Tea,a globally cultivated crop renowned for its uniqueflavor profile and health-promoting properties,ranks among the most favored functional beverages worldwide.However,diseases severely jeopardize the production and qu...Tea,a globally cultivated crop renowned for its uniqueflavor profile and health-promoting properties,ranks among the most favored functional beverages worldwide.However,diseases severely jeopardize the production and quality of tea leaves,leading to significant economic losses.While early and accurate identification coupled with the removal of infected leaves can mitigate widespread infection,manual leaves removal remains time-con-suming and expensive.Utilizing robots for pruning can significantly enhance efficiency and reduce costs.How-ever,the accuracy of object detection directly impacts the overall efficiency of pruning robots.In complex tea plantation environments,complex image backgrounds,the overlapping and occlusion of leaves,as well as small and densely harmful leaves can all introduce interference factors.Existing algorithms perform poorly in detecting small and densely packed targets.To address these challenges,this paper collected a dataset of 1108 images of harmful tea leaves and proposed the YOLO-DBD model.The model excels in efficiently identifying harmful tea leaves with various poses in complex backgrounds,providing crucial guidance for the posture and obstacle avoidance of a robotic arm during the pruning process.The improvements proposed in this study encompass the Cross Stage Partial with Deformable Convolutional Networks v2(C2f-DCN)module,Bi-Level Routing Atten-tion(BRA),Dynamic Head(DyHead),and Focal Complete Intersection over Union(Focal-CIoU)Loss function,enhancing the model’s feature extraction,computation allocation,and perception capabilities.Compared to the baseline model YOLOv8s,mean Average Precision at IoU 0.5(mAP0.5)increased by 6%,and Floating Point Operations Per second(FLOPs)decreased by 3.3 G.展开更多
Although seed dispersal is a key process determining the regeneration and spread of invasive plant populations,few studies have explicitly addressed the link between dispersal vector behavior and seedling recruitment ...Although seed dispersal is a key process determining the regeneration and spread of invasive plant populations,few studies have explicitly addressed the link between dispersal vector behavior and seedling recruitment to gain insight into the invasion process within an urban garden context.We evaluated the role of bird vectors in the dispersal of pokeweed(Phytolacca americana),a North American herb that is invasive in urban gardens in China.Fruiting P.americana attracted both generalist and specialist bird species that fed on and dispersed its seeds.The generalist species Pycnonotus sinensis and Urocissa erythrorhyncha were the most frequent dispersers.Seedling numbers of P.americana were strongly associated with the perching behavior of frugivorous birds.If newly recruited bird species use seedling-safe perching sites,the P.americana will regenerate faster,which would enhance its invasive potential.Based on our observations,we conclude that the 2 main bird vectors,P.sinensis and U.erythrorhyncha,provide potential effective dispersal agents for P.americana.Our results highlight the role of native birds in seed dispersal of invasive plants in urban gardens.展开更多
In this paper, a class of two-step continuity Runge-Kutta（TSCRK） methods for solving singular delay differential equations（DDEs） is presented. Analysis of numerical stability of this methods is given. We consider ...In this paper, a class of two-step continuity Runge-Kutta（TSCRK） methods for solving singular delay differential equations（DDEs） is presented. Analysis of numerical stability of this methods is given. We consider the two distinct cases： （i）τ≥ h, （ii）τ 〈 h, where the delay τ and step size h of the two-step continuity Runge-Kutta methods are both constant. The absolute stability regions of some methods are plotted and numerical examples show the efficiency of the method.展开更多
文摘Tea,a globally cultivated crop renowned for its uniqueflavor profile and health-promoting properties,ranks among the most favored functional beverages worldwide.However,diseases severely jeopardize the production and quality of tea leaves,leading to significant economic losses.While early and accurate identification coupled with the removal of infected leaves can mitigate widespread infection,manual leaves removal remains time-con-suming and expensive.Utilizing robots for pruning can significantly enhance efficiency and reduce costs.How-ever,the accuracy of object detection directly impacts the overall efficiency of pruning robots.In complex tea plantation environments,complex image backgrounds,the overlapping and occlusion of leaves,as well as small and densely harmful leaves can all introduce interference factors.Existing algorithms perform poorly in detecting small and densely packed targets.To address these challenges,this paper collected a dataset of 1108 images of harmful tea leaves and proposed the YOLO-DBD model.The model excels in efficiently identifying harmful tea leaves with various poses in complex backgrounds,providing crucial guidance for the posture and obstacle avoidance of a robotic arm during the pruning process.The improvements proposed in this study encompass the Cross Stage Partial with Deformable Convolutional Networks v2(C2f-DCN)module,Bi-Level Routing Atten-tion(BRA),Dynamic Head(DyHead),and Focal Complete Intersection over Union(Focal-CIoU)Loss function,enhancing the model’s feature extraction,computation allocation,and perception capabilities.Compared to the baseline model YOLOv8s,mean Average Precision at IoU 0.5(mAP0.5)increased by 6%,and Floating Point Operations Per second(FLOPs)decreased by 3.3 G.
基金supported by the National 973 Key Project of Basic Science Research(no.2012CB430405)National Natural Science Foundation Foundation of China(No.31470512+1 种基金No.41101172)China Postdoctoral Science Foundation(No.2015M571734).
文摘Although seed dispersal is a key process determining the regeneration and spread of invasive plant populations,few studies have explicitly addressed the link between dispersal vector behavior and seedling recruitment to gain insight into the invasion process within an urban garden context.We evaluated the role of bird vectors in the dispersal of pokeweed(Phytolacca americana),a North American herb that is invasive in urban gardens in China.Fruiting P.americana attracted both generalist and specialist bird species that fed on and dispersed its seeds.The generalist species Pycnonotus sinensis and Urocissa erythrorhyncha were the most frequent dispersers.Seedling numbers of P.americana were strongly associated with the perching behavior of frugivorous birds.If newly recruited bird species use seedling-safe perching sites,the P.americana will regenerate faster,which would enhance its invasive potential.Based on our observations,we conclude that the 2 main bird vectors,P.sinensis and U.erythrorhyncha,provide potential effective dispersal agents for P.americana.Our results highlight the role of native birds in seed dispersal of invasive plants in urban gardens.
文摘In this paper, a class of two-step continuity Runge-Kutta（TSCRK） methods for solving singular delay differential equations（DDEs） is presented. Analysis of numerical stability of this methods is given. We consider the two distinct cases： （i）τ≥ h, （ii）τ 〈 h, where the delay τ and step size h of the two-step continuity Runge-Kutta methods are both constant. The absolute stability regions of some methods are plotted and numerical examples show the efficiency of the method.
