm, and the number of grooves was 7. Additionally, the bench test results showed that in the range of 10–60 rpm, the relative deviation of the discharging rate between the simulation and bench test is from 0.47% to 10.39%, and the average relative deviation is 3.93%. Between the groove wheel rotation speed and discharge rate, R2 was 0.991, and the adjustable range of the discharge amount was between 3.68 and 23.43 g/s. The minimum and maximum variation coefficients of the average discharge rate among individual applicators were 1.01% and 2.79%, respectively, whereas the standard deviations were 0.09 and 0.46 g/s, respectively. In conclusion, the discharge stability and adjustable range of the spreader using the optimized groove wheel satisfied the requirements for solid particulate material discharge.


  • Open Access

    Research on Individual Tree Canopy Segmentation of Camellia oleifera Based on a UAV-LiDAR System

    by Liwan Wang, Ruirui Zhang, Linhuan Zhang, Tongchuan Yi, Danzhu Zhang, Aobin Zhu

    In consideration of the limited accuracy of individual tree canopy segmentation algorithms due to the diverse canopy structure and complex environments in mountainous and hilly areas, this study optimized the segmentation parameters of three algorithms for individual tree canopy segmentation of Camellia oleifera in such environments by analyzing their respective parameters. Utilizing an Unmanned Aerial Vehicle-Light Detecting and Ranging (UAV-LiDAR) system, we obtained Canopy Height Models (CHM) of Camellia oleifera canopies based on Digital Elevation Models (DEM) and Digital Surface Models (DSM). Subsequently, we investigated the effects of CHM segmentation, point cloud clustering segmentation, and layer stacking fitting segmentation on Camellia oleifera canopies across different research areas. Additionally, combining ground survey data from forest lands with visual interpretation of UAV orthophoto images, we evaluated the performance of these three segmentation algorithms in terms of the F-score as an evaluation indicator for individual tree canopy segmentation accuracy. Combined with the Cloth Simulation Filter (CSF) filtering algorithm after removing the ground point cloud, our findings indicate that among different camellia densities and terrain environments, the point cloud clustering segmentation algorithm achieved the highest segmentation accuracy at 93%, followed by CHM segmentation at 88% and the layer stacking fitting segmentation method at 84%. By analyzing the data from UAV-LiDAR technology involving various land and Camellia oleifera planting types, we verified the applicability of these three segmentation algorithms for extracting camellia canopies. In conclusion, this study holds significant importance for accurately delineating camellia canopies within mountainous hilly environments while providing valuable insights for further research in related fields.


  • Open Access

    Development of a Low-Power Automatic Monitoring System for Spodoptera frugiperda (J. E. Smith)

    by Meixiang Chen, Liping Chen, Tongchuan Yi, Ruirui Zhang, Lang Xia, Cheng Qu, Gang Xu, Weijia Wang, Chenchen Ding, Qing Tang, et al.

    Traditional traps for Spodoptera frugiperda (J. E. Smith) monitoring require manual counting, which is time-consuming and laborious. Automatic monitoring devices based on machine vision for pests captured by sex pheromone lures have the problems of large size, high power consumption, and high cost. In this study, we developed a micro- and low-power pest monitoring device based on machine vision, in which the pest image was acquired timely and processed using the MATLAB algorithm. The minimum and maximum power consumption of an image was 6.68 mWh and 78.93 mWh, respectively. The minimum and maximum days of monitoring device captured image at different resolutions were 7 and 1486, respectively. The optimal image resolutions and capture periods could be determined according to field application requirements, and a micro-solar panel for battery charging was added to further extend the field life of the device. The results of the automatic counting showed that the counting accuracy of S. frugiperda was 94.10%. The automatic monitoring device had the advantages of low-power consumption and high recognition accuracy, and real-time information on S. frugiperda could be obtained. It is suitable for large-scale and long-term pest monitoring and provides an important reference for pest control.


  • Open Access

    Algorithm for Extracting the 3D Pose Information of Hyphantria cunea (Drury) with Monocular Vision

    by Meixiang Chen, Ruirui Zhang, Meng Han, Tongchuan Yi, Gang Xu, Lili Ren, Liping Chen

    Currently, the robustness of pest recognition algorithms based on sample augmentation with two-dimensional images is negatively affected by moth pests with different postures. Obtaining three-dimensional (3D) posture information of pests can provide information for 3D model deformation and generate training samples for deep learning models. In this study, an algorithm of the 3D posture information extraction method for Hyphantria cunea (Drury) based on monocular vision is proposed. Four images of every collected sample of H. cunea were taken at 90° intervals. The 3D pose information of the wings was extracted using boundary tracking, edge fitting, precise positioning and matching, and calculation. The 3D posture information of the torso was obtained by edge extraction and curve fitting. Finally, the 3D posture information of the wings and abdomen obtained by this method was compared with that obtained by Metrology-grade 3D scanner measurement. The results showed that the relative error of the wing angle was between 0.32% and 3.03%, the root mean square error was 1.9363, and the average relative error of the torso was 2.77%. The 3D posture information of H. cunea can provide important data support for sample augmentation and species identification of moth pests.

  • Open Access

    Modeling and Experimental Validation of the Atomization Efficiency of a Rotary Atomizer for Aerial Spraying

    by Gen Li, Liping Chen, Longlong Li, Tongchuan Yi, Chenchen Ding, Juan Wang, Chunjiang Zhao, Ruirui Zhang

    Rotary atomizers are mainly used in agricultural manned aircrafts. Atomization characteristics at high speeds have been studied, but methods to measure the atomization efficiency have not been elucidated. The atomization efficiency of rotary atomizers under high-speed airflow was investigated using an IEA-I high-speed wind tunnel experimental installation, AU5000 rotary atomizer, and a laser diffraction particle size analyzer. Accordingly, a model equation for atomization efficiency measurements was innovatively obtained. When the flow rate, fan blade angle of the atomizer, and wind speed were used as variables, the experimental results showed that the atomization efficiency mainly depended on the fan blade angle. When the fan blade angle was 35°, the atomization efficiency was optimal, regardless of wind speed. In contrast, when the fan blade angle of the atomizer was 65°, it exhibited the worst atomization efficiency, regardless of the wind speed. The experimental data from this study can provide guidance for aerial application in fixed-wing manned aircraft, such as the flow rate, and operating speed.


  • Open Access

    Spray drift characteristics of pulse-width modulation sprays in wind tunnel

    by Longlong Li, Liping Chen, Ruirui Zhang, Qing Tang, Tongchuan Yi, Boqin Liu, Wei Deng

    Pulse-width modulation (PWM) sprays can improve flow accuracy by adjusting duty cycle and frequency signal which accurately controls the relative proportion of opening time of solenoid valve. The objective of this research was to determine the impacts of PWM duty cycle and frequency on spray drift characteristic. Spray tests were conducted in a wind tunnel with a PWM variable-rate spraying system. The airborne drift and sediment drift were determined with tracer method, and the drift potential reduction (DPR) compared with reference condition of 100% duty cycle at vertical profile and horizontal planes were calculated, respectively. The results show that, at a given frequency, droplet size decreases with the increase of duty cycle, the main reason is that the liquid does not reach full pattern development at lower duty cycle. Duty cycle has a greater impact than the frequency on spray drift, the influence weights of duty cycle on airborne drift and sediment drift were 88.32% and 77.89%, respectively. At a lower PWM frequency, in addition to the droplet size, the spray drift may be affected by the pulsed spray pattern. From the perspective of reducing spray drift, it is recommended that the PWM duty cycle should be set in the range of 20%-70% to reduce the potential drift in PWM sprays. This research provides a pesticide drift reduction scheme for variable spraying technology, which can serve as a theoretical basis for PWM parameter selection. Keywords: nozzle, spray drift, pulse-width modulation, drift potential reduction, droplets spectral DOI: 10.25165/j.ijabe.20221504.7440 Citation: Li L L, Chen L P, Zhang R R, Tang Q, Yi T C, Liu B Q, et al. Spray drift characteristics of pulse-width modulation sprays in wind tunnel. Int J Agric & Biol Eng, 2022; 15(4): 7–15.