检索结果-南通市图书馆

DTCC:Multi-level dilated convolution with transformer for weakly-supervised crowd counting

Computational Visual Media 2023年第4期9卷 859-873页

作者： Zhuangzhuang Miao Yong Zhang Yuan Peng Haocheng Peng Baocai Yin Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial IntelligenceFaculty of Information TechnologyBeijing University of TechnologyBeijing 100124China Taiji Computer Corporation Ltd. China

Crowd counting provides an important foundation for public security and urban management.Due to the existence of small targets and large density variations in crowd images,crowd counting is a challenging task.Mainstream methods usually apply convolution neural networks(CNNs)to regress a density map,which requires annotations of individual persons and counts.Weakly-supervised methods can avoid detailed labeling and only require counts as annotations of images,but existing methods fail to achieve satisfactory performance because a global perspective field and multi-level information are usually ignored.We propose a weakly-supervised method,DTCC,which effectively combines multi-level dilated convolution and transformer methods to realize end-to-end crowd counting.Its main components include a recursive swin transformer and a multi-level dilated convolution regression head.The recursive swin transformer combines a pyramid visual transformer with a fine-tuned recursive pyramid structure to capture deep multi-level crowd features,including global features.The multi-level dilated convolution regression head includes multi-level dilated convolution and a linear regression head for the feature extraction module.This module can capture both low-and high-level features simultaneously to enhance the receptive field.In addition,two regression head fusion mechanisms realize dynamic and mean fusion counting.Experiments on four well-known benchmark crowd counting datasets(UCF_CC_50,ShanghaiTech,UCF_QNRF,and JHU-Crowd++)show that DTCC achieves results superior to other weakly-supervised methods and comparable to fully-supervised methods.

关键词： crowd counting transformer dilated convolution global perspective field pyramid

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Application of the dilated convolution based on Small Object Detection

The Application of the Dilated Convolution based on Small Ob...

引用

第三十九届中国控制会议

作者： Chengtao Cai Yue Wu Shuofeng Li The college of Automation Harbin Engineering University

Object detection is an important part of computer vision applications. It is widely used in robot navigation, intelligent video surveillance, industrial testing, aerospace and other fields. Full application of computer vision can reduce the consumption of human capital. At present, most deep learning-based methods focus on large objects, and we know that large objects always account a large part of an image. Therefore, these methods are not ideal for detecting small objects. The reason is that small objects carry very little information and their ability to express features are also weak. To solve this problem, we use our model and try to enlarge the resolution of feature maps by applying the dilated convolution. The results show that it improves the accuracy of detecting small objects.

关键词： Object detection Small objects dilated convolution

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Ship Detection in Remote Sensing Image based on Faster R-CNN with dilated convolution

Ship Detection in Remote Sensing Image based on Faster R-CNN...

引用

第三十九届中国控制会议

作者： Shuaihao Wei Huimin Chen Xiaojin Zhu Hesheng Zhang School of Mechatronic Engineering and Automation Shanghai University

Ship detection based on remote sensing image can provide effective assistance for maritime reconnaissance, port and fisheries management. This paper mainly presents an improved Faster R-CNN algorithm for ship detection with dilated convolution. Firstly, the image of remote sensing ship is preprocessed. This paper uses dark channel prior method to dehaze image and enhance dehazed image quality by grey world algorithm. Second, The Faster R-CNN is improved in ship detection.The dilated convolutional is introduced into Faster R-CNN to increases its feature extraction capability. Finally, ship detection software platform is built. The remote ship image preprocessing and ship detection network is integrated into an application software. The ship detection network can be trained end to end. Experimental results on the HRSC2016 datasets illustrated that the proposed presents a good performance for ship detection task.

关键词： dilated convolution Faster R-CNN Image preprocessing Ship detection

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

dilated convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2021年第6期30卷 1120-1130页

作者： ZHANG Zhe WANG Bilin YU Zhezhou LI Zhiyuan College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed regions of each interest target as pseudo-labels for training segmentation networks, which achieve inferior performance compared with the fully supervised setting.We propose a dilated convolutional pixels affinity network(DCPAN) to localize and expand the seed regions of objects to bridge this gap. Although introduced dilated convolutional units enable capture of additional location information of objects, it falsely highlighted true negative regions as dilated rate enlarge. To address this problem,we properly integrate dilated convolutional units with different dilated rates and self-attention mechanisms to obtain pixel affinity measure matrix for promoting classification network to generate high-quality object seed regions as pseudo-labels; thus, the performance of the segmentation network is boosted. Furthermore,although our approach seems simple, our method obtains a competitive performance, and experiments show that the performance of DCPAN outperforms other state-ofart approaches in weakly-supervised settings, which only use image-level labels on the Pascal VOC 2012 dataset.

关键词： Weakly supervised Semantic segmentation convolutional neural networks dilated convolution Self-attention mechanism

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network

引用

Chinese Journal of Electronics 2023年第5期32卷 941-954页

作者： ZHANG Changfan HUANG Congcong HE Jing College of Railway Transportation Hunan University of Technology

Surface defect recognition of train wheel-set is crucial for the safe operation of the train wheel system. However, due to the diversity and complexity of such defects, it is difficult for existing algorithms to make rapid and accurate recognitions. To solve this problem, an improved spiking neural network(SNN) based defect recognition method for train wheelset tread is proposed.Specifically, a hybrid convolutional encoding module is first designed to conduct image-to-spike conversion and to create multi-scale sparse representations of the features.Second, a residual spiking convolutional neural network is implemented to extract spiking features optimally, and a multi-scale structure is adopted to enhance the SNN’s ability to handle details. A channel attention module is then incorporated to re-calibrate the weights of four-dimensional spiking feature maps. Finally, effective spiking features are obtained according to the recognition decisions which are made. The experimental results showed that the proposed method improved the accuracy of defect recognition. The recognition time of a single image is only 0.0195 s on average. The overall performance of the proposed method is noticeably superior to current mainstream algorithms.

关键词： Defects recognition Spiking neural network Spike train encoding dilated convolution Channel attention module Wheelset tread

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Deep Learning Approach for Crowd Counting in Highly Congested Scene

引用

Computers, Materials & Continua 2022年第12期73卷 5825-5844页

作者： Akbar Khan Kushsairy Abdul Kadir Jawad Ali Shah Waleed Albattah Muhammad Saeed Haidawati Nasir Megat Norulazmi Megat Mohamed Noor Muhammad Haris Kaka Khel Electrical Section Universiti Kuala Lumpur British Malaysian InstituteSelangor53100Malaysia Department of Electrical Engineering International Islamic UniversityIslamabad44000Pakistan Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Electrical Engineering National University of Computer and Emerging SciencesIslamabad44000Pakistan Computer Engineering Technology Section Universiti Kuala Lumpur Malaysian Institute of Information TechnologyKuala Lumpur50250Malaysia

With the rapid progress of deep convolutional neural networks,several applications of crowd counting have been proposed and explored in the literature.In congested scene monitoring,a variety of crowd density estimating approaches has been developed.The understanding of highly congested scenes for crowd counting during Muslim gatherings of Hajj and Umrah is a challenging task,as a large number of individuals stand nearby and,it is hard for detection techniques to recognize them,as the crowd can vary from low density to high density.To deal with such highly congested scenes,we have proposed the Congested Scene Crowd Counting Network(CSCC-Net)using VGG-16 as a core network with its first ten layers due to its strong and robust transfer learning rate.A hole dilated convolutional neural network is used at the back end to widen the relevant field to extract a large range of information from the image without losing its original resolution.The dilated convolution neural network is mainly chosen to expand the kernel size without changing other parameters.Moreover,several loss functions have been applied to strengthen the evaluation accuracy of the model.Finally,the entire experiments have been evaluated using prominent data sets namely,ShanghaiTech parts A,B,UCF_CC_50,and UCF_QNRF.Our model has achieved remarkable results i.e.,68.0 and 9.0 MAE on ShanghaiTech parts A,B,199.1 MAE on UCF_CC_50,and 99.8 on UCF_QNRF data sets respectively.

关键词： Deep learning congested scene crowd counting fully convolutional neural network dilated convolution

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Semantic segmentation for remote sensing images based on an AD-HRNet model

引用

International Journal of Digital Earth 2022年第1期15卷 2376-2399页

作者： Xue Yang Xiang Fan Mingjun Peng Qingfeng Guan Luliang Tang School of Geography and Information Engineering China University of GeosciencesWuhanPeople’s Republic of China Wuhan Geomatics Institute WuhanPeople’s Republic of China State Key Laboratory of Information Engineering in Surveying Mappingand Remote SensingWuhan UniversityWuhanPeople’s Republic of China

Semantic segmentation for remote sensing images faces challenges of unbalanced category weight,rich context causing difficulties of recognition,blurred boundaries of multi-scale objects,and so on.To address these problems,we propose a new model by combining HRNet with attention mechanisms and dilated convolution,denoted as:AD-HRNet for the semantic segmentation of remote sensing images.In the framework of AD-HRNet,we obtained the weight value of each category based on an improved weighted cross-entropy function by introducing the median frequency balance method to solve the issue of class weight imbalance.The Shuffle-CBAM module with channel attention and spatial attention in AD-HRNet framework was applied to extract more global context information of images through slightly increasing the amount of computation.To address the problem of blurred boundaries caused by multi-scale object segmentation and edge segmentation,we developed an MDC-DUC module in AD-HRNet framework to capture the context information of multi-scale objects and the edge information of many irregular objects.Taking Postdam,Vaihingen,and SAMA-VTOL datasets as materials,we verified the performance of AD-HRNet by comparing with eight typical semantic segmentation models.Experimental results shown that AD-HRNet increases the mIoUs to 75.59%and 71.58%based on the Postdam and Vaihingen datasets,respectively.

关键词： Semantic segmentation convolutional neural networks dilated convolution attention mechanism remote sensing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Towards understanding residual and dilated dense neural networks via convolutional sparse coding

引用

National Science Review 2021年第3期8卷 127-139页

作者： Zhiyang Zhang Shihua Zhang National Center for Mathematics and Interdisciplinary Sciences Center for Excellence in Mathematical Science Key Laboratory of Random Complex Structures and Data ScienceAcademy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences Center for Excellence in Animal Evolution and Genetics Chinese Academy of Sciences Key Laboratory of Systems Biology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences

convolutional neural network(CNN) and its variants have led to many state-of-the-art results in various fields.However,a clear theoretical understanding of such networks is still lacking.Recently,a multilayer convolutional sparse coding(ML-CSC) model has been proposed and proved to equal such simply stacked networks(plain networks).Here,we consider the initialization,the dictionary design and the number of iterations to be factors in each layer that greatly affect the performance of the ML-CSC model.Inspired by these considerations,we propose two novel multilayer models:the residual convolutional sparse coding(Res-CSC) model and the mixed-scale dense convolutional sparse coding(MSD-CSC) model.They are closely related to the residual neural network(ResNet) and the mixed-scale(dilated) dense neural network(MSDNet),respectively.Mathematically,we derive the skip connection in the ResNet as a special case of a new forward propagation rule for the ML-CSC model.We also find a theoretical interpretation of dilated convolution and dense connection in the MSDNet by analyzing the MSD-CSC model,which gives a clear mathematical understanding of each.We implement the iterative soft thresholding algorithm and its fast version to solve the Res-CSC and MSD-CSC models.The unfolding operation can be employed for further improvement.Finally,extensive numerical experiments and comparison with competing methods demonstrate their effectiveness.

关键词： convolutional neural network convolutional sparse coding residual neural network mixed-scale dense neural network dilated convolution dense connection

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Automatic Detection of Weld Defects in Pressure Vessel X-Ray Image Based on CNN

引用

Wuhan University Journal of Natural Sciences 2022年第6期27卷 489-498页

作者： XIAO Wenkai FENG Xiang NAN Shuiyu ZHANG Linlin Department of Computer Science and Engineering.East China University of Science and Technology Shanghai 200237China Shanghai Engineering Research Center of Smart Energy Shanghai 201103China Shanghai Aino Industrial Technology CO..LTD.Shanghai 201612 China

The visual automatic detection method based on artificial intelligence has attracted more and more attention. In order to improve the performance of weld nondestructive defect detection,we propose DRepDet(dilated RepPoints Detector). First, we analyze the weld defect dataset in detail and summarize the distribution characteristics of weld defect data, that is, the defect scale is very different and the aspect ratio distribution range is large. Second, according to the distribution characteristics of defect data, we design DResBlock module, and introduce dilated convolution with different dilated rates in the process of feature extraction to expand the receptive field and improve the detection performance of large-scale defects. Based on DResBlock and anchor-free detection framework RepPoints, we design DRepDet. Extensive experiments show that our proposed detector can detect 7 types of defects. When using combined dilated rate convolution network in detection, the AP50 and Recall50 of big defects are improved by 3.1% and 3.3% respectively, while the performance of small defects is not affected, almost the same or slightly improved. The final performance of the whole network is improved a large margin,with 6% AP50 and 4.2% Recall50 compared with Cascade RCNN and 1.4% AP50 and 2.9% Recall50 compared with RepPoints.

关键词： nondestructive testing depth learning weld defect detection convolutional neural networks dilated convolution

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Spatial-temporal Dynamic Forecasting of EVs Charging Load Based on DCC-2D

引用

Chinese Journal of Electrical Engineering 2022年第1期8卷 53-62页

作者： Shurong Peng Heng Zhang Yunhao Yang Bin Li Sheng Su Shijun Huang Guodong Zheng School of Electrical&Information Engineering Changsha University of Science&TechnologyChangsha 410114China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China

The charging load of electric vehicles(EVs)has a strong spatiotemporal randomness.Predicting the dynamic spatiotemporal distribution of the charging load of EVs is of great significance for the grid to cope with the access of large-scale EVs.Existing studies lack a prediction model that can accurately describe the dual dynamic changes of EVs charging the load time and space.Therefore,a spatial-temporal dynamic load forecasting model,dilated causal convolution-2D neural network(DCC-2D),is proposed.First,a hole factor is added to the time dimension of the three-dimensional convolutional convolution kernel to form a two-dimensional hole convolution layer so that the model can learn the spatial dimension information.The entire network is then formed by stacking the layers,ensuring that the network can accept long-term historical input,enabling the model to learn time dimension information.The model is simulated with the actual data of the charging pile load in a certain area and compared with the ConvLSTM model.The results prove the validity of the proposed prediction model.

关键词： Time and space dynamic prediction dilated convolution charging load convolutional neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：