检索结果-内蒙古大学图书馆

Deep convolution network for dense crowd counting

IET IMAGE PROCESSING 2020年第4期14卷 621-627页

作者： Zhang, Wei Wang, Yongjie Liu, Yanyan Zhu, Jianghua Tianjin Univ Sch Microelect Tianjin 300072 Peoples R China China Elect Technol Grp Corp Res Inst 54 Dept Intelligence Shijiazhuang 050081 Hebei Peoples R China Nankai Univ Key Lab Photoelect Thin Film Devices & Technol Ti Tianjin 300071 Peoples R China

Estimating the total number of people in a crowded situation is a challenging task due to numerous occlusions and perspective changes existing in crowd images. To address this issue, the authors have proposed a new deep learning framework for accurate and efficient crowd counting here. Inspired by multi-column convolutional neural network (MCNN) and contextual pyramid convolutional neural network (CP-CNN), the authors use a combination of a two branches, convolutional neutral network (CNN) and transposed convolutional layers, to generate a high-quality density map. The two-branch CNN for feature extraction generates a density map that is only a quarter of size of the original image Then a set of transposed convolutional layers and convolutional layers are combined with the network to make up for the detail loss of the density map conducted by stacked pooling. Compared with MCNN and CP-CNN, the authors' approach employs fewer branches and simpler architecture. Experimental result shows that their approach achieves MAE 80.7 and MSE 131.2 in ShanghaiTech PartA dataset, MAE 15.6 and MSE 26.8 in ShanghaiTech PartB dataset, and MAE Average 7.1 in WorldExpo'10 dataset.

关键词： learning (artificial intelligence) feature extraction object detection convolutional neural nets dense crowd counting deep learning framework MCNN CP-CNN convolutional neutral network transposed convolutional layers high-quality density map two-branch CNN deep convolution network feature extraction density map stacked pooling ShanghaiTech PartA dataset ShanghaiTech PartB dataset

来源：评论

学校读者我要写书评

暂无评论

Driver identification through vehicular CAN bus data: An ensemble deep learning approach

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第5期17卷 867-877页

作者： Hu, Hongyu Liu, Jiarui Chen, Guoying Zhao, Yuting Men, Yuzhuo Wang, Pin Jilin Univ State Key Lab Automot Simulat & Control Changchun Jilin Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China Changchun Inst Technol Sch Automot Engn Changchun Jilin Peoples R China Univ Calif Berkeley Calif PATH Berkeley CA 94720 USA

Driver identification using in-vehicle data is receiving considerable attention in the field of intelligent transportation owing to the advances in deep learning (DL). In order to improve accuracy and robustness of identification, this paper proposes an ensemble deep learning framework that integrates a modified one-dimensional convolutional neural network (M 1-D CNN) and bidirectional long short-term memory (BLSTM) to improve the performance and robustness of driver identification using information extracted from vehicular CAN-bus signals. The M 1-D CNN architecture is developed by adopting inception blocks, residual connection, and global average pooling to obtain optimal deep-feature representations of local time series. The BLSTM is used to learn the bidirectional long-term temporal dependencies. Results of extensive experiments using real driving data show that the proposed ensemble DL model can improve the accuracy and robustness of driver identification. Furthermore, four data augmentation methods, namely up-sampling, adding noise, data reversal, and random drifting, are used to expand the original training data to improve the performance of the ensemble method. Especially, few-shot learning is performed using the four data augmentation methods, and it shows excellent potential for driver identification with limited data.

关键词： feature extraction driver identification M 1-D CNN architecture recurrent neural nets deep-feature representations vehicular CAN-bus signals Time series BLSTM robustness time series few-shot learning neural nets vehicular CAN bus data neural net architecture Local area networks Control engineering computing convolutional neural nets controller area networks driver information systems Traffic engineering computing Data handling techniques bidirectional long short-term memory modified one-dimensional convolutional neural network intelligent transportation deep learning (artificial intelligence) data augmentation methods intelligent transportation systems ensemble deep learning approach data augmentation in-vehicle data

来源：评论

学校读者我要写书评

暂无评论

Asymmetric cost aggregation network for efficient stereo matching

引用

IET IMAGE PROCESSING 2023年第8期17卷 2450-2466页

作者： Wu, Zhong Zhu, Hong He, Lili Wang, Dong Shi, Jing Wu, Wenhuan Xian Univ Technol Sch Automat & Informat Engn Xian Shaanxi Peoples R China Yuncheng Univ Dept Phys & Elect Engn Yuncheng Peoples R China Hubei Univ Automot Technol Sch Elect & Informat Engn Shiyan Peoples R China Xian Univ Technol Sch Automat & Informat Engn 5 Jinhua South Rd Xian 710048 Shaanxi Peoples R China

Cost aggregation is crucial to the accuracy of stereo matching. A reasonable cost aggregation algorithm should aggregate costs within homogeneous regions where pixels have the same or similar disparities. Otherwise, the estimated disparity map is prone to the well-known edge-fattening issue and the problem of losing fine structures. However, current state-of-the-art convolutional neural networks (CNNs) mainly do cost aggregation with square-kernel convolutional layers that learn to adjust their kernel elements to make the actual receptive fields of the aggregated costs adapt to homogeneous regions with various shapes. This is a mechanism that easily leads to the above issues due to the translation equivalence and content-insensitivity properties of CNNs. To tackle these problems, a novel densely connected asymmetric convolution block (Dense-ACB) based on asymmetric convolutions is proposed to explicitly construct receptive fields with various shapes, which effectively alleviates the issues caused by mismatching shapes of receptive fields and homogeneous regions. The proposed Dense-ACB brings new insight to CNN-based stereo matching networks. Based on the proposed cost aggregation method, an efficient and effective stereo matching network is built, which not only achieves competitive overall accuracy compared with state-of-the-art models but also effectively alleviates the edge-fattening problem and preserves fine structures.

关键词： computer vision convolutional neural nets image matching stereo image processing

来源：评论

学校读者我要写书评

暂无评论

GIS partial discharge pattern recognition via a novel capsule deep graph convolutional network

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2022年第14期16卷 2903-2912页

作者： Wang, Yanxin Yan, Jing Ye, Xinyu Qi, Zhenkang Wang, Jianhua Geng, Yingsan Xi An Jiao Tong Univ State Key Lab Elect Insulat & Power Equipment Xian 710049 Peoples R China Tsinghua Univ State Key Lab Power Syst Beijing Peoples R China

Deep learning (DL) has attracted significant attention in partial discharge (PD) pattern recognition of gas-insulated switchgear (GIS). However, the existing DL method extracts numerical information and ignores spatial correlation information. In addition, once the sample size is reduced, model performance is severely degraded. To address these issues, a novel capsule deep graph convolutional network (CDGCN) is employed for GIS PD pattern recognition. First, the GIS PD data is transformed to graph data. Then, the CDGCN is established for GIS PD pattern recognition. The introduction of a ChannelSortPooling layer enriches the graph representation information and filters out the feature values with higher information content. In addition, the multi-view graph representation is converted to a capsule form, and a capsule network with stronger feature extraction capability is introduced to improve the accuracy of the final graph representation. The results reveal that the proposed CDGCN can effectively diagnose the GIS PD and is more accurate than the traditional DL method. The proposed CDGCN can handle small samples pattern recognition problems and provides a reliable reference for GIS PD pattern recognition.

关键词： gas-insulated switchgear GIS PD pattern recognition gas insulated switchgear graph theory image recognition spatial correlation information convolutional neural nets GIS partial discharge pattern recognition graph representation information deep learning capsule deep graph convolutional network DL method extracts numerical information partial discharges multiview graph representation feature extraction GIS PD data samples pattern recognition problems image representation CDGCN image motion analysis deep learning (artificial intelligence) power engineering computing

来源：评论

学校读者我要写书评

暂无评论

An efficient hyperspectral image classification method for limited training data

引用

IET IMAGE PROCESSING 2023年第6期17卷 1709-1717页

作者： Ren, Yitao Jin, Peiyang Li, Yiyang Mao, Keming Northeastern Univ Software Coll Shenyang Peoples R China

Hyperspectral image classification has gained great progress in recent years based on deep learning model and massive training data. However, it is expensive and unpractical to label hyperspectral image data and implement model in constrained environment. To address this problem, this paper proposes an effective ghost module based spectral network for hyperspectral image classification. First, Ghost3D module is adopted to reduce the size of model parameter dramatically by redundant feature maps generation with linear transformation. Then Ghost2D module with channel-wise attention is used to explore informative spectral feature representation. For large field covering, the non-local operation is utilized to promote self-attention. Compared with the state-of-the-art hyperspectral image classification methods, the proposed approach achieves superior performance on three hyperspectral image data sets with fewer sample labelling and less resource consumption.

关键词： computer vision convolutional neural nets hyperspectral imaging neural nets

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based hybrid model for the behaviour prediction of surrounding vehicles over long-time periods

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第10期16卷 1404-1412页

作者： Gao, Xiang Chen, Long Tai, Kangsheng Cai, Yingfeng Wang, Hai Li, Yicheng Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Univ Sch Automot & Traff Engn Zhenjiang Jiangsu Peoples R China

Autonomous vehicles need to have the ability to predict the future behaviour of surrounding vehicles, which helps with proper trajectory planning and tracking. Many behaviour prediction methods have limited application because they have a very limited prediction horizon. This paper proposes a deep learning-based hybrid model for behaviour prediction over long-time periods, including manoeuvre recognition and a behaviour prediction module. In manoeuvre recognition module, the CNN extracts the social characteristics of the target vehicle and LSTM outputs the manoeuvre probability vector to form a contextual feature vector with the social features. In the behaviour prediction module, LSTM and Attention are based on the contextual feature vector to capture multi-time step information in the behaviour time window to complete the prediction of the target vehicle behaviour. Real-car collection and open-source vehicle trajectory datasets were used for training and testing. The results show that the proposed algorithm could predict vehicle behaviour with an accuracy of 89.73% and an average prediction time of 2.032 s, which has a high engineering application value.

关键词： LSTM mobile robots autonomous vehicles target vehicle behaviour prediction trajectory control deep learning (artificial intelligence) contextual feature vector long-time periods control engineering computing automobiles real-car collection tracking path planning convolutional neural nets deep learning-based hybrid model recurrent neural nets open-source vehicle trajectory datasets road traffic control social features CNN manoeuvre recognition feature extraction trajectory planning manoeuvre probability vector behaviour time window probability multitime step information motion control attention mechanism surrounding vehicle behaviour average prediction time traffic engineering computing prediction horizon

来源：评论

学校读者我要写书评

暂无评论

SAR image classification based on multi-feature fusion decision convolutional neural network

引用

IET IMAGE PROCESSING 2022年第1期16卷 1-10页

作者： Guo, Liang Gannan Normal Univ Sch Informat & Educ Technol Ctr Ganzhou 341000 Jiangxi Peoples R China

With the success of convolutional neural network (CNN) in the field of image processing and image recognition, an improved fully convolutional neural network (FCNN) based on CNN is proposed. Although FCNN has better performance than CNN, the number of parameters of FCNN has also increased significantly compared to CNN. Consequently, this paper proposes a multi-feature fusion decision convolutional neural network (MFFD-CNN), which use two kinds down-sample methods in the pooling layer, and chooses the concatenate or add operation as the way that consolidates the feature of the convolutional layer with a stride of 2 and the max-pooling layer to execute fusion operations. Meanwhile replaces the traditional softmax loss with an additive margin Softmax (AM-Softmax) loss. The structure, which is based on the multi-target classification experiment results of the MSTAR data set, shows can not only obtain an average correct recognition rate 1.2% higher than FCNN, but also better stability without augmenting the training samples of MSTAR data.

关键词： multitarget classification image fusion fully convolutional neural network multifeature fusion decision convolutional neural network image classification concatenate operation convolutional neural nets SAR image classification radar imaging MFFD-CNN image sampling image recognition down-sample methods FCNN additive margin Softmax loss image processing add operation synthetic aperture radar radar target recognition MSTAR data set

来源：评论

学校读者我要写书评

暂无评论

Dual attention module and multi-label based fully convolutional network for crowd counting

引用

IET COMPUTER VISION 2020年第7期14卷 443-451页

作者： Wang, Suyu Yang, Bin Liu, Bo Zheng, Guanghui Beijing Engn Res Ctr IoT Software & Syst Beijing 100124 Peoples R China Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

High-density crowd counting in natural scenes is an extremely difficult and challenging research subject in computer vision. Although the algorithm based on the convolutional neural network has achieved significantly better results than the traditional algorithm, most of them tend to focus on the local features of images, and difficult to obtain the rich global contextual dependencies. To solve this problem, a dual attention module and a multi-label based fully convolutional network are proposed in this study. Moreover, the authors improve the algorithm by the following multiple perspectives. Firstly, introducing the dual attention module, the global-context and long-range dependency are adaptively integrated into both spatial and channel dimensions, which improve the network expression ability. Then, the prediction error is effectively reduced by designing a multilabel mechanism, so the crowd-counting task is transformed into foreground and background segmentation tasks to assist in the regression task of the density map. Furthermore, on the basis of the traditional Euclidean distance loss and cross-entropy loss, the structural similarity index is introduced to further improve the training effect of the model. The test results of the UCF_CC_50, ShanghaiTech, and UCF-QNRF datasets indicate that the proposed method is superior to the current mainstream algorithm.

关键词： natural scenes convolutional neural network multilabel based fully convolutional network rich global contextual dependencies cross-entropy loss computer vision dual attention module foreground segmentation task Euclidean distance loss spatial dimension density map current mainstream algorithm network expression ability object detection crowd-counting task multilabel mechanism convolutional neural nets channel dimension background segmentation task image segmentation structural similarity index high-density crowd counting entropy

来源：评论

学校读者我要写书评

暂无评论

SNR-dependent drone classification using convolutional neural networks

引用

IET RADAR SONAR AND NAVIGATION 2022年第1期16卷 22-33页

作者： Dale, Holly Baker, Chris Antoniou, Michail Jahangir, Mohammed Atkinson, George Harman, Stephen Univ Birmingham Microwave Integrated Syst Lab Birmingham B15 2TT W Midlands England Aveillant Cambridge England

Radar sensing offers a method of achieving 24-h all-weather drone surveillance, but in order to be maximally effective, systems need to be able to discriminate between birds and drones. This work examines drone-bird classification performance as a function of signal to noise ratio (SNR). Classification at low SNR values is necessary in order to classify drones with a small radar cross-section (RCS), as well as to facilitate reliable classification at longer ranges. To investigate the relationship between classification performance and SNR, Gaussian noise is added to an experimentally obtained dataset of radar spectrograms. Classification is performed by convolutional neural networks (CNNs). It is shown that for the data available classification accuracy drops with falling SNR, as might be expected for any given CNN. The degree to which performance degrades with reduced SNR is presented. It is further shown that simpler network architectures are more robust to noise. Finally, it is demonstrated that data augmentation can be used as a means of enhancing classification accuracy at lower SNR values. Bayesian optimisation is used to find the optimal augmentation hyperparameters and overall, classification accuracies of 92% are achieved at low SNR.

关键词： radar cross-sections Bayes methods Gaussian noise aerospace computing radar cross-section RCS control engineering computing data augmentation optimal augmentation hyperparameters optimisation radar sensing all-weather drone surveillance convolutional neural networks radar signal processing convolutional neural nets signal to noise ratio radar receivers neural net architecture surveillance data available classification accuracy autonomous aerial vehicles Bayesian optimisation SNR-dependent drone classification radar spectrograms signal classification network architectures drone-bird classification performance CNNs

来源：评论

学校读者我要写书评

暂无评论

A new scheme of target detection for pulse Doppler radar in interrupted sampling repeater jamming environment

引用

IET RADAR SONAR AND NAVIGATION 2022年第11期16卷 1836-1850页

作者： Zhang, Yu Jiu, Bo Peng, Xiaojun Liu, Hongwei Jiang, Wenqi Xidian Univ Natiotud Lab Radar Signal Proc Xian 710071 Peoples R China Rasearch Acad Rocket Xian Peoples R China

Research on the anti-jamming target detection for pulsed Doppler (PD) radar is intensively important to the normal work of radar in complicated and volatile electromagnetic environments. Generally, traditional anti-jamming target detection methods involve several stages, each one of these stages is based on a model. Due to the issues of poor flexibility caused by multi-stage processing and model mismatch caused by model-based methods, the detection performance will be severely decreased. Therefore, a new target detection scheme for PD radar in an Interrupted-Sampling Repeater Jamming (ISRJ) environment is proposed, which is a dual-driven method of model and data. This innovative solution first achieves energy accumulation on the Doppler channel by a model-driven method, then proposes a series of preprocessing methods to process radar signals to adapt to a data-driven convolutional neural Network (CNN) detector. Finally, a CNN detector structure is proposed. The effectiveness of this novel scheme is demonstrated by a series of performance and visualisation experiments.

关键词： model-driven method model-based methods preprocessing methods dual-driven method complicated environments radar signals multistage processing pulsed Doppler radar traditional anti-jamming target detection methods jamming radar signal processing volatile electromagnetic environments convolutional neural nets object detection Doppler radar pulse Doppler radar Interrupted-Sampling Repeater Jamming environment target detection scheme interrupted sampling repeater Doppler channel detection performance data-driven convolutional neural Network detector PD radar

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：