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

2,004 篇 会议
27 册 图书
9 篇 期刊文献

馆藏范围

2,040 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,276 篇 工学
- 602 篇 生物医学工程（可授...
- 425 篇 计算机科学与技术...
- 388 篇 软件工程
- 377 篇 电气工程
- 349 篇 机械工程
- 251 篇 信息与通信工程
- 186 篇 生物工程
- 179 篇 光学工程
- 115 篇 电子科学与技术（可...
- 72 篇 控制科学与工程
- 69 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 27 篇 安全科学与工程
- 23 篇 土木工程
- 22 篇 建筑学
- 16 篇 力学（可授工学、理...
- 16 篇 材料科学与工程（可...
461 篇 理学
- 196 篇 数学
- 186 篇 物理学
- 183 篇 生物学
- 66 篇 统计学（可授理学、...
- 62 篇 化学
- 24 篇 系统科学
407 篇 医学
- 403 篇 临床医学
- 197 篇 基础医学(可授医学...
- 113 篇 药学(可授医学、理...
- 35 篇 公共卫生与预防医...
113 篇 管理学
- 73 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 19 篇 工商管理
16 篇 法学
10 篇 经济学
9 篇 农学
4 篇 艺术学
3 篇 教育学
3 篇 军事学
2 篇 文学

主题

179 篇 feature extracti...
130 篇 image segmentati...
124 篇 signal processin...
93 篇 training
89 篇 informatics
87 篇 signal processin...
70 篇 image reconstruc...
69 篇 biomedical imagi...
66 篇 accuracy
51 篇 biomedical engin...
49 篇 image color anal...
48 篇 deep learning
48 篇 image edge detec...
47 篇 visualization
46 篇 convolution
44 篇 electroencephalo...
43 篇 support vector m...
42 篇 mathematical mod...
39 篇 biological syste...
37 篇 three-dimensiona...

机构

22 篇 school of inform...
20 篇 beijing-dublin i...
19 篇 school of electr...
19 篇 school of biomed...
18 篇 school of commun...
18 篇 school of electr...
18 篇 the adapt sfi re...
14 篇 lepu medical ele...
14 篇 school of contro...
13 篇 school of comput...
13 篇 school of inform...
12 篇 shanghai key lab...
11 篇 suzhou institute...
11 篇 school of comput...
10 篇 school of comput...
9 篇 school of comput...
9 篇 school of commun...
9 篇 school of biomed...
9 篇 school of intern...
9 篇 school of inform...

作者

21 篇 li jin
19 篇 ke li
18 篇 wang jun
17 篇 chen xiang
16 篇 li qingli
15 篇 li ke
15 篇 jin li
14 篇 xiang chen
13 篇 sun jinping
13 篇 shan liu
12 篇 jun wang
12 篇 liu zhi
10 篇 zhou mei
10 篇 dev soumyabrata
10 篇 qingli li
9 篇 diao shengxi
9 篇 soumyabrata dev
8 篇 yen-wei chen
8 篇 zhenyu zhang
8 篇 jin hua

语言

1,880 篇 英文
156 篇 其他
8 篇 中文
1 篇 德文

检索条件"任意字段=International Congress on Image and Signal Processing, BioMedical Engineering and Informatics"

共 2040 条记录，以下是1481-1490 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：

Small fire smoke region location and recognition in satellite image 9

Small fire smoke region location and recognition in satellit...

引用

9th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2016

作者： Miao, Sheng Hu, Kunrong Gao, Hao Wang, Xiaorui Southwest Forestry University Kunming China Key Laboratory for the Structure and Evolution of Celestial Objects Chinese Academy of Sciences Kunming China Radio Astronomy Research Group Yunnan Observatory of Chinese Academy of Science Kunming China

ISBN: (纸本)9781509037100

Since ancient times, forest fires are an important threat to human beings, with the development of satellite technology, forest fires can be constantly monitored by satellite. But face to number of satellite pictures, its hard to detect fire location, especially the fire initial stage. An sub-region detection method has been proposed, this method supply fast partition domain detection method using information entropy, fast detect each sub-region whether there is smoke feature or not. Due to the satellite image has large region, our method first segment the image and then detect the smoke feature in each sub-region using information entropy. More than 50 pictures has been used to test this methods, shows this algorithm the effectiveness of small range fire detection. © 2016 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

An Indoor Positioning Method Based on Wireless signal and image 9

An Indoor Positioning Method Based on Wireless Signal and Im...

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Jiao, Jichao Li, Fei Deng, Zhongliang Liu, Wen Beijing Univ Posts & Telecommun Lab Intelligent Commun Nav & Micro Nanosyst Beijing 100876 Peoples R China

ISBN: (纸本)9781509037100

In this paper, we propose a novel smartphone-based indoor localization algorithm by deeply combining wireless signals and images, which leads to improving the localization performance. Although the measured signals are polluted by the noise, we demonstrate that the combination of the image and wireless data dramatically improves the indoor positioning accuracy. Different with common wireless-based indoor positioning methods, the wireless signals that received in a certain time are transformed into frequency domain, and an image named W-image is created by using our proposed approach. Then, SIFT features that are extracted from the W-image is deeply combined with the LBP features that are extracted from the smartphone camera-based images. Moreover, the hybrid features from the smartphone camera images and images of reference database are matched which are used to determine correspondences indoor positioning points. In order to reduce the computation complexity of our proposed method, the wireless signals are illustrated to estimate the coarse positioning points for reducing the search space of image matching. By leveraging wireless signals and images, we are able to achieve almost a 0.86 in mean average precision and 57.65ms in mean average running time. The proposed algorithm can be applied to the smartphones that are integrated cameras to offer highaccuracy location-based services.

关键词： indoor positioning smartphone camera wireless signal visualizing feature matching

来源：评论

学校读者我要写书评

暂无评论

Automatic feature point detection using deep convolutional networks for quantitative evaluation of facial paralysis 9

Automatic feature point detection using deep convolutional n...

引用

9th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2016

作者： Yoshihara, Hiroki Seo, Masataka Ngo, Truc Hung Matsushiro, Naoki Chen, Yen-Wei College of Information Science and Engineering Ritsumeikan University Siga Japan Department of Otorhinolayngology Osaka Police Hospital Osaka Japan

ISBN: (纸本)9781509037100

Feature point detection is an important pre-processing step for quantitative evaluation of facial paralysis. Since the conventional methods such as active shape model (ASM) or active appearance model (AAM) are trained by using normal face and they are not possible to detect the feature points accurately for the face with paralysis. In this paper, we propose an automatic and accurate feature point detection method for quantitative evaluation of facial paralysis using deep convolutional neural networks (DCNN). The proposed method consists of two steps. We first use AAM for initial feature point detection. In the second step, a patch with the detected point at the center is used as an input of DCNN for refinement. Experiments demonstrated that the proposed method can significantly improve the detection accuracy of the conventional AAM. © 2016 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On the Typical Pulse Recognition Based on Support Vector Machine 9

On the Typical Pulse Recognition Based on Support Vector Mac...

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Li, Wanbing Sheng, Shangxiong Chou, Yongxin Xijing Univ Coll Mech Engn Xian Peoples R China Changshu Inst Technol Sch Elect & Automat Engn Changshu Peoples R China

ISBN: (纸本)9781509037100

The physiological and pathological information obtained by the single-point or complex multi-point pressure sensor is still less. In this paper, we adopt the pulse image sensor which can reflect the change of the pulse-taking skin surface particularly and comprehensively, we use the MM-3 pulse model (Group A) as the subjects produced by Shanghai University of Traditional Chinese Medicine to study the characteristic parameters in different pulse conditions. Through the area changes from the pulse dynamic image to get the pulse waveform, and extract the frequency characteristic and pulse frequency value, at the same time extract the pulse length and pulse width from the three-dimensional reconstruction of the frame at the maximum amplitude. Finally, Support Vector Machine (SVM) are used to recognize the different pulse conditions, and to find out the features which can characterize the normal pulse, the slippery pulse, the slow pulse and the soft pulse. Experimental results show that the SVM is used in four kinds of pulse condition recognition the rate can reach 90% or more.

关键词： Pulse image Pulse characteristics SVM Pulse recognition

来源：评论

学校读者我要写书评

暂无评论

An Improved Feature Fusion Algorithm for image Retrieval 9

An Improved Feature Fusion Algorithm for Image Retrieval

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Che, Shilin Chen, Dongfang Wang, Xiaofeng Wuhan Univ Sci & Technol Coll Comp Sci & Technol Wuhan Peoples R China Hubei Prov Key Lab Intelligent Informat Proc & Re Wuhan Peoples R China

ISBN: (纸本)9781509037100

Single feature extract method for image retrieval usually cannot get good results and it is hard to find a stable fusion method when across image datasets because the image descriptors usually describe image from single aspect. For this pragmatic issue, an improved FCTH-BoVW feature fusion algorithm called robust FCTH-BoVW is proposed in this paper. Traditional feature fusion methods almost use liner weight method, but this method will be easily affected by the weights, and not easy to find the optimal weights. In this paper, FCTH feature is used as the global feature and BoVW feature as the local feature, and use k-reciprocal nearest neighbors method to fuse them. FCTH is an efficient descriptor and contains both color and texture information, in order to emphasize the center area as main region of interest, an annular weight method is proposed to improve the global feature. A soft assignment method is adopted to quantize the visual words for the improvement of the local feature. This method enhances the description ability of both global and local features. We find those improvements are quite practical, the results show that this fused method gets a higher retrieval precision, and we also find it is a stable image retrieval method for varieties of image datasets.

关键词： image retrieval FCTH BoVW feature fusion k-reciprocal nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

All-in-focus image Reconstruction with Depth Sensing 9

All-in-focus Image Reconstruction with Depth Sensing

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Sui, ZHong-shan Li, Jun-shan Fan, Jing-bo Ren, Xin-bo Li, Yan Liu, Ya-li Rocket Force Univ Engn Dept Informat Engn Xian 710025 Peoples R China Shanluo Coll Econ & Management Acad Shangluo 726000 Peoples R China

ISBN: (纸本)9781509037100

In order to reconstruct the all-in-focus image from a conventional camera, a spatially-varying defocus deblurring approach based on blur map and TV/L2 regularization was proposed. Firstly, lenticular defocus model was studied and analyzed, and the principle, characteristic and applicability of disk defocus model and Gaussian defocus model were generalized;Secondly, we modified the local contrast prior using edge properties, and combined it with the gradient of blurry edge to gain blur map, in addition, in order to decrease the noise of blur map and ambiguous edges, a guided filtering approach was also adopted to gain a better blur map;Finally, TV/L2 regularization method solved by an augmented Lagrangian method was employed to deblur the defocus image. The all-in-focus image is obtained using scale selection and image reconstruction. The experimental results based on both synthesized images and real images showed that the proposed approach can gain excellent all-in-focus images and the performance outperforms the state-of-theart space-invariant methods and spatially-varying methods for defocus deblurring, and the all-in-focus images show a better visual effect.

关键词： all-in-focus image reconstruction depth of field Gaussian defocus model TV/L2 regularization augmented Lagrangian method

来源：评论

学校读者我要写书评

暂无评论

A Modified Approach for Thermal Distribution Monitoring of the Container Data Center by Thermal image Registration 9

A Modified Approach for Thermal Distribution Monitoring of t...

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Liu, Hang Xie, Ting Ran, Jian Gao, Shan Dalian Univ Technol Sch Elect Sci & Technol Dalian Peoples R China Dalian Univ Technol Network & Informat Ctr Dalian Peoples R China

ISBN: (纸本)9781509037100

Data centers are extremely important facilities that contain core business information and applications, but the energy consumption is an inevitable issue, so the thermal distribution monitoring is critical for data centers reliable and stable operation. Thermal information enables monitoring and autonomic thermal management in large data centers. Recent approaches that employed a mobile robot or a thermal camera network can already collect the physical positions of hot spots. However, most of the features extracted from thermal images, such as shape and gradient, may be affected by changes in the position and direction of the thermal camera. In this paper, a thermal distribution monitoring method is proposed to extract the thermal features of a hot spot or a server in a container data center. In the first stage of our method, thermal and visual images are registered based on texture characteristics in images that are obtained in data centers. Then, the thermal distribution of each server is standardized. The features of the hot spot or server extracted from the standard distribution can diminish the impact of camera position and direction. The experimental results verified the efficient and the advantages of this method.

关键词： data center hot spots image registration thermal distribution monitoring

来源：评论

学校读者我要写书评

暂无评论

A waveform-agile unscented Kalman filter for radar target tracking 9

A waveform-agile unscented Kalman filter for radar target tr...

引用

9th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2016

作者： Wang, Bingbing Sun, Jinping Zhang, Xuwang Yang, Xiuwei School of Electronic and Information Engineering Beihang University Beijing China Automation Institute of Shandong Academy of Sciences Jinan China

ISBN: (纸本)9781509037100

This paper proposes a dynamic waveform selection algorithm for radar target tracking. Following the waveform auto-adaptive ideas in the classical control theory, the Cramer-Rao lower bound (CRLB) of the covariance of target range and range rate estimations is utilized to describe the statistic characteristics of the measurement noises in tracking. Then the relationship between waveform parameters and tracking performance is established. The CRLB of target estimations corresponding to a certain waveform is obtained through the ambiguity function. The unscented Kalman filter (UKF) is used as the tracker and a secondary UKF is used to predict the tracking MSE. Minimizing the tracking MSE is chosen as the criterion of the dynamic waveform selection. At every time step of tracking, optimal transmitted waveform parameters are selected to track the nonlinear 2D target. Simulation results show the algorithm can improve the tracking performance when target states and measurements are nonlinear. © 2016 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Model and Metric Choice of image Retrieval System Based on Deep Learning 9

Model and Metric Choice of Image Retrieval System Based on D...

引用

9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI)

作者： Wang, Lei Wang, Xili Shaanxi Normal Univ Sch Comp Sci Xian Peoples R China Shangluo Univ Ctr Network Shangluo Peoples R China

ISBN: (纸本)9781509037100

In the era of big data, Content-Based image Retrieval combined with deep learning technology gradually becomes the mainstream. This method can overcome some drawbacks of traditional CBIR, but at the same time there are still some problems to be solved, such as : The extracted feature dimension (generally more than 2000) is higher, which is not beneficial for efficient data storage and fast real-time query on a large scale;And the measurement method for feature matching is difficult to be determined, since the typical method based on distance is designed in the low dimension, but in high dimensional space curse of dimensionality can make those former methods may be no longer suitable. In this paper we discuss a fast efficient CBIR to improve the performace of image retrieval system, through contrasting different model and metric choices. Contrast experiments show that 4 kinds of distances (namely Euclidean Distance, Minkowski Distance, Cosine Distance, Pearson Correlation Distance) is more suitable for processing the similarity measurement on high-dimensional feature, and 5 kinds of models (namely vgg-m-128, vgg-m-1024, vgg-m-2048, vgg-verydeep-16, vgg-verydeep-19) have higher average query precision for image retrieval task.

关键词： deep learning convolutional neural network image retrieval

来源：评论

学校读者我要写书评

暂无评论

A local path planning algorithm under the variable planning size 9

A local path planning algorithm under the variable planning ...

引用

9th international congress on image and signal processing, biomedical engineering and informatics, CISP-BMEI 2016

作者： Wan, Teng Li, Ce Zhang, Yachao College of Electrical and Information Engineering Lanzhou University of Technology Lanzhou China

ISBN: (纸本)9781509037100

The research in the field of the localization and navigation of mobile robot is becoming more and more significant. Among them, the local real-time path planning for robot autonomous navigation in complex environment is particularly important. However, the current local path planning algorithms are all planning the local path in the same plan-scope. Sometimes, this situation leads to a waste of time and computing resources. Therefore, in this article, a new path planning method called the variable planning size (VPS) for robot in static workspace is presented. In this paper, the graph theory is the basic algorithm of path planning. In addition, the mobile robot using this algorithm could autonomous to decide the planning scope according to the complexity of the surrounding environment. Therefore, in a complex environment, the robot is more efficient to find a local optimal path. As a result, the VPS path planning algorithm can plan out of the local optimal path preferably. © 2016 IEEE.

关键词： Mobile robots

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204页 << < 145 146 147 148 149 150 151 152 153 154 > >>

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：