检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

848 篇 会议
120 篇 期刊文献

馆藏范围

968 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

621 篇 工学
- 331 篇 信息与通信工程
- 329 篇 计算机科学与技术...
- 254 篇 软件工程
- 112 篇 电子科学与技术（可...
- 89 篇 控制科学与工程
- 59 篇 光学工程
- 59 篇 生物工程
- 55 篇 机械工程
- 53 篇 仪器科学与技术
- 53 篇 航空宇航科学与技...
- 50 篇 电气工程
- 46 篇 化学工程与技术
- 31 篇 生物医学工程（可授...
- 24 篇 建筑学
- 24 篇 土木工程
- 20 篇 动力工程及工程热...
- 18 篇 安全科学与工程
- 16 篇 交通运输工程
- 14 篇 环境科学与工程（可...
323 篇 理学
- 194 篇 数学
- 65 篇 生物学
- 58 篇 物理学
- 50 篇 统计学（可授理学、...
- 47 篇 化学
- 21 篇 系统科学
- 15 篇 大气科学
116 篇 管理学
- 64 篇 管理科学与工程(可...
- 55 篇 图书情报与档案管...
- 20 篇 工商管理
19 篇 医学
- 15 篇 基础医学(可授医学...
18 篇 农学
11 篇 法学
11 篇 军事学
9 篇 教育学
7 篇 经济学
2 篇 艺术学
1 篇 文学

主题

91 篇 synthetic apertu...
52 篇 feature extracti...
30 篇 training
25 篇 accuracy
23 篇 object detection
22 篇 radar
22 篇 radar imaging
20 篇 image segmentati...
20 篇 convolution
17 篇 semantics
17 篇 field programmab...
15 篇 radar polarimetr...
15 篇 computational mo...
15 篇 target recogniti...
15 篇 convolutional ne...
13 篇 target tracking
13 篇 real-time system...
13 篇 remote sensing
11 篇 support vector m...
11 篇 deep learning

机构

215 篇 beijing key labo...
196 篇 hubei province k...
147 篇 beijing key labo...
132 篇 school of comput...
114 篇 college of compu...
72 篇 radar research l...
66 篇 hubei province k...
64 篇 school of inform...
50 篇 beijing institut...
36 篇 advanced technol...
33 篇 beijing key labo...
25 篇 chongqing innova...
21 篇 radar technology...
19 篇 wuhan university...
19 篇 radar research l...
17 篇 hubei key labora...
17 篇 beijing key labo...
17 篇 school of electr...
16 篇 school of comput...
15 篇 hubei province k...

作者

52 篇 ding zegang
40 篇 chen he
39 篇 he chen
35 篇 chen liang
33 篇 hu cheng
30 篇 wang yanhua
28 篇 liang chen
26 篇 xie yizhuang
26 篇 zegang ding
25 篇 li yang
25 篇 zeng tao
24 篇 cheng hu
24 篇 tao zeng
22 篇 xiaolong zhang
22 篇 linbo tang
21 篇 zhang xiaolong
21 篇 tang linbo
20 篇 wang rui
19 篇 teng long
19 篇 liu jun

语言

939 篇 英文
21 篇 其他
8 篇 中文

检索条件"机构=Key Laboratory of Embedded Real-Time Information Processing Technology"

共 968 条记录，以下是491-500 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Multi-level feature fusion model-based real-time person re-identification for forensics

Multi-level feature fusion model-based real-time person re-i...

引用

作者： Wang, Shiqin Xu, Xin Liu, Lei Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China Artificial Intelligence Institute Wuhan University of Science and Technology Wuhan430065 China Institute of Systems Science National University of Singapore Singapore119615 Singapore

Person forensics aims to retrieve the specified person across non-overlapping cameras. It is difficult owing to the appearance variations caused by occlusion, human pose change, background clutter, illumination variation, etc. In this scenario, current models face great challenges in extracting effective features. Recent deep learning models mainly focus on extracting representative deep features to cope with appearance variations, while handcrafted features are not fully explored. In this paper, a multi-level feature fusion model (MFFM) is designed to combine both deep features and handcrafted features in real time. MFFM is first utilized to describe person appearance. Then, local binary pattern (LBP) and histogram of oriented gradient (HOG) are extracted to cope with geometric change and illumination variance. Using LBP and HOG, 11.89% on the CUHK03, 15.30% on the Market-1501 and 8.25% on the VIPeR top-1 recognition accuracy improvement for the proposed method are achieved with only 9.66%, 4.90%, and 7.59% extra processing time. Experimental results indicate MFFM can achieve the best performance compared to the state-of-the-art models on the Market1501, CUHK03, and VIPeR datasets. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Moving target detection based on Circular Video SAR

Moving target detection based on Circular Video SAR

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Hongshuo Wang Baojun Zhao Xingsha Yang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Video Synthetic Aperture Radar (Video-SAR) achieves radar video observation by continuously monitoring a certain area to form continuous image data of the target, and it plays an important role in civil and military fields. The SAR image of the moving target is defocused and deviates from its true position, but in its real position, a shadow area similar to the target size is generated. In this paper, the shadow area is used to detect the moving target. Firstly, the image sequence is de-noised by wavelet analysis. Then the maximum threshold segmentation of Tsallis gray entropy is performed. The SIFT and FAST algorithms are used to detect and match the corners of each frame. At the same time, the RANSAC algorithm is used to optimize the pairing results to complete the image registration. Finally, the moving target is extracted by the three-frame difference method, and the result is marked to the corresponding position of the original image. Based on the Video SAR segment published by Sandia Labs in the United States, the detection of the largest moving vehicle in the video is realized, and the effectiveness and anti-interference of the proposed algorithm is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Abrupt Motion Change Radar Target Detection Based on Generalized Radon-Fourier Transform

A Novel Method for Abrupt Motion Change Radar Target Detecti...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Siyuan Liu Zegang Ding Xu Zhou Pengjie You Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Long-time integration is an effective method to improve the signal-to-noise ratio (SNR) and detection performance of highly maneuvering targets. The existing methods for long-time integration mainly focus on detecting targets with high-order motion under fixed model, losing sight of the possibility that targets may have an abrupt motion change at an unknown instant. Therefore, this paper proposes a novel long-time integration method for highly maneuvering target with abrupt change model (ACM) based on generalized Radon-Fourier transform (GRFT), which could coherently integrate the target echoes before and after ACM and obtain the optimal coherent integration gain. The simulation and experiment results show that the proposed method can detect the ACM target under the condition of extremely low SNR and improve the detection performance compared with the fixed model GRFT.

关键词： abrupt motion change target detection highly maneuvering target detection long-time coherent integration generalized Radon-Fourier transform (GRFT)

来源：评论

学校读者我要写书评

暂无评论

A SAR target recognition method with frequency and spatial domain enhancement

A SAR target recognition method with frequency and spatial d...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Zhiru Wang Liang Chen Baogui Qi Guanqun Wang Hao Shi Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Synthetic aperture radar (SAR) image target recognition is a hot issue in remote sensing image application. High accuracy SAR target recognition is truly important in both military and civilian fields. Recently, convolutional neural networks (CNNs) have played an important role in the field of SAR image target recognition, however, most of the existing networks incurs some additional problems such as ignoring the influence of speckle noise on the target recognition process, so the recognition accuracy is low. To cope with these problems, this paper proposes a novel SAR image target recognition method based on CNN with frequency and spatial domain enhancement. First, the image is transformed by Gabor feature descriptor in different frequency directions to generate a plurality of feature maps. Then, the image is spatially enhanced using a Laplace transform. The feature maps which obtained by the frequency and spatial domain enhancement together with the original image are used as the network input. Finally, the improved deep residual network (ResNet) is used to complete the target recognition task. Experimental results demonstrate that the proposed method achieves a state-of-the-art accuracy on the MSTAR dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Binary Separable Convolutional: An Efficient Fast Image Classification Method

Binary Separable Convolutional: An Efficient Fast Image Clas...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Donglin Jing Linbo Tang Yu Pan Wei Tang Shichao Zhou Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

The training and running of neural network require large computational space and memory space, which makes it difficult to deploy on a resource-constrained embedded sys-tems. To address this limitation, we introduce a two-stage pipeline: Depth separable, local binary. Our method is divided into two steps. Firstly, a deep separable convolution is applied to each input channel. Then, point-by-point convolution is applied to the feature map obtained by the filter. In the second step, we use local binarization method to initialize the filter corresponding to the input channel into sparse binary. In network training, the sparse binary filter remains fixed and only needs to train convolution of 1×1 size. Our experimental results show that, on the basis of approximate accuracy with the original network, we have reduced the number of convolution parameters by 9x to 10x, and reduced the training time and testing time to by 2x. Our compression method helps to deploy complex neural networks on resource-constrained embedded platform.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weighted Anomaly Detection Algorithm Based on Local Density

Weighted Anomaly Detection Algorithm Based on Local Density

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yibing Tian Linbo Tang Zhen Li Yun Huang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Anomaly detection for hyperspectral imagery (HSI) has drawn a lot of attention lately. In the past decades, several methods for detecting anomalies in HSI have been developed. The Reed-Xiaoli detector (RXD) is one of the most widely used methods for anomaly detection. However, RXD assumes that background follow the Gaussian distribution, not always conformed to the real case. In order to solve this problem, we improve the RX anomaly detection algorithm by weighting changes of background. First, the concentric double-window model is utilized to obtain the local densities of each background pixels. Then, the local densities are applied to weight background mean and covariance matrix to reduce the influence of abnormal pixels in the background. The experimental results show that our method outperforms other approaches in anomaly detection.

关键词： hyperspectral imagery anomaly detection local RXD weighted covariance matrix anomaly detection hyperspectral imagery AKR1B10 gene variance covariance matrix Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Ground Target Automatic Recognition and Tracking in Complex Battlefield Environment

Ground Target Automatic Recognition and Tracking in Complex ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Chen Wu Linbo Tang Chenhui Duan Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

With the developments of science and the changes of modern warfare modes, the precise guidance and attack towards hostile targets in complex battlefield environments has extremely important military needs and research significance. However, the existing guidance mode is often constrained by factors such as battlefield background interference, target appearance variation and limited data links, which in turn affects tracking and strike performance. To this end, we present an integrated recognition and tracking scheme for the ground targets in complex battlefield environment. Specifically, with the missile-target distance information, we design an adaptive scale estimation scheme to tackle the aspect ratio variation during tracking. Furthermore, an efficient tracking monitoring index is advocated to judge the tracking condition as well as forecast the potential tracking failure. Once tracking failure is determined, a deep-learning based detection module is activated to re-detect the target as well as correct the tracking drift. In the strike stage of the mission, the key region of the hostile target would be identified and locked by the missile in order to maximize the attack effect. The proposed recognition and tracking scheme are tested upon extensive actual videos and achieved a tracking accuracy over 85%, which demonstrates its effectiveness as well as provides a novel solution for accurate and robust attack on enemy targets in a complex battlefield environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Crop Planting Area Classification From Remote Sensing Image Based on Deep Learning

Research on Crop Planting Area Classification From Remote Se...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Yun Huang Linbo Tang Donglin Jing Zhen Li Yibing Tian Shichao Zhou Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Remote sensing technology is widely used in agriculture monitoring because of the advantages of large-area simultaneous observation, low cost and dynamic monitoring of time and space. However, a manual visual interpretation method is often used to extract the information behind the remote sensing images, which is time and labor consuming. Moreover, handcraft features such as texture and structure of crop images are applied to classify crop planting area while these features are not robust. In order to reduce the cost and enhance the classification accuracy, we improved the state-of-the-art image semantic segmentation network SegNet in crop planting area classification which can speed up the convergence and reduce the model size largely with small gains in accuracy. The experiment result shows that the classification accuracy of the improved SegNet is slightly increased compared with SegNet, and the computational cost (FLOPs) of the improved SegNet is much less than SegNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Three-level Memory Access Architecture for FPGA-based real-time Remote Sensing Image processing System

Three-level Memory Access Architecture for FPGA-based Real-t...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Ning Zhang Xin Wei Lei Chen He Chen Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Recently, extensive convolutional neural network (CNN)-based methods have been used for real-time remote sensing image processing system. However, the huge storage requirement for model and input image bring a great challenge to hardware implement. In this paper, we propose a three-level memory access architecture for FPGA-based real-time remote sensing image processing system to meet the storage requirement. Moreover, in the proposed architecture, the computational throughput is well matched to the storage bandwidth, which improve the efficiency of arithmetic processing on the hardware platform. In the experiment, we applied the architecture to the hardware implementation of CNN, and implement on Xilinx ZYNQ xc7z035 platform. Our design is evaluated on a main part of the modified YOLOv2 framework [1]. The experimental results demonstrate that this design can access the off-chip memory efficiently, and can provide the required parameters and input data for the CNN on-chip pipeline processing.

关键词： Convolutional Neural Network FPGA Memory Access Image processing Field programmable gate arrays Image processing Storage requirements ARCHITECTURE Building construction three-level Hardware Platform Memory Memory Access

来源：评论

学校读者我要写书评

暂无评论

Ripple-Effect Analysis of Ontology Evolution Based on CK-Modes Algorithm

Ripple-Effect Analysis of Ontology Evolution Based on CK-Mod...

引用

International Conference on Industrial Engineering and Applications (ICIEA)

作者： Jianghe Gong Haidong Fu School of Computer Science and Technology Wuhan University of Science and Technology Key Laboratory of Intelligent Information Processing a nd Real-time Industrial System in Hubei Province Wuhan China

ISBN: (数字)9781728167855

ISBN: (纸本)9781728167862

Ontology users can accurately and comprehensively analyze the construction and evolution of the ontology by quantitatively analyzing the Ripple-Effect of the concepts or entities in the ontology, and provide a basis for the subsequent updating of the ontology. Existing methods quantify the Ripple-Effect in ontology, but do not consider the impact of ontology semantic structure on the Ripple-Effect. Existing methods preliminary quantify the Ripple-Effect in ontology, but do not consider the impact of ontology semantic structure on the Ripple-Effect. Aiming at the above problems, this paper proposes a method for analyzing the Ripple-Effect of ontology based on CK-Modes clustering. This method transforms the ontology into an ontology labeled attribute graph, cut the ontology according to the CK-Modes clustering algorithm, multiplied by different quantization coefficients according to different cutting modules, thus quantify the semantic from the perspective of semantic structure. Then, the transformation from the ontology to the semantic relation matrix is completed through the quantified semantic relations. Finally, the effect of each concept or entity is calculated by the improved Freud algorithm. The experimental result show, CK-Modes clustering-based ontology evolution Ripple-Effect analysis method can more accurately measure the concept or entity Ripple-Effect during the ontology evolution process. At the same time, the results of the measurement of the common nodes in different versions are more stable.

关键词： Ontologies Semantics Vegetation Forestry Clustering algorithms Quantization (signal) Current measurement

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共97页 << < 46 47 48 49 50 51 52 53 54 55 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：