Monitoring agricultural drought using remote sensing data is crucial for precision irrigation in modern agriculture.Utilizing unmanned aerial vehicle(UAV)remote sensing,we explored the applicability of an empirical cr...Monitoring agricultural drought using remote sensing data is crucial for precision irrigation in modern agriculture.Utilizing unmanned aerial vehicle(UAV)remote sensing,we explored the applicability of an empirical crop water stress index(CWSI)based on canopy temperature and three-dimensional drought indices(TDDI)constructed from surface temperature(T_(s)),air temperature(T_(a))and five vegetation indices(VIs)for monitoring the moisture status of dryland crops.Three machine learning algorithms(random forest regression(RFR),support vector regression,and partial least squares regression)were used to compare the performance of the drought indices for vegetation moisture content(VMC)estimation in sorghum and maize.The main results of the study were as follows:(1)Comparative analysis of the drought indices revealed that T_(s)-T_(a)-normalized difference vegetation index(TDDIn)and T_(s)-T_(a)-enhanced vegetation index(TDDIe)were more strongly correlated with VMC compared with the other indices.The indices exhibited varying sensitivities to VMC under different irrigation regimes;the strongest correlation observed was for the TDDIe index with maize under the fully irrigated treatment(r=-0.93).(2)Regarding spatial and temporal characteristics,the TDDIn,TDDIe and CWSI indices showed minimal differences Over the experimental period,with coefficients of variation were 0.25,0.18 and 0.24,respectively.All three indices were capable of effectively characterizing the moisture distribution in dryland maize and sorghum crops,but the TDDI indices more accurately monitored the spatial distribution of crop moisture after a rainfall or irrigation event.(3)For prediction of the moisture content of single crops,RFR models based on TDDIn and TDDIe estimated VMC most accurately(R^(2)>0.7),and the TDDIn-based model predicted VMC with the highest accuracy when considering multiple-crop samples,with R^(2)and RMSE of 0.62 and 14.26%,respectively.Thus,TDDI proved more effective than the CWSI in estimating crop water content.展开更多
In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convo...In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.展开更多
The mathematical model of quadcopter-unmanned aerial vehicle （UAV） is derived by using two approaches： One is the Newton-Euler approach which is formulated using classical meehanics; and other is the Euler-Lagrange...The mathematical model of quadcopter-unmanned aerial vehicle （UAV） is derived by using two approaches： One is the Newton-Euler approach which is formulated using classical meehanics; and other is the Euler-Lagrange approach which describes the model in terms of kinetic （translational and rotational） and potential energy. The proposed quadcopter＇s non-linear model is incorporated with aero-dynamical forces generated by air resistance, which helps aircraft to exhibits more realistic behavior while hovering. Based on the obtained model, the suitable control strategy is developed, under which two effective flight control systems are developed. Each control system is created by cascading the proportional-derivative （PD） and T-S fuzzy controllers that are equipped with six and twelve feedback signals individually respectively to ensure better tracking, stabilization, and response. Both pro- posed flight control designs are then implemented with the quadcopter model respectively and multitudinous simulations are conducted using MATLAB/Simulink to analyze the tracking performance of the quadcopter model at various reference inputs and trajectories.展开更多
The statistics of the number of rapeseed seedlings are very important for breeders and planters to conduct seed quality testing,field crop management and yield estimation.Calculating the number of seedlings is ineffic...The statistics of the number of rapeseed seedlings are very important for breeders and planters to conduct seed quality testing,field crop management and yield estimation.Calculating the number of seedlings is inefficient and cumbersome in the traditional method.In this study,a method was proposed for efficient detection and calculation of rapeseed seedling number based on improved you only look once version 5(YOLOv5)to identify objects and deep-sort to perform object tracking for rapeseed seedling video.Coordinated attention(CA)mechanism was added to the trunk of the improved YOLOv5s,which made the model more effective in identifying shaded,dense and small rapeseed seedlings.Also,the use of the GSConv module replaced the standard convolution at the neck,reduced model parameters and enabled it better able to be equipped for mobile devices.The accuracy and recall rate of using improved YOLOv5s on the test set by 1.9%and 3.7%compared to 96.2%and 93.7%of YOLOv5s,respectively.The experimental results showed that the average error of monitoring the number of seedlings by unmanned aerial vehicles(UAV)video of rapeseed seedlings based on improved YOLOv5s combined with depth-sort method was 4.3%.The presented approach can realize rapid statistics of the number of rapeseed seedlings in the field based on UAV remote sensing,provide a reference for variety selection and precise management of rapeseed.展开更多
The estimation of fractional vegetation cover(FVC) is important for identifying and monitoring desertification, especially in arid and semiarid regions. By using regression and pixel dichotomy models, we present the c...The estimation of fractional vegetation cover(FVC) is important for identifying and monitoring desertification, especially in arid and semiarid regions. By using regression and pixel dichotomy models, we present the comparison of Sentinel-2A(S2) multispectral instrument(MSI) and Landsat 8(L8) operational land imager(OLI) data regarding the retrieval of FVC in a semi-arid sandy area(Mu Us Sandland, China, in August 2016). A combination of unmanned aerial vehicle(UAV) high-spatial-resolution images and field plots were used to produce verified data. Based on a normalized difference vegetation index(NDVI) regression model, the results showed that, compared with that of L8, the coefficient of determination(R2) of S2 increased by 26.0%, and the root mean square error(RMSE) and the sum of absolute error(SAE) decreased by 3.0% and 11.4%, respectively. For the ratio vegetation index(RVI) regression model, compared with that of L8, the R2 of S2 increased by 26.0%, and the RMSE and SAE decreased by 8.0% and 20.0%, respectively. When the pixel dichotomy model was used, compared with that of L8, the RMSE of S2 decreased by 21.3%, and the SAE decreased by 26.9%. Overall, S2 performed better than L8 in terms of FVC inversion. Additionally, in this paper, we develop a verified scheme based on UAV data in combination with the object-based classification method. This scheme is feasible and sufficiently robust for building relationships between field data and inversion results from satellite data. Further, the synergy of multi-source sensors(especially UAVs and satellites) is a potential effective way to estimate and evaluate regional ecological environmental parameters(FVC).展开更多
Most interesting area is the growing demand of flying-IoT mergers with smart cities.However,aerial vehicles,especially unmanned aerial vehicles(UAVs),have limited capabilities for maintaining node energy efficiency.In...Most interesting area is the growing demand of flying-IoT mergers with smart cities.However,aerial vehicles,especially unmanned aerial vehicles(UAVs),have limited capabilities for maintaining node energy efficiency.In order to communicate effectively,IoT is a key element for smart cities.While improving network performance,routing protocols can be deployed in flying-IoT to improve latency,packet drop rate,packet delivery,power utilization,and average-end-to-end delay.Furthermore,in literature,proposed techniques are verymuch complex which cannot be easily implemented in realworld applications.This issue leads to the development of lightweight energyefficient routing in flying-IoT networks.This paper addresses the energy conservation problem in flying-IoT.This paper presents a novel approach for the internet of flying vehicles using DSDV routing.ISH-DSDV gives the notion of bellman-ford algorithm consisting of routing updates,information broadcasting,and stale method.DSDV shows optimal results in comparison with other contemporary routing protocols.Nomadic mobility model is utilized in the scenario of flying networks to check the performance of routing protocols.展开更多
基金supported by the National Key Research and Development Program of China(2022YFD1901500/2022YFD1901505)the Key Laboratory of Molecular Breeding for Grain and Oil Crops in Guizhou Province,China(Qiankehezhongyindi(2023)008)the Key Laboratory of Functional Agriculture of Guizhou Provincial Higher Education Institutions,China(Qianjiaoji(2023)007)。
文摘Monitoring agricultural drought using remote sensing data is crucial for precision irrigation in modern agriculture.Utilizing unmanned aerial vehicle(UAV)remote sensing,we explored the applicability of an empirical crop water stress index(CWSI)based on canopy temperature and three-dimensional drought indices(TDDI)constructed from surface temperature(T_(s)),air temperature(T_(a))and five vegetation indices(VIs)for monitoring the moisture status of dryland crops.Three machine learning algorithms(random forest regression(RFR),support vector regression,and partial least squares regression)were used to compare the performance of the drought indices for vegetation moisture content(VMC)estimation in sorghum and maize.The main results of the study were as follows:(1)Comparative analysis of the drought indices revealed that T_(s)-T_(a)-normalized difference vegetation index(TDDIn)and T_(s)-T_(a)-enhanced vegetation index(TDDIe)were more strongly correlated with VMC compared with the other indices.The indices exhibited varying sensitivities to VMC under different irrigation regimes;the strongest correlation observed was for the TDDIe index with maize under the fully irrigated treatment(r=-0.93).(2)Regarding spatial and temporal characteristics,the TDDIn,TDDIe and CWSI indices showed minimal differences Over the experimental period,with coefficients of variation were 0.25,0.18 and 0.24,respectively.All three indices were capable of effectively characterizing the moisture distribution in dryland maize and sorghum crops,but the TDDI indices more accurately monitored the spatial distribution of crop moisture after a rainfall or irrigation event.(3)For prediction of the moisture content of single crops,RFR models based on TDDIn and TDDIe estimated VMC most accurately(R^(2)>0.7),and the TDDIn-based model predicted VMC with the highest accuracy when considering multiple-crop samples,with R^(2)and RMSE of 0.62 and 14.26%,respectively.Thus,TDDI proved more effective than the CWSI in estimating crop water content.
基金National Defense Pre-research Fund Project(No.KMGY318002531)。
文摘In order to solve the problem of small objects detection in unmanned aerial vehicle(UAV)aerial images with complex background,a general detection method for multi-scale small objects based on Faster region-based convolutional neural network(Faster R-CNN)is proposed.The bird’s nest on the high-voltage tower is taken as the research object.Firstly,we use the improved convolutional neural network ResNet101 to extract object features,and then use multi-scale sliding windows to obtain the object region proposals on the convolution feature maps with different resolutions.Finally,a deconvolution operation is added to further enhance the selected feature map with higher resolution,and then it taken as a feature mapping layer of the region proposals passing to the object detection sub-network.The detection results of the bird’s nest in UAV aerial images show that the proposed method can precisely detect small objects in aerial images.
基金supported by the National Natural Science Foundation of China(Nos.61673209,61741313,61304223)the Aeronautical Science Foundation(Nos.2016ZA52009)+1 种基金the Jiangsu Six Peak of Talents Program(No.KTHY-027)the Fundamental Research Funds for the Central Universities(Nos.NJ20160026,NS2017015)
文摘The mathematical model of quadcopter-unmanned aerial vehicle （UAV） is derived by using two approaches： One is the Newton-Euler approach which is formulated using classical meehanics; and other is the Euler-Lagrange approach which describes the model in terms of kinetic （translational and rotational） and potential energy. The proposed quadcopter＇s non-linear model is incorporated with aero-dynamical forces generated by air resistance, which helps aircraft to exhibits more realistic behavior while hovering. Based on the obtained model, the suitable control strategy is developed, under which two effective flight control systems are developed. Each control system is created by cascading the proportional-derivative （PD） and T-S fuzzy controllers that are equipped with six and twelve feedback signals individually respectively to ensure better tracking, stabilization, and response. Both pro- posed flight control designs are then implemented with the quadcopter model respectively and multitudinous simulations are conducted using MATLAB/Simulink to analyze the tracking performance of the quadcopter model at various reference inputs and trajectories.
文摘The statistics of the number of rapeseed seedlings are very important for breeders and planters to conduct seed quality testing,field crop management and yield estimation.Calculating the number of seedlings is inefficient and cumbersome in the traditional method.In this study,a method was proposed for efficient detection and calculation of rapeseed seedling number based on improved you only look once version 5(YOLOv5)to identify objects and deep-sort to perform object tracking for rapeseed seedling video.Coordinated attention(CA)mechanism was added to the trunk of the improved YOLOv5s,which made the model more effective in identifying shaded,dense and small rapeseed seedlings.Also,the use of the GSConv module replaced the standard convolution at the neck,reduced model parameters and enabled it better able to be equipped for mobile devices.The accuracy and recall rate of using improved YOLOv5s on the test set by 1.9%and 3.7%compared to 96.2%and 93.7%of YOLOv5s,respectively.The experimental results showed that the average error of monitoring the number of seedlings by unmanned aerial vehicles(UAV)video of rapeseed seedlings based on improved YOLOv5s combined with depth-sort method was 4.3%.The presented approach can realize rapid statistics of the number of rapeseed seedlings in the field based on UAV remote sensing,provide a reference for variety selection and precise management of rapeseed.
基金National Natural Science Foundation of China(No.41301451,41541008)Fundamental Research Funds for the Central Universities(No.2452018144)
文摘The estimation of fractional vegetation cover(FVC) is important for identifying and monitoring desertification, especially in arid and semiarid regions. By using regression and pixel dichotomy models, we present the comparison of Sentinel-2A(S2) multispectral instrument(MSI) and Landsat 8(L8) operational land imager(OLI) data regarding the retrieval of FVC in a semi-arid sandy area(Mu Us Sandland, China, in August 2016). A combination of unmanned aerial vehicle(UAV) high-spatial-resolution images and field plots were used to produce verified data. Based on a normalized difference vegetation index(NDVI) regression model, the results showed that, compared with that of L8, the coefficient of determination(R2) of S2 increased by 26.0%, and the root mean square error(RMSE) and the sum of absolute error(SAE) decreased by 3.0% and 11.4%, respectively. For the ratio vegetation index(RVI) regression model, compared with that of L8, the R2 of S2 increased by 26.0%, and the RMSE and SAE decreased by 8.0% and 20.0%, respectively. When the pixel dichotomy model was used, compared with that of L8, the RMSE of S2 decreased by 21.3%, and the SAE decreased by 26.9%. Overall, S2 performed better than L8 in terms of FVC inversion. Additionally, in this paper, we develop a verified scheme based on UAV data in combination with the object-based classification method. This scheme is feasible and sufficiently robust for building relationships between field data and inversion results from satellite data. Further, the synergy of multi-source sensors(especially UAVs and satellites) is a potential effective way to estimate and evaluate regional ecological environmental parameters(FVC).
基金This work was supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(Grant No.NRF-2020R1I1A3074141)the Brain Research Program through the NRF funded by the Ministry of Science,ICT and Future Planning(Grant No.NRF-2019M3C7A1020406),and“Regional Innovation Strategy(RIS)”through the NRF funded by the Ministry of Education.
文摘Most interesting area is the growing demand of flying-IoT mergers with smart cities.However,aerial vehicles,especially unmanned aerial vehicles(UAVs),have limited capabilities for maintaining node energy efficiency.In order to communicate effectively,IoT is a key element for smart cities.While improving network performance,routing protocols can be deployed in flying-IoT to improve latency,packet drop rate,packet delivery,power utilization,and average-end-to-end delay.Furthermore,in literature,proposed techniques are verymuch complex which cannot be easily implemented in realworld applications.This issue leads to the development of lightweight energyefficient routing in flying-IoT networks.This paper addresses the energy conservation problem in flying-IoT.This paper presents a novel approach for the internet of flying vehicles using DSDV routing.ISH-DSDV gives the notion of bellman-ford algorithm consisting of routing updates,information broadcasting,and stale method.DSDV shows optimal results in comparison with other contemporary routing protocols.Nomadic mobility model is utilized in the scenario of flying networks to check the performance of routing protocols.
