为提高小麦病害检测精度,实现将模型方便快速部署到移动端,该研究提出了一种基于改进YOLOv8的轻量化小麦病害检测方法。首先,使用PP-LCNet模型替换YOLOv8网络结构的骨干网络,并在骨干网络层引入深度可分离卷积(depthwise separable conv...为提高小麦病害检测精度,实现将模型方便快速部署到移动端,该研究提出了一种基于改进YOLOv8的轻量化小麦病害检测方法。首先,使用PP-LCNet模型替换YOLOv8网络结构的骨干网络,并在骨干网络层引入深度可分离卷积(depthwise separable convolution, DepthSepConv)结构,减少模型参数量,提升模型检测性能;其次,在颈部网络部分添加全局注意力机制(global attention mechanism, GAM)模块,强化特征中语义信息和位置信息,提高模型特征融合能力;然后,引入轻量级通用上采样内容感知重组(content-aware reassembly of features,CARAFE)模块,提高模型对重要特征的提取能力;最后,使用Wise-IoU(weighted interpolation of sequential evidence for intersection over union)边界损失函数代替原损失函数,提升网络边界框回归性能和对小目标病害的检测效果。试验结果表明,对于大田环境下所采集的小麦病害数据集,改进后模型的参数量及模型大小相比原YOLOv8n基线模型分别降低了12.5%和11.3%,同时精确度(precision)及平均精度均值(mean average precision,m AP)相较于原模型分别提高了4.5和1.9个百分点,优于其他对比目标检测算法,可为小麦病害检测无人机等移动端检测装备的部署和应用提供参考。展开更多
Granite is usually composed of quartz,biotite,feldspar,and cracks,and the variation characteristics of these components could reflect the deformation and failure process of rock well.Taking granite as an example,the v...Granite is usually composed of quartz,biotite,feldspar,and cracks,and the variation characteristics of these components could reflect the deformation and failure process of rock well.Taking granite as an example,the video camera was used to record the deformation and failure process of rock.The distribution of meso-components in video images was then identified.The meso-components of rock failure precursors were also discussed.Moreover,a modified LSTM(long short-term memory method)based on SSA(sparrow search algorithm)was proposed to estimate the change of meso-components of rock failure precursor.It shows that the initiation and expansion of cracks are mainly caused by feldspar and quartz fracture,and when the quartz and feldspar exit the stress framework,rock failure occurs;the second large increase of crack area and the second large decrease of quartz or feldspar area may be used as a precursor of rock failure;the precursor time of rock failure based on meso-scopic components is about 4 s earlier than that observed by the naked eye;the modified LSTM network has the strongest estimation ability for quartz area change,followed by feldspar and biotite,and has the worst estimation ability for cracks;when using the modified LSTM network to predict the precursors of rock instability and failure,quartz and feldspar could be given priority.The results presented herein may provide reference in the investigation of rock failure mechanism.展开更多
Due to rainfall infiltration,groundwater activity,geological processes,and natural erosion,soil often exhibits heterogeneity and unsaturation.Additionally,seismic events can compromise slope stability.Existing analyti...Due to rainfall infiltration,groundwater activity,geological processes,and natural erosion,soil often exhibits heterogeneity and unsaturation.Additionally,seismic events can compromise slope stability.Existing analytical solutions typically consider a single failure mode,leading to inaccurate slope stability assessments.This study analyzes the impact of matric suction through three nonlinear shear strength models and adopts a heterogeneous soil model where cohesion linearly increases with depth.An improved pseudo-dynamic method is used to account for seismic effects.Based on a three-dimensional(3D)trumpet-shaped rotational failure mechanism,a new framework is established to analyze the stability of 3D two-bench slopes in heterogeneous unsaturated soil under seismic effects.The internal energy dissipation rate and external power at failure are calculated,and the gravity increase method is introduced to derive an explicit expression for the safety factor(F_(s)).The results are compared with previously published results,demonstrating the effectiveness of the proposed method.Sensitivity analyses on different parameters are conducted,discussing the influence of various factors on F s.This study proposes a new formula for calculating the F_(s) of 3D two-bench slopes in heterogeneous unsaturated soil under seismic effects,providing a practical application for slope engineering.展开更多
文摘为提高小麦病害检测精度,实现将模型方便快速部署到移动端,该研究提出了一种基于改进YOLOv8的轻量化小麦病害检测方法。首先,使用PP-LCNet模型替换YOLOv8网络结构的骨干网络,并在骨干网络层引入深度可分离卷积(depthwise separable convolution, DepthSepConv)结构,减少模型参数量,提升模型检测性能;其次,在颈部网络部分添加全局注意力机制(global attention mechanism, GAM)模块,强化特征中语义信息和位置信息,提高模型特征融合能力;然后,引入轻量级通用上采样内容感知重组(content-aware reassembly of features,CARAFE)模块,提高模型对重要特征的提取能力;最后,使用Wise-IoU(weighted interpolation of sequential evidence for intersection over union)边界损失函数代替原损失函数,提升网络边界框回归性能和对小目标病害的检测效果。试验结果表明,对于大田环境下所采集的小麦病害数据集,改进后模型的参数量及模型大小相比原YOLOv8n基线模型分别降低了12.5%和11.3%,同时精确度(precision)及平均精度均值(mean average precision,m AP)相较于原模型分别提高了4.5和1.9个百分点,优于其他对比目标检测算法,可为小麦病害检测无人机等移动端检测装备的部署和应用提供参考。
基金Project(41472254)supported by the National Natural Science Foundation of China。
文摘Granite is usually composed of quartz,biotite,feldspar,and cracks,and the variation characteristics of these components could reflect the deformation and failure process of rock well.Taking granite as an example,the video camera was used to record the deformation and failure process of rock.The distribution of meso-components in video images was then identified.The meso-components of rock failure precursors were also discussed.Moreover,a modified LSTM(long short-term memory method)based on SSA(sparrow search algorithm)was proposed to estimate the change of meso-components of rock failure precursor.It shows that the initiation and expansion of cracks are mainly caused by feldspar and quartz fracture,and when the quartz and feldspar exit the stress framework,rock failure occurs;the second large increase of crack area and the second large decrease of quartz or feldspar area may be used as a precursor of rock failure;the precursor time of rock failure based on meso-scopic components is about 4 s earlier than that observed by the naked eye;the modified LSTM network has the strongest estimation ability for quartz area change,followed by feldspar and biotite,and has the worst estimation ability for cracks;when using the modified LSTM network to predict the precursors of rock instability and failure,quartz and feldspar could be given priority.The results presented herein may provide reference in the investigation of rock failure mechanism.
基金Project(51378510)supported by the National Natural Science Foundation of China。
文摘Due to rainfall infiltration,groundwater activity,geological processes,and natural erosion,soil often exhibits heterogeneity and unsaturation.Additionally,seismic events can compromise slope stability.Existing analytical solutions typically consider a single failure mode,leading to inaccurate slope stability assessments.This study analyzes the impact of matric suction through three nonlinear shear strength models and adopts a heterogeneous soil model where cohesion linearly increases with depth.An improved pseudo-dynamic method is used to account for seismic effects.Based on a three-dimensional(3D)trumpet-shaped rotational failure mechanism,a new framework is established to analyze the stability of 3D two-bench slopes in heterogeneous unsaturated soil under seismic effects.The internal energy dissipation rate and external power at failure are calculated,and the gravity increase method is introduced to derive an explicit expression for the safety factor(F_(s)).The results are compared with previously published results,demonstrating the effectiveness of the proposed method.Sensitivity analyses on different parameters are conducted,discussing the influence of various factors on F s.This study proposes a new formula for calculating the F_(s) of 3D two-bench slopes in heterogeneous unsaturated soil under seismic effects,providing a practical application for slope engineering.
