UAV-based object detection is rapidly expanding in both civilian and military applications,including security surveillance,disaster assessment,and border patrol.However,challenges such as small objects,occlusions,comp...UAV-based object detection is rapidly expanding in both civilian and military applications,including security surveillance,disaster assessment,and border patrol.However,challenges such as small objects,occlusions,complex backgrounds,and variable lighting persist due to the unique perspective of UAV imagery.To address these issues,this paper introduces DAFPN-YOLO,an innovative model based on YOLOv8s(You Only Look Once version 8s).Themodel strikes a balance between detection accuracy and speed while reducing parameters,making itwell-suited for multi-object detection tasks from drone perspectives.A key feature of DAFPN-YOLO is the enhanced Drone-AFPN(Adaptive Feature Pyramid Network),which adaptively fuses multi-scale features to optimize feature extraction and enhance spatial and small-object information.To leverage Drone-AFPN’smulti-scale capabilities fully,a dedicated 160×160 small-object detection head was added,significantly boosting detection accuracy for small targets.In the backbone,the C2f_Dual(Cross Stage Partial with Cross-Stage Feature Fusion Dual)module and SPPELAN(Spatial Pyramid Pooling with Enhanced LocalAttentionNetwork)modulewere integrated.These components improve feature extraction and information aggregationwhile reducing parameters and computational complexity,enhancing inference efficiency.Additionally,Shape-IoU(Shape Intersection over Union)is used as the loss function for bounding box regression,enabling more precise shape-based object matching.Experimental results on the VisDrone 2019 dataset demonstrate the effectiveness ofDAFPN-YOLO.Compared to YOLOv8s,the proposedmodel achieves a 5.4 percentage point increase inmAP@0.5,a 3.8 percentage point improvement in mAP@0.5:0.95,and a 17.2%reduction in parameter count.These results highlight DAFPN-YOLO’s advantages in UAV-based object detection,offering valuable insights for applying deep learning to UAV-specific multi-object detection tasks.展开更多
Stay-green(SG)in wheat is a beneficial trait that increases yield and stress tolerance.However,conventional phenotyping techniques limited the understanding of its genetic basis.Spectral indices(SIs)as non-destructive...Stay-green(SG)in wheat is a beneficial trait that increases yield and stress tolerance.However,conventional phenotyping techniques limited the understanding of its genetic basis.Spectral indices(SIs)as non-destructive tools to evaluate crop temporal senescence provide an alternative strategy.Here,we applied Sls to monitor the senescence dynamics of 565 diverse wheat accessions from anthesis to maturation stages over 2 field seasons.Four Sis(normalized difference vegetation index,green normalized difference vegetation index,normalized difference red edge index,and optimized soil-adjusted vegetation index)were normalized to develop relative stay-green scores(RSGS)as the SG indicators.An RSGS-based genome-wide association study identified 47 high-confidence quantitative trait loci(QTL)harboring 3,079 single-nucleotide polymorphisms associated with SG and 1,085 corresponding candidate genes.Among them,15 QTL overlapped or were adjacent to known SG-related QTL/genes,while the remaining QTL were novel.Notably,a set of favorable haplotypes of SG-related candidate genes such as TraesCS2A03G1081100,TracesCS6B03G0356400,and TracesCS2B03G1299500 are increasing following the Green Revolution,further validating the feasibility of the pipeline.This study provided a valuable reference for further quantitative SG and genetic research in diverse wheat panels.展开更多
The disease of banana Fusarium wilt currently threatens banana production areas all over the world.Rapid and large-area monitoring of Fusarium wilt disease is very important for the disease treatment and crop planting...The disease of banana Fusarium wilt currently threatens banana production areas all over the world.Rapid and large-area monitoring of Fusarium wilt disease is very important for the disease treatment and crop planting adjustments.The objective of this study was to evaluate the performance of supervised classification algorithms such as support vector machine(SVM),random forest(RF),and artificial neural network(ANN)algorithms to identify locations that were infested or not infested with Fusarium wilt.An unmanned aerial vehicle(UAV)equipped with a five-band multi-spectral sensor(blue,green,red,red-edge and near-infrared bands)was used to capture the multi-spectral imagery.A total of 139 ground sample-sites were surveyed to assess the occurrence of banana Fusarium wilt.The results showed that the SVM,RF,and ANN algorithms exhibited good performance for identifying and mapping banana Fusarium wilt disease in UAV-based multi-spectral imagery.The overall accuracies of the SVM,RF,and ANN were 91.4%,90.0%,and 91.1%,respectively for the pixel-based approach.The RF algorithm required significantly less training time than the SVM and ANN algorithms.The maps generated by the SVM,RF,and ANN algorithms showed the areas of occurrence of Fusarium wilt disease were in the range of 5.21-5.75 hm2,accounting for 36.3%-40.1%of the total planting area of bananas in the study area.The results also showed that the inclusion of the red-edge band resulted in an increase in the overall accuracy of 2.9%-3.0%.A simulation of the resolutions of satellite-based imagery(i.e.,0.5 m,1 m,2 m,and 5 m resolutions)showed that imagery with a spatial resolution higher than 2 m resulted in good identification accuracy of Fusarium wilt.The results of this study demonstrate that the RF classifier is well suited for the identification and mapping of banana Fusarium wilt disease from UAV-based remote sensing imagery.The results provide guidance for disease treatment and crop planting adjustments.展开更多
Accurate and timely estimation of above-ground biomass is crucial for understanding crop growth dynamics,optimizing agricultural input management,and assessing productivity in sustainable farming practices.However,con...Accurate and timely estimation of above-ground biomass is crucial for understanding crop growth dynamics,optimizing agricultural input management,and assessing productivity in sustainable farming practices.However,conventional biomass assessments are destructive and resource-intensive.In contrast,remote sensing techniques,particularly those utilizing low-altitude unmanned aerial vehicles,provide a non-destructive approach to collect imagery data on plant canopy features,including spectral reflectance and structural details at any stage of the crop life cycle.This study explores the potential visible-light-derived vegetative indices to improve biomass prediction during the flowering period of buckwheat(Fagopyrum tataricum).Red,green,and blue(RGB)images of buckwheat were acquired during peak flowering,using a DJI P4 multispectral Drone.From the analysis of those images,four vegetative indices were calculated.Aboveground fresh biomass was harvested and measured on 14 September 2024.The results showed negative correlations between the green-band based excess green(ExG),excess green minus excess red(ExGR),and green leaf index(GLI)indices and the fresh above-ground biomass of buckwheat,while the red band-based excess red(ExR)index showed an insignificant positive correlation at p<0.10.An investigation into greenband-based vegetation indices(VIs)for estimating fresh biomass revealed significant negative correlations during the experimental period.This unexpected inverse relationship is attributed to spectral interference from abundant white flowers during the flowering stage,where the high reflectance of white petals masked the green vegetation signal.Consequently,these green-band VIs demonstrated limited predictive power for biomass under such conditions,indicating that their utility is compromised when floral reflectance is dominant.Therefore,we suggest that further experiments are required to validate this relationship and improve the estimation of fresh above-ground biomass in white-flowered buckwheat plants.展开更多
The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-gener...The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.展开更多
Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite commun...Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite communication resource in multi-UAV networks, this paper joints consideration of task offloading and wireless channel allocation on a collaborative multi-UAV computing network, where a high altitude platform station (HAPS)is adopted as the relay device for communication between UAV clusters consisting of UAV cluster heads (ch-UAVs) and mission UAVs (m-UAVs). We propose an algorithm, jointing task offloading and wireless channel allocation to maximize the average service success rate (ASSR)of a period time. In particular,the simulated annealing(SA)algorithm with random perturbations is used for optimal channel allocation,aiming to reduce interference and minimize transmission delay.A multi-agent deep deterministic policy gradient (MADDPG) is proposed to get the best task offloading strategy. Simulation results demonstrate the effectiveness of the SA algorithm in channel allocation. Meanwhile,when jointly considering computation and channel resources,the proposed scheme effectively enhances the ASSR in comparison to other benchmark algorithms.展开更多
Unmanned aerial vehicle(UAV)technology,artificial intelligence,and the relevant hardware can be used for monitoring wild animals.However,existing methods have several limitations.Therefore,this study explored the monit...Unmanned aerial vehicle(UAV)technology,artificial intelligence,and the relevant hardware can be used for monitoring wild animals.However,existing methods have several limitations.Therefore,this study explored the monitoring and protection of Amur tigers and their main prey species using images from UAVs by optimizing the algorithm models with respect to accuracy,model size,recognition speed,and elimination of environmental inter-ference.Thermal imaging data were collected from 2000 pictures with a thermal imaging lens on a DJI M300RTK UAV at the Hanma National Nature Reserve in the Greater Khingan Mountains in Inner Mongolia,Wangqing National Nature Reserve in Jilin Province,and Siberian Tiger Park in Heilongjiang Province.The YOLO V5s al-gorithm was applied to recognize the animals in the pictures.The accuracy rate was 94.1%,and the size of the model weight(total weight of each model layer trained with the training set)was 14.8 MB.The authors improved the structures and parameters of the YOLO V5s algorithm.As a result,the recognition accuracy rate became 96%,and the model weight was 9.3 MB.The accuracy rate increased by 1.9%,the model weight decreased by 37.2%from 14.8 MB to 9.3 MB,and the recognition time of a single picture was shortened by 34.4%from 0.032 to 0.021 s.This not only increases the recognition accuracy but also effectively lowers the hardware requirements that the algorithm relies on,which provides a lightweight fast recognition method for UAV-based edge computing and online investigation of wild animals.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62101275 and 62101274).
文摘UAV-based object detection is rapidly expanding in both civilian and military applications,including security surveillance,disaster assessment,and border patrol.However,challenges such as small objects,occlusions,complex backgrounds,and variable lighting persist due to the unique perspective of UAV imagery.To address these issues,this paper introduces DAFPN-YOLO,an innovative model based on YOLOv8s(You Only Look Once version 8s).Themodel strikes a balance between detection accuracy and speed while reducing parameters,making itwell-suited for multi-object detection tasks from drone perspectives.A key feature of DAFPN-YOLO is the enhanced Drone-AFPN(Adaptive Feature Pyramid Network),which adaptively fuses multi-scale features to optimize feature extraction and enhance spatial and small-object information.To leverage Drone-AFPN’smulti-scale capabilities fully,a dedicated 160×160 small-object detection head was added,significantly boosting detection accuracy for small targets.In the backbone,the C2f_Dual(Cross Stage Partial with Cross-Stage Feature Fusion Dual)module and SPPELAN(Spatial Pyramid Pooling with Enhanced LocalAttentionNetwork)modulewere integrated.These components improve feature extraction and information aggregationwhile reducing parameters and computational complexity,enhancing inference efficiency.Additionally,Shape-IoU(Shape Intersection over Union)is used as the loss function for bounding box regression,enabling more precise shape-based object matching.Experimental results on the VisDrone 2019 dataset demonstrate the effectiveness ofDAFPN-YOLO.Compared to YOLOv8s,the proposedmodel achieves a 5.4 percentage point increase inmAP@0.5,a 3.8 percentage point improvement in mAP@0.5:0.95,and a 17.2%reduction in parameter count.These results highlight DAFPN-YOLO’s advantages in UAV-based object detection,offering valuable insights for applying deep learning to UAV-specific multi-object detection tasks.
基金supported by the National Key R&D Program of China(no.2022YFE0116200)the Key R&D Program of Qinghai Province(2022-NK-125)the Key R&D Program of Yangling Seed Industry Innovation Center(grant no.Ylzy-xm-01).
文摘Stay-green(SG)in wheat is a beneficial trait that increases yield and stress tolerance.However,conventional phenotyping techniques limited the understanding of its genetic basis.Spectral indices(SIs)as non-destructive tools to evaluate crop temporal senescence provide an alternative strategy.Here,we applied Sls to monitor the senescence dynamics of 565 diverse wheat accessions from anthesis to maturation stages over 2 field seasons.Four Sis(normalized difference vegetation index,green normalized difference vegetation index,normalized difference red edge index,and optimized soil-adjusted vegetation index)were normalized to develop relative stay-green scores(RSGS)as the SG indicators.An RSGS-based genome-wide association study identified 47 high-confidence quantitative trait loci(QTL)harboring 3,079 single-nucleotide polymorphisms associated with SG and 1,085 corresponding candidate genes.Among them,15 QTL overlapped or were adjacent to known SG-related QTL/genes,while the remaining QTL were novel.Notably,a set of favorable haplotypes of SG-related candidate genes such as TraesCS2A03G1081100,TracesCS6B03G0356400,and TracesCS2B03G1299500 are increasing following the Green Revolution,further validating the feasibility of the pipeline.This study provided a valuable reference for further quantitative SG and genetic research in diverse wheat panels.
基金This research was funded by the Hainan Provincial Key R&D Program of China(ZDYF2018073)National Natural Science Foundation of China(41571354)+2 种基金Hainan Provincial Major Science and Technology Program of China(ZDKJ2019006)Agricultural Science and Technology Innovation of Sanya,China(2016NK16)National Special Support Program for High-level Personnel Recruitment(Ten-thousand Talents Program)(Wenjiang Huang),Innovation Foundation of Director of Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences.We also gratefully acknowledge the National Meteorological Information Center of China,Guangxi Jiejiarun Technology Co.,Ltd.and Guangxi Jinsui Agriculture Group Co.,Ltd.for the experiments.
文摘The disease of banana Fusarium wilt currently threatens banana production areas all over the world.Rapid and large-area monitoring of Fusarium wilt disease is very important for the disease treatment and crop planting adjustments.The objective of this study was to evaluate the performance of supervised classification algorithms such as support vector machine(SVM),random forest(RF),and artificial neural network(ANN)algorithms to identify locations that were infested or not infested with Fusarium wilt.An unmanned aerial vehicle(UAV)equipped with a five-band multi-spectral sensor(blue,green,red,red-edge and near-infrared bands)was used to capture the multi-spectral imagery.A total of 139 ground sample-sites were surveyed to assess the occurrence of banana Fusarium wilt.The results showed that the SVM,RF,and ANN algorithms exhibited good performance for identifying and mapping banana Fusarium wilt disease in UAV-based multi-spectral imagery.The overall accuracies of the SVM,RF,and ANN were 91.4%,90.0%,and 91.1%,respectively for the pixel-based approach.The RF algorithm required significantly less training time than the SVM and ANN algorithms.The maps generated by the SVM,RF,and ANN algorithms showed the areas of occurrence of Fusarium wilt disease were in the range of 5.21-5.75 hm2,accounting for 36.3%-40.1%of the total planting area of bananas in the study area.The results also showed that the inclusion of the red-edge band resulted in an increase in the overall accuracy of 2.9%-3.0%.A simulation of the resolutions of satellite-based imagery(i.e.,0.5 m,1 m,2 m,and 5 m resolutions)showed that imagery with a spatial resolution higher than 2 m resulted in good identification accuracy of Fusarium wilt.The results of this study demonstrate that the RF classifier is well suited for the identification and mapping of banana Fusarium wilt disease from UAV-based remote sensing imagery.The results provide guidance for disease treatment and crop planting adjustments.
基金supported by the 2025 scientific promotion program funded by Jeju National University.
文摘Accurate and timely estimation of above-ground biomass is crucial for understanding crop growth dynamics,optimizing agricultural input management,and assessing productivity in sustainable farming practices.However,conventional biomass assessments are destructive and resource-intensive.In contrast,remote sensing techniques,particularly those utilizing low-altitude unmanned aerial vehicles,provide a non-destructive approach to collect imagery data on plant canopy features,including spectral reflectance and structural details at any stage of the crop life cycle.This study explores the potential visible-light-derived vegetative indices to improve biomass prediction during the flowering period of buckwheat(Fagopyrum tataricum).Red,green,and blue(RGB)images of buckwheat were acquired during peak flowering,using a DJI P4 multispectral Drone.From the analysis of those images,four vegetative indices were calculated.Aboveground fresh biomass was harvested and measured on 14 September 2024.The results showed negative correlations between the green-band based excess green(ExG),excess green minus excess red(ExGR),and green leaf index(GLI)indices and the fresh above-ground biomass of buckwheat,while the red band-based excess red(ExR)index showed an insignificant positive correlation at p<0.10.An investigation into greenband-based vegetation indices(VIs)for estimating fresh biomass revealed significant negative correlations during the experimental period.This unexpected inverse relationship is attributed to spectral interference from abundant white flowers during the flowering stage,where the high reflectance of white petals masked the green vegetation signal.Consequently,these green-band VIs demonstrated limited predictive power for biomass under such conditions,indicating that their utility is compromised when floral reflectance is dominant.Therefore,we suggest that further experiments are required to validate this relationship and improve the estimation of fresh above-ground biomass in white-flowered buckwheat plants.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(RS-2025-00559546)supported by the IITP(Institute of Information&Coummunications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korea government(Ministry of Science and ICT)(IITP-2025-RS-2023-00259004).
文摘The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.
基金supported in part by the National Natural Science Foundation of China under Grants 62341104,62201085,62325108,and 62341131.
文摘Unmanned aerial vehicle (UAV)-based edge computing is an emerging technology that provides fast task processing for a wider area. To address the issues of limited computation resource of a single UAV and finite communication resource in multi-UAV networks, this paper joints consideration of task offloading and wireless channel allocation on a collaborative multi-UAV computing network, where a high altitude platform station (HAPS)is adopted as the relay device for communication between UAV clusters consisting of UAV cluster heads (ch-UAVs) and mission UAVs (m-UAVs). We propose an algorithm, jointing task offloading and wireless channel allocation to maximize the average service success rate (ASSR)of a period time. In particular,the simulated annealing(SA)algorithm with random perturbations is used for optimal channel allocation,aiming to reduce interference and minimize transmission delay.A multi-agent deep deterministic policy gradient (MADDPG) is proposed to get the best task offloading strategy. Simulation results demonstrate the effectiveness of the SA algorithm in channel allocation. Meanwhile,when jointly considering computation and channel resources,the proposed scheme effectively enhances the ASSR in comparison to other benchmark algorithms.
基金funded by a program of the Natural Science Foundation of Heilongjiang Province,Research on Key Technologies of Wildlife Intelligent Monitoring(LH2020C034)the National Natural Science Foundation of China(NSFC31872241,32100392)the Fundamental Research Funds for the Central Universities(2572022DS04).
文摘Unmanned aerial vehicle(UAV)technology,artificial intelligence,and the relevant hardware can be used for monitoring wild animals.However,existing methods have several limitations.Therefore,this study explored the monitoring and protection of Amur tigers and their main prey species using images from UAVs by optimizing the algorithm models with respect to accuracy,model size,recognition speed,and elimination of environmental inter-ference.Thermal imaging data were collected from 2000 pictures with a thermal imaging lens on a DJI M300RTK UAV at the Hanma National Nature Reserve in the Greater Khingan Mountains in Inner Mongolia,Wangqing National Nature Reserve in Jilin Province,and Siberian Tiger Park in Heilongjiang Province.The YOLO V5s al-gorithm was applied to recognize the animals in the pictures.The accuracy rate was 94.1%,and the size of the model weight(total weight of each model layer trained with the training set)was 14.8 MB.The authors improved the structures and parameters of the YOLO V5s algorithm.As a result,the recognition accuracy rate became 96%,and the model weight was 9.3 MB.The accuracy rate increased by 1.9%,the model weight decreased by 37.2%from 14.8 MB to 9.3 MB,and the recognition time of a single picture was shortened by 34.4%from 0.032 to 0.021 s.This not only increases the recognition accuracy but also effectively lowers the hardware requirements that the algorithm relies on,which provides a lightweight fast recognition method for UAV-based edge computing and online investigation of wild animals.
