Pod phenotypic traits are closely related to grain yield and quality. Pod phenotype detection in soybean populations in natural environments is important to soybean breeding, cultivation, and field management. For an accurate pod phenotype description, a dynamic detection method is proposed based on an improved YOLO-v5 network. First, two varieties were taken as research objects. A self-developed field soybean three-dimensional color image acquisition vehicle was used to obtain RGB and depth images of soybean pods in the field. Second, the red–green–blue (RGB) and depth images were registered using an edge feature point alignment metric to accurately distinguish complex environmental backgrounds and establish a red–green–blue-depth (RGB-D) dataset for model training. Third, an improved feature pyramid network and path aggregation network (FPN+PAN) structure and a channel attention atrous spatial pyramid pooling (CA-ASPP) module were introduced to improve the dim and small pod target detection. Finally, a soybean pod quantity compensation model was established by analyzing the influence of the number of individual plants in the soybean population on the detection precision to statistically correct the predicted pod quantity. In the experimental phase, we analyzed the impact of different datasets on the model and the performance of different models on the same dataset under the same test conditions. The test results showed that compared with network models trained on the RGB dataset, the recall and precision of models trained on the RGB-D dataset increased by approximately 32% and 25%, respectively. Compared with YOLO-v5s, the precision of the improved YOLO-v5 increased by approximately 6%, reaching 88.14% precision for pod quantity detection with 200 plants in the soybean population. After model compensation, the mean relative errors between the predicted and actual pod quantities were 2% to 3% for the two soybean varieties. Thus, the proposed method can provide rapid and massive detection for pod phenotyping in soybean populations and a theoretical basis and technical knowledge for soybean breeding, scientific cultivation, and field management.
In order to reduce the use of chemical pesticides in crop plant protection and improve the utilization efficiency of pesticides, it is necessary to study advanced application machinery and application techniques. The use of unmanned aerial vehicle (UAV) for pesticide spraying has the characteristics of less application, strong penetrability, wide applicability and flexible operation scheduling, and has gradually become one of the important development directions in the field of aviation plant protection. However, the operation process of the UAV is often affected by meteorological factors and human manipulation, resulting in poor actual operation with inaccurate spray volume and uneven application. Therefore, to improve the stability and uniformity of the application of the plant protection UAV under variable operating conditions, in this paper a real-time control method was proposed for the application flow rate, and a precision variable-rate spray system was designed based on single-chip microcomputer and micro diaphragm pump that can controls the flow rate of the pump in real time with the changes of the operating state. The response speed of the variable-rate spray system was tested. The average control response time of the system was 0.18 s, and the average stability time of the pump flow change was 0.75 s. The test results showed that the system has a quick response to the working state and the adjustment of the target flow of the pump can be quickly completed to realize the variable-rate spray function. The research results can provide a reference for the practical application of plant protection UAV variable-rate spray system.
To solve the problems of a large number of clods remaining in potatoes after mechanized harvesting in northern heavy clay soil planting areas in China and requiring much labor to separate clods from potatoes, which leads to a heavy workload, inefficiency and a low cleaning rate, an RGB-D-based Mask R-CNN dynamic potato identification model is established by using acquired RBG-D image data of untreated potatoes after mechanized harvesting, and a potato cleaning method is presented in this paper. This makes it possible to automatically separate clod impurities from potatoes. The experimental results showed that the prediction accuracy of the identification model is more than 97%. With the increase in cleaning conveyance speed, the prediction accuracy of the model and the actual cleaning precision show a downward trend. Comprehensively considering the potato cleaning efficiency and accuracy, when the speed is set to 0.4 m•s -1 , the cleaning precision reaches as high as 96.35%. This research provides a method and theoretical reference for the further study of intelligent potato cleaning systems.
In the plant protection spray operation of UAVs, the process of droplet from formation to sedimentation target is affected by airflow, easy to form uneven deposition. Accurately description of rotor downwash flow field, clarification of velocity vector distribution at different heights of the UAV rotor flow field, simulation of the flow field with high precision, which are the prerequisites for accurately analyzing the droplet deposition distribution in rotor downwash flow field. Based on CFD method, the detail of rotor flow field was numerically calculated. Taking LTH-100 single-rotor agricultural UAV as the research object, the three-dimensional solid model of UAV was established, the Reynolds average N-S equation was used as the control equation and the RNG κ-ε as the turbulence model to simulate the flow field of UAV in hover and lateral wind conditions, the wind velocity distribution at different altitudes of rotor downwash flow field was studied. The simulation results of the hover state showed that: In the flow field, the peak velocity appears in a circular distribution below the distal axis of the rotor. With the decrease of height, the peak velocity distribution area showed a tendency to expand gradually after small shrinkage; When the distance from the rotor was not more than 1.5 m, the downwash flow field presented an axisymmetric distribution based on the rotor axis, and the variation rate of velocity in the peak velocity was basically the same, turbulence in downwash flow field made the flow field more complex when the distance from rotor was larger than 2.0 m. On this basis, the optimal flight altitude of UAV is 1.5 m. Wind velocity test of the flow field was carried out on a rotor test bench, wind velocities at four altitudes of 0.5 m, 1.0 m, 1.5 m and 2.0 m were measured to verify the coincidence between the simulated and measured values. The test results showed that: the relative error between the measured and simulated values at four measurement heights were between 0.382-0.524, and the overall average relative errors was 0.430, which verified the confidence level of simulated values for measured values. When the lateral wind velocity was 3 m/s, 4 m/s and 5 m/s, the simulation results showed that: The distribution trend of airflow velocity at the same altitude in lateral-wind flow field with different wind speeds was similar; When the lateral wind speed was 5 m/s, the coupling field formed by the lateral wind and rotor airflow cannot reach the height of 2 m below the rotor. The results of this study can provide more accurate environmental conditions for theoretical analysis of droplet deposition regularity in the flow field, and also provide methodological guidance for the related research on rotor flow field of multi-rotor UAV.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.