The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation...The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.展开更多
Image segmentation of sea-land remote sensing images is of great importance for downstream applications including shoreline extraction,the monitoring of near-shore marine environment,and near-shore target recognition....Image segmentation of sea-land remote sensing images is of great importance for downstream applications including shoreline extraction,the monitoring of near-shore marine environment,and near-shore target recognition.To mitigate large number of parameters and improve the segmentation accuracy,we propose a new Squeeze-Depth-Wise UNet(SDW-UNet)deep learning model for sea-land remote sensing image segmentation.The proposed SDW-UNet model leverages the squeeze-excitation and depth-wise separable convolution to construct new convolution modules,which enhance the model capacity in combining multiple channels and reduces the model parameters.We further explore the effect of position-encoded information in NLP(Natural Language Processing)domain on sea-land segmentation task.We have conducted extensive experiments to compare the proposed network with the mainstream segmentation network in terms of accuracy,the number of parameters and the time cost for prediction.The test results on remote sensing data sets of Guam,Okinawa,Taiwan China,San Diego,and Diego Garcia demonstrate the effectiveness of SDW-UNet in recognizing different types of sea-land areas with a smaller number of parameters,reduces prediction time cost and improves performance over other mainstream segmentation models.We also show that the position encoding can further improve the accuracy of model segmentation.展开更多
The high dimensionalhyperspectral image classification is a challenging task due to the spectral feature vectors.The high correlation between these features and the noises greatly affects the classification performanc...The high dimensionalhyperspectral image classification is a challenging task due to the spectral feature vectors.The high correlation between these features and the noises greatly affects the classification performances.To overcome this,dimensionality reduction techniques are widely used.Traditional image processing applications recently propose numerous deep learning models.However,in hyperspectral image classification,the features of deep learning models are less explored.Thus,for efficient hyperspectral image classification,a depth-wise convolutional neural network is presented in this research work.To handle the dimensionality issue in the classification process,an optimized self-organized map model is employed using a water strider optimization algorithm.The network parameters of the self-organized map are optimized by the water strider optimization which reduces the dimensionality issues and enhances the classification performances.Standard datasets such as Indian Pines and the University of Pavia(UP)are considered for experimental analysis.Existing dimensionality reduction methods like Enhanced Hybrid-Graph Discriminant Learning(EHGDL),local geometric structure Fisher analysis(LGSFA),Discriminant Hyper-Laplacian projection(DHLP),Group-based tensor model(GBTM),and Lower rank tensor approximation(LRTA)methods are compared with proposed optimized SOM model.Results confirm the superior performance of the proposed model of 98.22%accuracy for the Indian pines dataset and 98.21%accuracy for the University of Pavia dataset over the existing maximum likelihood classifier,and Support vector machine(SVM).展开更多
With the rapid development of social economy,transportation has become faster and more efficient.As an important part of goods transportation,the safe maintenance of tunnel highways has become particularly important.T...With the rapid development of social economy,transportation has become faster and more efficient.As an important part of goods transportation,the safe maintenance of tunnel highways has become particularly important.The maintenance of tunnel roads has become more difficult due to problems such as sealing,narrowness and lack of light.Currently,target detection methods are advantageous in detecting tunnel vehicles in a timely manner through monitoring.Therefore,in order to prevent vehicle misdetection and missed detection in this complex environment,we propose aYOLOv5-Vehicle model based on the YOLOv5 network.This model is improved in three ways.Firstly,The backbone network of YOLOv5 is replaced by the lightweight MobileNetV3 network to extract features,which reduces the number of model parameters;Next,all convolutions in the neck module are improved to the depth-wise separable convolutions to further reduce the number of model parameters and computation,and improve the detection speed of the model;Finally,to ensure the accuracy of the model,the CBAM attention mechanism is introduced to improve the detection accuracy and precision of the model.Experiments results demonstrate that the YOLOv5-Vehicle model can improve the accuracy.展开更多
为实现绝缘子及其缺陷实时检测,文章以改进的区域卷积神经网络(Faster Region Convolutional Neural Networks,Faster R-CNN)作为基础研究算法,将残差网络和特征金字塔网络相融合作为特征提取网络,使用深度可分离卷积替换原有的普通卷积...为实现绝缘子及其缺陷实时检测,文章以改进的区域卷积神经网络(Faster Region Convolutional Neural Networks,Faster R-CNN)作为基础研究算法,将残差网络和特征金字塔网络相融合作为特征提取网络,使用深度可分离卷积替换原有的普通卷积,引入SE通道注意力模块,同时改进了网络中的激活函数。改进后的Faster R-CNN与普通Faster R-CNN相比,全类别平均正确率(mean Average Precision,mAP)和检测速度都有所提高。展开更多
为使苹果采摘机器人在复杂果树背景下能快速准确地检测出苹果,提出一种轻量化YOLO(You only look once)卷积神经网络(Light-YOLOv3)模型与苹果检测方法。首先,对传统YOLOv3深度卷积神经网络架构进行改进,设计一种同构残差块串联的特征...为使苹果采摘机器人在复杂果树背景下能快速准确地检测出苹果,提出一种轻量化YOLO(You only look once)卷积神经网络(Light-YOLOv3)模型与苹果检测方法。首先,对传统YOLOv3深度卷积神经网络架构进行改进,设计一种同构残差块串联的特征提取网络结构,简化目标检测的特征图尺度,采用深度可分离卷积替换普通卷积,提出一种融合均方误差损失和交叉熵损失的多目标损失函数;其次,开发爬虫程序,从互联网上获取训练数据并进行标注,采用数据增强技术对训练数据进行扩充,并对数据进行归一化,针对Light-YOLOv3网络训练,提出一种基于随机梯度下降(Stochastic gradient descent,SGD)和自适应矩估计(Adaptive moment estimation,Adam)的多阶段学习优化技术;最后,分别在计算机工作站和嵌入式开发板上进行了复杂果树背景下的苹果检测实验。结果表明,基于轻量化YOLOv3网络的苹果检测方法在检测速度和准确率方面均有显著的提高,在工作站和嵌入式开发板上的检测速度分别为116.96、7.59 f/s,F1值为94.57%,平均精度均值(Mean average precision,mAP)为94.69%。展开更多
文摘针对船舶实时性检测中出现的检测精度低、漏检问题,改进一种基于YOLOv3-Tiny的船舶目标检测算法。通过引入深度可分离卷积作为主干网络,提高通道数量,减少模型的参数量和运算量;采用H-Swish和Leaky ReLU激活函数改进卷积结构,提取更多特征信息;利用GIOU(Generalized Intersection Over Union)损失优化边界框,突显目标区域重合度,提高精度。在混合船舶数据集上检测结果表明,改进后YOLOv3-Tiny的检测精度为83.40%,较原算法提高5.33百分点,召回率和检测速度也均优于原算法,适用于船舶实时性检测。
基金supported by the Hunan Provincial Natural Science Foundation of China(2021JJ50074)the Scientific Research Fund of Hunan Provincial Education Department(19B082)+6 种基金the Science and Technology Development Center of the Ministry of Education-New Generation Information Technology Innovation Project(2018A02020)the Science Foundation of Hengyang Normal University(19QD12)the Science and Technology Plan Project of Hunan Province(2016TP1020)the Subject Group Construction Project of Hengyang Normal University(18XKQ02)theApplication Oriented SpecialDisciplines,Double First ClassUniversity Project of Hunan Province(Xiangjiaotong[2018]469)the Hunan Province Special Funds of Central Government for Guiding Local Science and Technology Development(2018CT5001)the First Class Undergraduate Major in Hunan Province Internet of Things Major(Xiangjiaotong[2020]248,No.288).
文摘The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.
基金This paper is supported by the following funds:The National Key Research and Development Program of China(2018YFF01010100)The Beijing Natural Science Foundation(4212001)+1 种基金Basic Research Program of Qinghai Province under Grants No.2021-ZJ-704Advanced information network Beijing laboratory(PXM2019_014204_500029).
文摘Image segmentation of sea-land remote sensing images is of great importance for downstream applications including shoreline extraction,the monitoring of near-shore marine environment,and near-shore target recognition.To mitigate large number of parameters and improve the segmentation accuracy,we propose a new Squeeze-Depth-Wise UNet(SDW-UNet)deep learning model for sea-land remote sensing image segmentation.The proposed SDW-UNet model leverages the squeeze-excitation and depth-wise separable convolution to construct new convolution modules,which enhance the model capacity in combining multiple channels and reduces the model parameters.We further explore the effect of position-encoded information in NLP(Natural Language Processing)domain on sea-land segmentation task.We have conducted extensive experiments to compare the proposed network with the mainstream segmentation network in terms of accuracy,the number of parameters and the time cost for prediction.The test results on remote sensing data sets of Guam,Okinawa,Taiwan China,San Diego,and Diego Garcia demonstrate the effectiveness of SDW-UNet in recognizing different types of sea-land areas with a smaller number of parameters,reduces prediction time cost and improves performance over other mainstream segmentation models.We also show that the position encoding can further improve the accuracy of model segmentation.
文摘The high dimensionalhyperspectral image classification is a challenging task due to the spectral feature vectors.The high correlation between these features and the noises greatly affects the classification performances.To overcome this,dimensionality reduction techniques are widely used.Traditional image processing applications recently propose numerous deep learning models.However,in hyperspectral image classification,the features of deep learning models are less explored.Thus,for efficient hyperspectral image classification,a depth-wise convolutional neural network is presented in this research work.To handle the dimensionality issue in the classification process,an optimized self-organized map model is employed using a water strider optimization algorithm.The network parameters of the self-organized map are optimized by the water strider optimization which reduces the dimensionality issues and enhances the classification performances.Standard datasets such as Indian Pines and the University of Pavia(UP)are considered for experimental analysis.Existing dimensionality reduction methods like Enhanced Hybrid-Graph Discriminant Learning(EHGDL),local geometric structure Fisher analysis(LGSFA),Discriminant Hyper-Laplacian projection(DHLP),Group-based tensor model(GBTM),and Lower rank tensor approximation(LRTA)methods are compared with proposed optimized SOM model.Results confirm the superior performance of the proposed model of 98.22%accuracy for the Indian pines dataset and 98.21%accuracy for the University of Pavia dataset over the existing maximum likelihood classifier,and Support vector machine(SVM).
文摘With the rapid development of social economy,transportation has become faster and more efficient.As an important part of goods transportation,the safe maintenance of tunnel highways has become particularly important.The maintenance of tunnel roads has become more difficult due to problems such as sealing,narrowness and lack of light.Currently,target detection methods are advantageous in detecting tunnel vehicles in a timely manner through monitoring.Therefore,in order to prevent vehicle misdetection and missed detection in this complex environment,we propose aYOLOv5-Vehicle model based on the YOLOv5 network.This model is improved in three ways.Firstly,The backbone network of YOLOv5 is replaced by the lightweight MobileNetV3 network to extract features,which reduces the number of model parameters;Next,all convolutions in the neck module are improved to the depth-wise separable convolutions to further reduce the number of model parameters and computation,and improve the detection speed of the model;Finally,to ensure the accuracy of the model,the CBAM attention mechanism is introduced to improve the detection accuracy and precision of the model.Experiments results demonstrate that the YOLOv5-Vehicle model can improve the accuracy.
文摘为实现绝缘子及其缺陷实时检测,文章以改进的区域卷积神经网络(Faster Region Convolutional Neural Networks,Faster R-CNN)作为基础研究算法,将残差网络和特征金字塔网络相融合作为特征提取网络,使用深度可分离卷积替换原有的普通卷积,引入SE通道注意力模块,同时改进了网络中的激活函数。改进后的Faster R-CNN与普通Faster R-CNN相比,全类别平均正确率(mean Average Precision,mAP)和检测速度都有所提高。
文摘为使苹果采摘机器人在复杂果树背景下能快速准确地检测出苹果,提出一种轻量化YOLO(You only look once)卷积神经网络(Light-YOLOv3)模型与苹果检测方法。首先,对传统YOLOv3深度卷积神经网络架构进行改进,设计一种同构残差块串联的特征提取网络结构,简化目标检测的特征图尺度,采用深度可分离卷积替换普通卷积,提出一种融合均方误差损失和交叉熵损失的多目标损失函数;其次,开发爬虫程序,从互联网上获取训练数据并进行标注,采用数据增强技术对训练数据进行扩充,并对数据进行归一化,针对Light-YOLOv3网络训练,提出一种基于随机梯度下降(Stochastic gradient descent,SGD)和自适应矩估计(Adaptive moment estimation,Adam)的多阶段学习优化技术;最后,分别在计算机工作站和嵌入式开发板上进行了复杂果树背景下的苹果检测实验。结果表明,基于轻量化YOLOv3网络的苹果检测方法在检测速度和准确率方面均有显著的提高,在工作站和嵌入式开发板上的检测速度分别为116.96、7.59 f/s,F1值为94.57%,平均精度均值(Mean average precision,mAP)为94.69%。
