针对真实环境下采集的病害图像中存在的大量噪声和复杂背景干扰,导致作物病害识别准确性和泛化性低的问题,该研究提出基于自适应BayesShrink和频-空特征融合的作物病害识别方法(adaptive BayesShrink and frequencyspatial domain featu...针对真实环境下采集的病害图像中存在的大量噪声和复杂背景干扰,导致作物病害识别准确性和泛化性低的问题,该研究提出基于自适应BayesShrink和频-空特征融合的作物病害识别方法(adaptive BayesShrink and frequencyspatial domain features fusion, AFSF-DCT)。首先,设计了自适应BayesShrink算法(Ad-BayesShrink)以减少噪声干扰,同时保留更多细节,降低识别模型提取病害特征的难度。然后提出基于频-空特征融合和动态交叉自注意机制的作物病害识别模型(crop leaf disease identification model based on frequency-spatial features fusion and dynamic cross-self-attention,FSF-DCT)。为实现全面的频-空特征映射,设计了基于离散小波变换(discrete wavelet transform,DWT)和倒残差结构(bneck)的频-空特征映射(DWT-Bneck)分支以捕获多尺度病害特征。频域分支设计了基于2D DWT的特征映射模块(2D DWT-based frequency-features decomposition module, DWFD)以捕获病害细节和纹理,用于补充空间域特征在全局信息表达上的不足。空间域分支在bneck中引入CBAM(convolutional block attention module)和Dynamic Shift Max激活函数以实现全面的空间特征映射。最后设计了动态交叉自注意特征融合模块(multi-scale features fusion network based on dynamic cross-self-attention, MDCS-DF)融合频-空特征并增强模型对病害特征的关注。结果表明,Ad-BayesShrink获得了35.78的最高峰值信噪比,优于VisuShrink和SUREShrink。FSF-DCT在自建数据集和2个开源数据集(PlantVillage和AI challenger 2018)上分别获得了99.20%、99.90%和90.75%的识别精度,且具有较小的参数量(7.48 M)和浮点运算数(4.62 G),优于当前大部分的主流识别模型。AFSF-DCT可为复杂背景下的作物叶片病害的快速精准检测提供模型参考。展开更多
无人驾驶车辆近年来一直是研究的热点.无人车运行环境复杂、不确定因素多,尤其当其意外驶入水坑、泥潭等地形时可能直接导致抛锚,造成不可估量的损失,因此水体检测对无人车的运行有着重要意义.借助深度网络的强大学习能力,本文首先将反...无人驾驶车辆近年来一直是研究的热点.无人车运行环境复杂、不确定因素多,尤其当其意外驶入水坑、泥潭等地形时可能直接导致抛锚,造成不可估量的损失,因此水体检测对无人车的运行有着重要意义.借助深度网络的强大学习能力,本文首先将反射注意力单元和自注意力机制相结合,并在(U shape Network,U-Net)模型基础上添加残差卷积块和上采样卷积模块,得到了新的道路场景水体区域检测模型(U shape Network with Attention for Road,URA-Net),该模型能够更好地捕捉特征依赖关系,提高水体语义特征的表示能力.进一步,本文提出了一种基于双生成器对抗学习的训练模型(Redundant With Dual Generative Adversarial Network,RWD-GAN),它对URA-Net稍做修改,拓展成两个生成器,通过在对抗网络框架下让生成器与鉴别器、生成器与生成器之间实现对抗学习,促进不同网络模型之间的信息传递.在公开数据集上的大量实验表明URA-Net达到了87.18%的F1指标,而RWD-GAN模型能够进一步提高水体检测的精度,使提升到了88.54%,URA-Net和RWD-GAN均超出现有深度网络水体检测方法的性能表现.展开更多
Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention an...Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention and control measures.The self-potential(SP)stands out for its sensitivity to contamination plumes,offering a solution for monitoring and detecting the movement and seepage of subsurface pollutants.However,traditional SP inversion techniques heavily rely on precise subsurface resistivity information.In this study,we propose the Attention U-Net deep learning network for rapid SP inversion.By incorporating an attention mechanism,this algorithm effectively learns the relationship between array-style SP data and the location and extent of subsurface contaminated sources.We designed a synthetic landfill model with a heterogeneous resistivity structure to assess the performance of Attention U-Net deep learning network.Additionally,we conducted further validation using a laboratory model to assess its practical applicability.The results demonstrate that the algorithm is not solely dependent on resistivity information,enabling effective locating of the source distribution,even in models with intricate subsurface structures.Our work provides a promising tool for SP data processing,enhancing the applicability of this method in the field of near-subsurface environmental monitoring.展开更多
文摘针对真实环境下采集的病害图像中存在的大量噪声和复杂背景干扰,导致作物病害识别准确性和泛化性低的问题,该研究提出基于自适应BayesShrink和频-空特征融合的作物病害识别方法(adaptive BayesShrink and frequencyspatial domain features fusion, AFSF-DCT)。首先,设计了自适应BayesShrink算法(Ad-BayesShrink)以减少噪声干扰,同时保留更多细节,降低识别模型提取病害特征的难度。然后提出基于频-空特征融合和动态交叉自注意机制的作物病害识别模型(crop leaf disease identification model based on frequency-spatial features fusion and dynamic cross-self-attention,FSF-DCT)。为实现全面的频-空特征映射,设计了基于离散小波变换(discrete wavelet transform,DWT)和倒残差结构(bneck)的频-空特征映射(DWT-Bneck)分支以捕获多尺度病害特征。频域分支设计了基于2D DWT的特征映射模块(2D DWT-based frequency-features decomposition module, DWFD)以捕获病害细节和纹理,用于补充空间域特征在全局信息表达上的不足。空间域分支在bneck中引入CBAM(convolutional block attention module)和Dynamic Shift Max激活函数以实现全面的空间特征映射。最后设计了动态交叉自注意特征融合模块(multi-scale features fusion network based on dynamic cross-self-attention, MDCS-DF)融合频-空特征并增强模型对病害特征的关注。结果表明,Ad-BayesShrink获得了35.78的最高峰值信噪比,优于VisuShrink和SUREShrink。FSF-DCT在自建数据集和2个开源数据集(PlantVillage和AI challenger 2018)上分别获得了99.20%、99.90%和90.75%的识别精度,且具有较小的参数量(7.48 M)和浮点运算数(4.62 G),优于当前大部分的主流识别模型。AFSF-DCT可为复杂背景下的作物叶片病害的快速精准检测提供模型参考。
文摘无人驾驶车辆近年来一直是研究的热点.无人车运行环境复杂、不确定因素多,尤其当其意外驶入水坑、泥潭等地形时可能直接导致抛锚,造成不可估量的损失,因此水体检测对无人车的运行有着重要意义.借助深度网络的强大学习能力,本文首先将反射注意力单元和自注意力机制相结合,并在(U shape Network,U-Net)模型基础上添加残差卷积块和上采样卷积模块,得到了新的道路场景水体区域检测模型(U shape Network with Attention for Road,URA-Net),该模型能够更好地捕捉特征依赖关系,提高水体语义特征的表示能力.进一步,本文提出了一种基于双生成器对抗学习的训练模型(Redundant With Dual Generative Adversarial Network,RWD-GAN),它对URA-Net稍做修改,拓展成两个生成器,通过在对抗网络框架下让生成器与鉴别器、生成器与生成器之间实现对抗学习,促进不同网络模型之间的信息传递.在公开数据集上的大量实验表明URA-Net达到了87.18%的F1指标,而RWD-GAN模型能够进一步提高水体检测的精度,使提升到了88.54%,URA-Net和RWD-GAN均超出现有深度网络水体检测方法的性能表现.
基金Projects(42174170,41874145,72088101)supported by the National Natural Science Foundation of ChinaProject(CX20200228)supported by the Hunan Provincial Innovation Foundation for Postgraduate,China。
文摘Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention and control measures.The self-potential(SP)stands out for its sensitivity to contamination plumes,offering a solution for monitoring and detecting the movement and seepage of subsurface pollutants.However,traditional SP inversion techniques heavily rely on precise subsurface resistivity information.In this study,we propose the Attention U-Net deep learning network for rapid SP inversion.By incorporating an attention mechanism,this algorithm effectively learns the relationship between array-style SP data and the location and extent of subsurface contaminated sources.We designed a synthetic landfill model with a heterogeneous resistivity structure to assess the performance of Attention U-Net deep learning network.Additionally,we conducted further validation using a laboratory model to assess its practical applicability.The results demonstrate that the algorithm is not solely dependent on resistivity information,enabling effective locating of the source distribution,even in models with intricate subsurface structures.Our work provides a promising tool for SP data processing,enhancing the applicability of this method in the field of near-subsurface environmental monitoring.
