条锈病和黄矮病是严重威胁小麦生产的重大病害,病害的早期识别对病害防控具有重要意义。现有病害识别模型对相似表型症状识别困难,对早期病害的识别准确度低。为此,该研究构建了一种改进的快速区域卷积神经网络(Faster Regions with CNN...条锈病和黄矮病是严重威胁小麦生产的重大病害,病害的早期识别对病害防控具有重要意义。现有病害识别模型对相似表型症状识别困难,对早期病害的识别准确度低。为此,该研究构建了一种改进的快速区域卷积神经网络(Faster Regions with CNN Features,Faster-RCNN)的病害识别方法。该方法采用卷积核拆解和下采样延迟策略优化了深度残差网络(Deep Residual Neural Network,ResNet-50),用优化后的ResNet-50作为主干特征提取网络以增强所提取特征的表达力,同时简化模型的参数;并采用ROI(Region of Interest)Align改进ROI迟化层以降低特征量化误差,提升识别的精度。在自建的涵盖200余种不同发病时期、不同抗感性的小麦叶部图像数据集上进行试验,结果表明:改进的Faster-RCNN识别方法比其他SSD(Single Shot Multi-Box Detector)、YOLO(You Only Look Once)和Faster-RCNN网络模型的平均精度均值(mean Average Precision,m AP)分别提升了9.26个百分点、7.64个百分点和14.97个百分点。对小麦条锈病、黄矮病、健康小麦和其他黄化症状小麦识别的平均精度均值可达98.74%;对小麦条锈病和黄矮病轻、重症识别的平均精度均值可达91.06%。同时,模型损失函数值降低更快,整体性能表现更优。进一步开发小麦病害智能识别系统部署研究模型,使用微信小程序进行田间小麦病害的识别。在最大并发100的条件下,小程序平均返回时延为5.02 s,识别返回成功率为97.85%,对两种小麦病害及其细分轻重症识别的平均准确率为93.56%,能够有效满足实际应用需求,可用于指导病害的科学防控。展开更多
基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键...基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键点检测,提出基于改进的Faster R-CNN的手部位姿估计方法。首先提出基于改进的Faster R-CNN手部检测网络,将传统Faster R-CNN网络中的对ROI(regional of interest)的最大值池化,更改为ROI Align,并增加损失函数用于区分左右手。在此基础上增加了头网络分支用以训练输出MANO(hand model with articulated and non-rigid deformations)手部模型的姿态参数和形状参数,得到手部关键点三维坐标,最终得到手部的三维位姿估计结果。实验表明,手部检测结果中存在的自遮挡和尺度问题得到了解决,并且检测结果的准确性有所提高,本文手部检测算法准确率为85%,比传统Faster R-CNN算法提升13%。手部关键点提取算法在MSRA、ICVL、NYU三个数据集分别取得关键点坐标的均方误差值(key-point mean square error,KMSE)为7.50、6.32、8.50的结果。展开更多
This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In ...This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In this paper,since the amount of data collected for deep learning is insufficient,we intend to use the efficient feature extraction function of the neural network based on the Transformer algorithm.We want to use the Cascade Region-based Convolutional Neural Networks(Cascade R-CNN)Swin model,which is a mixture of the transformer model and Cascade R-CNN model to detect greening disease occurring in citrus.In this paper,we try to improve model safety by establishing a linear relationship between samples using Mixup and Cutmix algorithms,which are image processing-based data augmentation techniques.In addition,by using the ImageNet dataset,transfer learning,and stochastic weight averaging(SWA)methods,more accuracy can be obtained.This study compared the Faster Region-based Convolutional Neural Networks Residual Network101(Faster R-CNN ResNet101)model,Cascade Regionbased Convolutional Neural Networks Residual Network101(Cascade RCNN-ResNet101)model,and Cascade R-CNN Swin Model.As a result,the Faster R-CNN ResNet101 model came out as Average Precision(AP)(Intersection over Union(IoU)=0.5):88.2%,AP(IoU=0.75):62.8%,Recall:68.2%,and the Cascade R-CNN ResNet101 model was AP(IoU=0.5):91.5%,AP(IoU=0.75):67.2%,Recall:73.1%.Alternatively,the Cascade R-CNN Swin Model showed AP(IoU=0.5):94.9%,AP(IoU=0.75):79.8%and Recall:76.5%.Thus,the Cascade R-CNN Swin Model showed the best results for detecting citrus greening disease.展开更多
文摘条锈病和黄矮病是严重威胁小麦生产的重大病害,病害的早期识别对病害防控具有重要意义。现有病害识别模型对相似表型症状识别困难,对早期病害的识别准确度低。为此,该研究构建了一种改进的快速区域卷积神经网络(Faster Regions with CNN Features,Faster-RCNN)的病害识别方法。该方法采用卷积核拆解和下采样延迟策略优化了深度残差网络(Deep Residual Neural Network,ResNet-50),用优化后的ResNet-50作为主干特征提取网络以增强所提取特征的表达力,同时简化模型的参数;并采用ROI(Region of Interest)Align改进ROI迟化层以降低特征量化误差,提升识别的精度。在自建的涵盖200余种不同发病时期、不同抗感性的小麦叶部图像数据集上进行试验,结果表明:改进的Faster-RCNN识别方法比其他SSD(Single Shot Multi-Box Detector)、YOLO(You Only Look Once)和Faster-RCNN网络模型的平均精度均值(mean Average Precision,m AP)分别提升了9.26个百分点、7.64个百分点和14.97个百分点。对小麦条锈病、黄矮病、健康小麦和其他黄化症状小麦识别的平均精度均值可达98.74%;对小麦条锈病和黄矮病轻、重症识别的平均精度均值可达91.06%。同时,模型损失函数值降低更快,整体性能表现更优。进一步开发小麦病害智能识别系统部署研究模型,使用微信小程序进行田间小麦病害的识别。在最大并发100的条件下,小程序平均返回时延为5.02 s,识别返回成功率为97.85%,对两种小麦病害及其细分轻重症识别的平均准确率为93.56%,能够有效满足实际应用需求,可用于指导病害的科学防控。
文摘基于视觉的手部位姿估计技术应用于诸多领域,具备着广泛的国际应用市场前景和巨大发展潜力。然而,手部自身存在检测目标过小、手指高自由度以及手部自遮挡等问题。通过对目前存在的难点分析,将手部位姿估计任务分为手部检测和手部关键点检测,提出基于改进的Faster R-CNN的手部位姿估计方法。首先提出基于改进的Faster R-CNN手部检测网络,将传统Faster R-CNN网络中的对ROI(regional of interest)的最大值池化,更改为ROI Align,并增加损失函数用于区分左右手。在此基础上增加了头网络分支用以训练输出MANO(hand model with articulated and non-rigid deformations)手部模型的姿态参数和形状参数,得到手部关键点三维坐标,最终得到手部的三维位姿估计结果。实验表明,手部检测结果中存在的自遮挡和尺度问题得到了解决,并且检测结果的准确性有所提高,本文手部检测算法准确率为85%,比传统Faster R-CNN算法提升13%。手部关键点提取算法在MSRA、ICVL、NYU三个数据集分别取得关键点坐标的均方误差值(key-point mean square error,KMSE)为7.50、6.32、8.50的结果。
基金This research was supported by the Honam University Research Fund,2021.
文摘This study aims to detect and prevent greening disease in citrus trees using a deep neural network.The process of collecting data on citrus greening disease is very difficult because the vector pests are too small.In this paper,since the amount of data collected for deep learning is insufficient,we intend to use the efficient feature extraction function of the neural network based on the Transformer algorithm.We want to use the Cascade Region-based Convolutional Neural Networks(Cascade R-CNN)Swin model,which is a mixture of the transformer model and Cascade R-CNN model to detect greening disease occurring in citrus.In this paper,we try to improve model safety by establishing a linear relationship between samples using Mixup and Cutmix algorithms,which are image processing-based data augmentation techniques.In addition,by using the ImageNet dataset,transfer learning,and stochastic weight averaging(SWA)methods,more accuracy can be obtained.This study compared the Faster Region-based Convolutional Neural Networks Residual Network101(Faster R-CNN ResNet101)model,Cascade Regionbased Convolutional Neural Networks Residual Network101(Cascade RCNN-ResNet101)model,and Cascade R-CNN Swin Model.As a result,the Faster R-CNN ResNet101 model came out as Average Precision(AP)(Intersection over Union(IoU)=0.5):88.2%,AP(IoU=0.75):62.8%,Recall:68.2%,and the Cascade R-CNN ResNet101 model was AP(IoU=0.5):91.5%,AP(IoU=0.75):67.2%,Recall:73.1%.Alternatively,the Cascade R-CNN Swin Model showed AP(IoU=0.5):94.9%,AP(IoU=0.75):79.8%and Recall:76.5%.Thus,the Cascade R-CNN Swin Model showed the best results for detecting citrus greening disease.
