检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics (ICCE)

作者： Heungmin Oh Minjung Lee Hyungtae Kim Joonki Paik Image Processing and Intelligent System Laboratory Chung-Ang University Seoul Korea

ISBN: (数字)9781728151861

ISBN: (纸本)9781728151878

Recently, surveillance cameras are ubiquitous for both real-time monitoring and recording important moments. Temporarily seamless surveillance using multiple cameras requires increasing amount of human efforts and enormous size of storage. The use of dynamic cameras further requires advanced computer vision algorithms, and is another challenge for intelligent visual surveillance. To solve those problems, we present an enhanced metadata extraction method for robust object search and a person re-identification. More specifically, the proposed method accurately extracts an object region using a modified DeepLab version 3, and then extracts metadata including representative color, size, aspect ratio, and moving trajectory of the object. The proposed metadata extraction method can be applied to a wide range of surveillance systems such as search for missing children in a large public space and crowd monitoring system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coarse to Fine: Progressive and Multi-Task Learning for Salient Object Detection

Coarse to Fine: Progressive and Multi-Task Learning for Sali...

引用

International Conference on Pattern Recognition

作者： Donggoo Kang Sangwoo Park Joonki Paik Image Processing and Intelligent System Laboratory Chung-Ang University Seoul Korea

Most deep learning-based salient object detection (SOD) methods tried to manipulate the convolution block to effectively capture the context of object. In this paper, we propose a novel method, called progressive and mutl-task learning scheme, to extract the context of object by only manipulating the learning scheme without changing the network architecture. The progressive learning scheme is a method to grow the decoder progressively in the train phase. In other words, starting from easier low-resolution layers, it gradually adds high-resolution layers. Although the progressive learning successfully captures the context of object, its output boundary tends to be rough. To solve this problem, we also propose a multi-task learning (MTL) scheme that processes the object saliency map and contour in a single network jointly. The proposed MTL scheme trains the network in an edge-preserved direction through an auxiliary branch that learns contours. The proposed a learning scheme can be combined with other convolution block manipulation methods. Extensive experiments on five datasets show that the proposed method performs best compared with state-of-the-art methods in most cases.

关键词： Convolution Object detection Network architecture Decoding Pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Non-dyadic lens distortion correction and enhancement of fish-eye lens images

Non-dyadic lens distortion correction and enhancement of fis...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jinho Park Donggyun Kim Daehee Kim Joonki Paik Image Processing and Intelligent System Laboratory Chung-Ang University Seoul Korea

ISBN: (纸本)9781479975440

In this paper, a novel image enhancement method is presented for a fish-eye lens camera. In order to remove jagging and blur artifacts that are generated by a correction process of geometric lens distortion, the proposed method searches similar patches in a non-dyadic scale space. For further enhancing the artifact-removed image, a self-example-based image restoration is also used. Experimental results show that the proposed method can successfully remove not only geometric distortion of a fish-eye lens but also jagging and blur artifacts in the corrected image.

关键词： Lenses image enhancement Mathematical model Conferences Consumer electronics Imaging image restoration

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Generation Using Deep Local Features for Augmented and Mixed Reality Contents

Point Cloud Generation Using Deep Local Features for Augment...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Sohee Lim Minwoo Shin Joonki Paik Image Processing and Intelligent System Laboratory Chung-Ang University Seoul Korea

ISBN: (数字)9781728151861

ISBN: (纸本)9781728151878

With the commercialization of 5G network and the mounted of 3D sensor such as ToF on smartphones, augmented and mixed reality (AR/MR) technology has attracted increasing attention. AR/MR contents need 3D data in various models to interact with human users. However, creating a 3D model is a complicated and expensive process involving 3D acquisition, 3D reconstruction, and rendering with computer graphics techniques. To solve that problem, we use an autoencoder to extract local information. We then train the latent space in a generative adversarial network (GAN). The GAN takes local context from the latent variable, and then generates a point cloud of various robust shapes. The proposed method can generate a novel 3D model that can significantly save computational load to render AR/MR contents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-Activated 3D CNN and Feature Pyramid Network for Traffic Accident Detection

Pre-Activated 3D CNN and Feature Pyramid Network for Traffic...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Hyunwoo Kim Seokmok Park Joonki Paik Image Processing and Intelligent System Laboratory Chung-Ang University Seoul Korea

ISBN: (数字)9781728151861

ISBN: (纸本)9781728151878

In this paper, we present a novel traffic accident detection method using a spatio-temporal three-dimensional (3D) convolutional neural network. The proposed method consists of pre-activation ResNet and feature pyramid network (FPN) structure. To reduce computational load with preserving the detection accuracy, we propose interval input method. Experimental results show that the proposed network outperforms existing methods in the sense of both precision and recall measures.

关键词： Accidents Three-dimensional displays Feature extraction Residual neural networks Conferences Computer vision Control systems

来源：评论

学校读者我要写书评

暂无评论

The trading between virtual mobile operator and wireless service provider in the two-tier Femtocell network

The trading between virtual mobile operator and wireless ser...

引用

8th International Conference on Wireless Algorithms, systems, and Applications, WASA 2013

作者： Yang, Fan Yang, Bo Guan, Xinping Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Shanghai Jiao Tong University China

ISBN: (纸本)9783642397004

This paper considers the problem that the virtual mobile operator (VMO) buys services from the wireless service provider (WSP) to serve its users. When faced with poor indoor coverage or at the edge of marcocell, the WSP would ask nearby femto base stations (FBSs) to help serve the VMO. We focus on the interesting questions when the WSP prefers to ask help from FBSs and how WSP, VMO and FBSs adjust their strategies to maximize their profits. A two-stage Stackelberg game is built for the situation when the WSP serve the VMO by itself and a four-stage Stackelberg game is considered when the WSP rents FBSs by offering spectrum bands to FBSs. We firstly define the utility functions of VMO, WSP and FBSs to reflect their satisfaction and cost in participating into the game and then give the analysis based on the backward induction method. Meanwhile, the competition among FBSs when the WSP allocates spectrum bands for FBSs' help is formulated as a non-cooperative spectrum competition game (NSCG) and the existence and uniqueness of the Nash equilibrium in NSCG is proved. Simulation results of the two service modes show the WSP can obtain more profits through renting FBSs in poor coverage areas. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of NOMA-Based Cooperative Networks with Relay Selection

引用

China Communications 2020年第11期17卷 111-119页

作者： Ronglan Huang Dehuan Wan Fei Ji Hua Qing Jie Li Hua Yu Fangjiong Chen Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou UniversityWuzhou 543002China Guangdong University of Finance Guangzhou 510521China School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourcesGuangzhou510300China

Non-orthogonal multiple access(NOMA)technique is an expert on channel differences *** this paper,a dual-hop NOMA-based cooperative relaying network where a best relay is selected as an active node to accomplish the communication between a source and a destination is *** assume that both decode-and-forward(DF)and amplify-and-forward(AF)protocols are applied to the selected *** metrics that ergodic sum-rate and outage probability are investigated,and the closed-form expressions of the latter for DF and AF protocols are *** and simulation results are conducted to verify the validity of the theoretical analysis,in which we can see that the NOMA based DF relaying is better than the NOMA based AF relaying and other existing NOMA-based cooperative communication schemes.

关键词： non-orthogonal multiple access(NOMA) decode-and-forward(DF) amplify-and-forward(AF) relay selection ergodic sum-rate outage probability

来源：评论

学校读者我要写书评

暂无评论

Reaching Non-Negative Edge Consensus of Networked Dynamical systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2018年第9期48卷 2712-2722页

作者： Wang, Xiao Ling Su, Housheng Chen, Michael Z. Q. Wang, Xiao Fan Chen, Guanrong College of Automation Nanjing University of Posts and Telecommunications Nanjing China School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan China School of Automation Nanjing University of Science and Technology Nanjing China Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Department of Electronic Engineering City University of Hong Kong Hong Kong

In this paper, the problem of non-negative edge consensus of undirected networked linear time-invariant systems is addressed by associating each edge of the network with a state variable, for which a distributed algorithm is constructed. Sufficient conditions referring only to the number of edges are derived for non-negative edge consensus of the networked systems. Subsequently, the linear programming method and a low-gain feedback technique are introduced to simplify the design of the feedback gain matrix for achieving the non-negative edge consensus. It is found that the low-gain feedback technique has a good effect on the non-negative edge consensus of the networked systems subject to input saturation. Numerical simulations are presented to verify the effectiveness of the theoretical results.

关键词： Distributed algorithm line graph low-gain feedback networked system non-negative edge consensus

来源：评论

学校读者我要写书评

暂无评论

G-Strong Chain Recurrent Point And G-Chain Equivalent Point of Topological G-Conjugacy On Metric G-Space

G-Strong Chain Recurrent Point And G-Chain Equivalent Point ...

引用

2019虚拟现实与智能系统国际会议

作者： Ji Zhan-jiang Tu Jing-xian School of Data Science and Software Engineering Wuzhou University Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Guangxi Colleges and Universities Key Laboratory of Professional Software Technology Wuzhou University

ISBN: (纸本)9781728150505

In this paper,we study the dynamical properties of Gstrong chain recurrent point,G-chain point set and G-chain equivalent point of topological G-conjugacy on metric *** inference,we give the following conclusions that if let f:X→X and f:Y→Y be two continous map of metric G-space X and *** the map h:X→Y is a topogical G-conjugacy from f to f,then（1） h(SCR（f）)=SCR（f）;（2） h(S（x,f）)=S(h（x）,f);（3）h(CE（x,f）)=CE(h（x）,f).These results will enrich the theory of G-strong chain recurrent point,G-chain point and G-chain equivalent point of topological G-conjugacy on metric G-space

关键词： metric G-space topological G-conjugacy G-strong chain recurrent point G-chain point G-chain equivalent point

来源：评论

学校读者我要写书评

暂无评论

The research of the accessibility and transitivity of topological group

The research of the accessibility and transitivity of topolo...

引用

2020 International Conference on Virtual Reality and intelligent systems, ICVRIS 2020

作者： Zhan-Jiang, Ji Wei, Shi Wuzhou University School of Information and Electronic Engineering China Guangxi Colleges Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University China Guangxi Colleges China Wuzhou Vocational College China

ISBN: (纸本)9781728196367

The accessibility and transitivity have an important significance in terms of theory and application. The concept of the accessibility and transitivity are introduced in this paper. We study their dynamical properties. The following result are obtained: (l)Let (K , G ) be the hyperspace of (X , G ). Then ( X , G ) is accessible if and only if (K , G ) is accessible;(2) Let (K , G) be the hyperspace of (X , G). Then (X , G ) is transitive if and only if (K , G ) is transitive. These results enriched the theory of the accessibility and transitivity of topological group. © 2020 IEEE.

关键词： Accessibility Topological group Transitivity

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：