针对拥挤场景下的尺度变化导致人群计数任务中精度较低的问题,提出一种基于多尺度注意力网络(MANet)的密集人群计数模型。通过构建多列模型以捕获多尺度特征,促进尺度信息融合;使用双注意力模块获取上下文依赖关系,增强多尺度特征图的信...针对拥挤场景下的尺度变化导致人群计数任务中精度较低的问题,提出一种基于多尺度注意力网络(MANet)的密集人群计数模型。通过构建多列模型以捕获多尺度特征,促进尺度信息融合;使用双注意力模块获取上下文依赖关系,增强多尺度特征图的信息;采用密集连接重用多尺度特征图,生成高质量的密度图,之后对密度图积分得到计数。此外,提出一种新的损失函数,直接使用点注释图进行训练,以减少由高斯滤波生成新的密度图而带来的额外的误差。在公开人群数据集ShanghaiTech Part A/B、UCF-CC-50、UCF-QNRF上的实验结果均达到了最优,表明该网络可以有效处理拥挤场景下的目标多尺度,并且生成高质量的密度图。展开更多
针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作...针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作为其基础网络,同时修改卷积核尺寸,进一步降低特征图信息的损耗,并且为增强检测模型对小尺度目标的鲁棒性,额外增加第4个尺寸为104×104像素的特征检测层;在对特征图融合操作方面,使用双线性插值法进行上采样操作代替原最近邻插值法上采样操作,解决大部分检测算法中存在的特征严重损失问题;在损失函数方面,使用广义交并比(GIoU)代替交并比(IoU)来计算边界框的损失值,同时引入Focal Loss焦点损失函数作为边界框的置信度损失函数。实验结果表明,改进算法在VisDrone2019数据集上的均值平均精度(mAP)为63.3%,较原始YOLOv3检测模型提高了13.2百分点,并且在GTX 1080 Ti设备上可实现52帧/s的检测速度,对小目标有着较好的检测性能。展开更多
The precision and quality of machining in computer numerical control(CNC)machines are significantly impacted by the state of the tool.Therefore,it is essential and crucial to monitor the tool’s condition in real time...The precision and quality of machining in computer numerical control(CNC)machines are significantly impacted by the state of the tool.Therefore,it is essential and crucial to monitor the tool’s condition in real time during operation.To improve the monitoring accuracy of tool wear values,a tool wear monitoring approach is developed in this work,which is based on an improved integrated model of densely connected convolutional network(DenseNet)and gated recurrent unit(GRU),which incorporates data preprocessing via wavelet packet transform(WPT).Firstly,wavelet packet decomposition(WPD)is used to extract time-frequency domain features from the original timeseries monitoring signals of the tool.Secondly,the multidimensional deep features are extracted from DenseNet containing asymmetric convolution kernels,and feature fusion is performed.A dilation scheme is employed to acquire more historical data by utilizing dilated convolutional kernels with different dilation rates.Finally,the GRU is utilized to extract temporal features from the extracted deep-level signal features,and the feature mapping of these temporal features is then carried out by a fully connected neural network,which ultimately achieves the monitoring of tool wear values.Comprehensive experiments conducted on reference datasets show that the proposed model performs better in terms of accuracy and generalization than other cutting-edge tool wear monitoring algorithms.展开更多
Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy...Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy,insufficient generalization ab ility,and poor noise resistance.To address these issues,this study proposes a novel driving fatigue detection approach based on a n improved dense connection convolutional network.This method innovatively utilizes raw Electroencephalogram(EEG)signals as inp ut to the model without requiring any data preprocessing,thereby enabling end-to-end feature extraction and classification.The network enhances information flow within dense blocks to promote feature reuse,employs multi-scale convolutional layers for fe ature extraction,and integrates an attention mechanism to assign adaptive weights to multi-scale feature channels.After completing primary feature extraction through stacked dense blocks and pooling layers,a multi-class classification function is applie d to detect driving fatigue.Experimental results on the SEED-VIG driving fatigue dataset show that the proposed method achieves an accuracy of 97.32%,a precision of 96.43%,a recall of 95.78%,and an F1-score of 96.10%.Compared to traditional approaches such as Convolutional Neural Networks(CNN)and Long Short-Term Memory Networks(LSTM),the accuracy improves by 5.14%and 3.45%,respectively.This study demonstrates that the proposed method has significant practical value:on one hand,the end-to-end a rchitecture greatly simplifies the complex feature engineering required by traditional methods;on the other hand,the incorporation of feature reuse and attention mechanisms substantially enhances the model’s classification performance and generalization capability,providing a new technical perspective for intelligent driving safety monitoring.展开更多
文摘针对拥挤场景下的尺度变化导致人群计数任务中精度较低的问题,提出一种基于多尺度注意力网络(MANet)的密集人群计数模型。通过构建多列模型以捕获多尺度特征,促进尺度信息融合;使用双注意力模块获取上下文依赖关系,增强多尺度特征图的信息;采用密集连接重用多尺度特征图,生成高质量的密度图,之后对密度图积分得到计数。此外,提出一种新的损失函数,直接使用点注释图进行训练,以减少由高斯滤波生成新的密度图而带来的额外的误差。在公开人群数据集ShanghaiTech Part A/B、UCF-CC-50、UCF-QNRF上的实验结果均达到了最优,表明该网络可以有效处理拥挤场景下的目标多尺度,并且生成高质量的密度图。
文摘针对小尺度目标在检测时精确率低且易出现漏检和误检等问题,提出一种改进的YOLOv3(You Only Look Once version 3)小目标检测算法。在网络结构方面,为提高基础网络的特征提取能力,使用DenseNet-121密集连接网络替换原Darknet-53网络作为其基础网络,同时修改卷积核尺寸,进一步降低特征图信息的损耗,并且为增强检测模型对小尺度目标的鲁棒性,额外增加第4个尺寸为104×104像素的特征检测层;在对特征图融合操作方面,使用双线性插值法进行上采样操作代替原最近邻插值法上采样操作,解决大部分检测算法中存在的特征严重损失问题;在损失函数方面,使用广义交并比(GIoU)代替交并比(IoU)来计算边界框的损失值,同时引入Focal Loss焦点损失函数作为边界框的置信度损失函数。实验结果表明,改进算法在VisDrone2019数据集上的均值平均精度(mAP)为63.3%,较原始YOLOv3检测模型提高了13.2百分点,并且在GTX 1080 Ti设备上可实现52帧/s的检测速度,对小目标有着较好的检测性能。
基金supported by the National Natural Science Foundation of China(62020106003,62273177,62233009)the Natural Science Foundation of Jiangsu Province of China(BK20222012)+2 种基金the Programme of Introducing Talents of Discipline to Universities of China(B20007)the Fundamental Research Funds for the Central Universities(NI2024001)the National Key Laboratory of Space Intelligent Control(HTKJ2023KL502006).
文摘The precision and quality of machining in computer numerical control(CNC)machines are significantly impacted by the state of the tool.Therefore,it is essential and crucial to monitor the tool’s condition in real time during operation.To improve the monitoring accuracy of tool wear values,a tool wear monitoring approach is developed in this work,which is based on an improved integrated model of densely connected convolutional network(DenseNet)and gated recurrent unit(GRU),which incorporates data preprocessing via wavelet packet transform(WPT).Firstly,wavelet packet decomposition(WPD)is used to extract time-frequency domain features from the original timeseries monitoring signals of the tool.Secondly,the multidimensional deep features are extracted from DenseNet containing asymmetric convolution kernels,and feature fusion is performed.A dilation scheme is employed to acquire more historical data by utilizing dilated convolutional kernels with different dilation rates.Finally,the GRU is utilized to extract temporal features from the extracted deep-level signal features,and the feature mapping of these temporal features is then carried out by a fully connected neural network,which ultimately achieves the monitoring of tool wear values.Comprehensive experiments conducted on reference datasets show that the proposed model performs better in terms of accuracy and generalization than other cutting-edge tool wear monitoring algorithms.
文摘Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety.Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy,insufficient generalization ab ility,and poor noise resistance.To address these issues,this study proposes a novel driving fatigue detection approach based on a n improved dense connection convolutional network.This method innovatively utilizes raw Electroencephalogram(EEG)signals as inp ut to the model without requiring any data preprocessing,thereby enabling end-to-end feature extraction and classification.The network enhances information flow within dense blocks to promote feature reuse,employs multi-scale convolutional layers for fe ature extraction,and integrates an attention mechanism to assign adaptive weights to multi-scale feature channels.After completing primary feature extraction through stacked dense blocks and pooling layers,a multi-class classification function is applie d to detect driving fatigue.Experimental results on the SEED-VIG driving fatigue dataset show that the proposed method achieves an accuracy of 97.32%,a precision of 96.43%,a recall of 95.78%,and an F1-score of 96.10%.Compared to traditional approaches such as Convolutional Neural Networks(CNN)and Long Short-Term Memory Networks(LSTM),the accuracy improves by 5.14%and 3.45%,respectively.This study demonstrates that the proposed method has significant practical value:on one hand,the end-to-end a rchitecture greatly simplifies the complex feature engineering required by traditional methods;on the other hand,the incorporation of feature reuse and attention mechanisms substantially enhances the model’s classification performance and generalization capability,providing a new technical perspective for intelligent driving safety monitoring.
