检索结果-内蒙古大学图书馆

2015 IEEE International Conference on Computer and Communications(ICCC 2015)

作者： Yongtang Bao Yue Qi Min Liu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University

Chinese character component recognition plays an important role in Chinese character studying process. In this digital age, using the technology of computer science to analyzing Chinese character component, has a very important significance for the development of traditional culture. In this paper, we propose an optimal combined strategy based method for component recognition. First, we execute preprocessing for all input images. For each image, we process it with image binaryzation and homogenization. Second, we generate the candidate strokes from the results of preprocessing step. Third, we construct the search graph and calculate the possible solution for searching component. Finally, we describe the detailed algorithm for component recognition using optimal combined strategy. Our method can produce accurate Chinese character component recognition results.

关键词： optimal combined strategy component recognition Chinese character

来源：评论

学校读者我要写书评

暂无评论

Chinese Character Image Retrieval Based on Moment Invariants and Shape Context

Chinese Character Image Retrieval Based on Moment Invariants...

引用

2015 IEEE International Conference on Computer and Communications(ICCC 2015)

作者： Huanian Zhan Yue Qi State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University

this paper presents a retrieval method for the image of Chinese characters calligraphy. The precision and recall rate are main indicators to measure the quality of image retrieval algorithm. Starting from the two aspects, there are two parts in the process of image retrieve which is proposed in this paper. In this paper, carry out the retrieve with the Hu invariant moment matching algorithm, which is fast and efficient, but little of the accuracy. Then, execute trice retrieval with shape context algorithm taking the advantages of high level of accuracy and good robustness based on the result set of the first retrieval. Experiments show that the method referred in this paper is accurate and efficient.

关键词： calligraphy image retrieval moment invariants shape context matching

来源：评论

学校读者我要写书评

暂无评论

Video moving object detection based on region classification using three-order central moment

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2015年第5期27卷 832-840and846页

作者： Zheng, Jin Li, Bo Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

For the complex outdoor video surveillance, the existing moving object detection methods are difficult to overcome the background interference and accurately detect slow moving objects, as well as small objects simultaneously. These methods have the problem of low accuracy. This paper proposes a moving object detection method based on region classification using three-order central moment. For the different change characteristics of the different pixels in foreground region, cluster region, and background region, which imply the true motion, meaningless motion and background noise, three-order central moment is employed to build the corresponding relationship between the changes of pixel values and the classification of different regions. Therefore, the classifier based on three-order central moments is designed to adaptively classify the scene regions. Accordingly, the moving objects can be detected based on the region classification. The experimental results demonstrate that the proposed method can classify the different regions for outdoor video surveillance effectively. It also can overcome the background interference, e.g., branches swings and water fluctuates, and can detect slow objects and moving small objects accurately. ©, 2015, institute of Computing technology. All right reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Fast and compact dynamic data compression based on composite rigid body construction

引用

Science China(Information Sciences) 2014年第11期57卷 66-84页

作者： MA ZhiQiang WANG LiLi ZHANG BoNing KE Wei ZHAO QinPing State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University Macao Polytechnic Institute

3D dynamic datasets compression still poses two challenges. One is high time cost due to growing data and complex computation of compression algorithms. The other is low compression factor because of complex motions of dynamic scenes and unknown motion equations. In this paper, composite rigid body construction for fast and compact compression of 3D dynamic datasets is proposed to solve these two problems. It accelerates the compression with a fast rigid body decomposition based on disjoint union, and avoids serial searching, comparing and merging of the rigid body decomposition. To increase the compression factor,composite rigid body is introduced with consideration of motion consistency among rigid bodies at different time periods. The results of the experiments show that our algorithm compresses dynamic datasets quickly and achieves a high compression factor.

关键词： time-varying datasets dynamic datasets compression rigid body decomposition disjoint union composite rigid body construction

来源：评论

学校读者我要写书评

暂无评论

Interactive texture design and synthesis from mesh sketches

引用

Frontiers of Computer Science 2014年第2期8卷 330-341页

作者： Lili WANG Qinglin QI Yi CHEN Wei KE Aimin HAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing 100191 China Macao Polytechnic Institute Macao China

Geometry mesh introduces user control into tex- ture synthesis and editing, and brings more variations in the synthesized results. But still two problems related remain in need of better solutions. One problem is generating the meshes with desired size and pattern efficiently from easier user inputs. The other problem is improving the quality of synthesized results with mesh information. We present a new two-step texture design and synthesis method that addresses these two problems. Besides example texture, a small piece of mesh sketch drawn by hand or detected from example texture is input to our algorithm. And then a mesh synthesis method of geometry space is provided to avoid optimizations cell by cell. Distance and orientation features are introduced to im- prove the quality of mesh rasterization. Results show that with our method, users can design and synthesize textures from mesh sketches easily and interactively.

关键词： texture synthesis texture design feature-basedmethod structural texture

来源：评论

学校读者我要写书评

暂无评论

Cuboids detection in RGB-D images via Maximum Weighted Clique

Cuboids detection in RGB-D images via Maximum Weighted Cliqu...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Han Zhang Xiaowu Chen Yu Zhang Jia Li Qing Li Xiaogang Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang University International Research Institute for Multidisciplinary Science Beihang University Beijing Key Laboratory of Information Service Engineering Beijing Union University

Cuboid detection is an essential step for understanding 3D structure of scenes. As most of indoor scene cuboids are actually objects, we propose in this paper an object-based approach to detect 3D cuboids in indoor RGB-D images. The proposed approach is learning-free and can handle general object classes rather than a limited pre-defined category set. In our approach, we first apply an extended version of the CPMC framework to generate a set of segment hypotheses, and fit a set of cuboid candidates. Given the candidate set, we select several cuboids that can provide plausible interpretations of the images by solving a Maximum Weighted Clique (MWC) problem. With this formulation, a set of ranked mid-level representations of the input image is obtained, and are further re-ranked by Maximal Marginal Relevance (MMR) measure to improve their diversity. Experimental results on NYU-V2 dataset shows that our method significantly outperforms the state-of-the-art, and shows impressive results.

关键词： Three-dimensional displays Image segmentation Detectors Reliability Training Layout Cameras

来源：评论

学校读者我要写书评

暂无评论

Signal processing for Ka-band FMCW miniature SAR/GMTI system

Signal processing for Ka-band FMCW miniature SAR/GMTI system

引用

International Radar Symposium (IRS)

作者： Shichao Zheng Xiangyang Li Hui Wang Jianwei Niu Sisi Chen State Key Laboratory of Virtual Reality Technology and Systems ChinaUniversity Beijing China Shandong Institute of Aerospace Electronic Technology China Academy of Space Technology Yantai China Institute of Electronics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479978410

Frequency-Modulated Continuous Wave (FMCW) Synthetic Aperture Radar (SAR) systems are gaining more and more attention for earth observation with the compact size, light weight and low cost. A Ka-band FMCW miniature SAR/GMTI system is being developed by Shandong institute of Aerospace Electronic technology which aims at high resolution imaging and moving target indication. In order to validate the system design, signal processing algorithms including high resolution imaging and moving target indication are investigated. Furthermore, as multiple moving targets may exist in real scenes, a processing method for multiple moving targets is discussed in this paper. Simulation results validate the processing methods and the system design is also proved to be reasonable.

关键词： Azimuth Synthetic aperture radar Object detection Image resolution Interpolation System analysis and design Modulation

来源：评论

学校读者我要写书评

暂无评论

A spaceborne WAS-GMTI mode based on azimuth multi-channels

A spaceborne WAS-GMTI mode based on azimuth multi-channels

引用

IET International Radar Conference 2015

作者： Shichao Zheng Jianwei Niu Hui Wang Xiaolei Han State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Institute of Electronics Chinese Academy of Sciences Beijing China Beijing Institute of spacecraft system engineering Beijing China

In this paper, the spaceborne wide-area surveillance ground moving target indication (WAS-GMTI) mode is proposed. In the proposed mode, the requirement of detecting targets from different aspect angles with a high revisit rate can be achieved by modifying the TOPS mode which steers antenna in the azimuth direction. And a three-channel system is chosen to achieve fine GMTI performance. With the three-channel system, the detection of moving targets is realized by displaced phase center antenna (DPCA) technique and the motion parameter is estimated using the interferometric phase. The feasibility of the proposed mode as well as the performance of GMTI is validated by theoretical analysis and simulation experiments.

关键词： ground moving target indication (GMTI) synthetic aperture radar (SAR) terrain observation by progressive scans (TOPS) wide-area surveillance (WAS) Synthetic aperture radar MULTICHANNEL azimuth ground moving target indication ANTENNA antennae ASPECT ANGLE Theoretical analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-task rank learning for image quality assessment 40

Multi-task rank learning for image quality assessment

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Xu, Long Li, Jia Lin, Weisi Zhang, Yongbing Ma, Lin Fang, Yuming Zhang, Yun Yan, Yihua Key Laboratory of Solar Activity National Astronomical Observatories Chinese Academy of Sciences Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering BeihangUniversity Beijing China International Research Institute for Multidisciplinary Science Beihang University Beijing China Department of Computer Engineering Nanyang Technological University Singapore Graduate School at Shenzhen Tsinghua University Shenzhen China Huawei Noah's Ark Lab Hong Kong School of Information Technology Jiangxi University of Finance and Economics Nanchang China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9781467369978

In practice, multiple types of distortions are associated with an image quality degradation process. The existing machine learning (ML) based image quality assessment (IQA) approaches generally established a unified model for all distortion types, or each model is trained independently for each distortion type by using single-task learning, which lead to the poor generalization ability of the models as applied to practical image processing. There are often the underlying cross relatedness amongst these single-task learnings in IQA, which is ignored by the previous approaches. To solve this problem, we propose a multi-task learning framework to train IQA models simultaneously across individual tasks each of which concerns one distortion type. These relatedness can be therefore exploited to improve the generalization ability of IQA models from single-task learning. In addition, pairwise image quality rank instead of image quality rating is optimized in learning task. By mapping image quality rank to image quality rating, a novel no-reference (NR) IQA approach can be derived. The experimental results confirm that the proposed Multi-task Rank Learning based IQA (MRLIQ) approach is prominent among all state-of-the-art NR-IQA approaches. © 2015 IEEE.

关键词： image quality assessment machine learning MOS pairwise comparison Rank learning

来源：评论

学校读者我要写书评

暂无评论

Chaotic artificial bee colony approach to step planning of maintaining balance for quadruped robot

引用

International Journal of Intelligent Computing and Cybernetics 2014年第2期7卷 175-191页

作者： Qinan Luo Haibin Duan National Key Laboratory of Science and Technology on Aircraft Control Beihang UniversityBeijingPR China School of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and SystemsBeihang University(BUAA)BeijingChina

Purpose–Artificial bee colony(ABC)algorithm is a relatively new optimization method inspired by the herd behavior of honey bees,which shows quite *** purpose of this paper is to propose an improved ABC optimization algorithm based on chaos theory for solving the push recovery problem of a quadruped robot,which can tune the controller parameters based on its search *** simulation environment is adopted to implement the proposed scheme for the quadruped ***/methodology/approach–Maintaining balance is a rather complicated global optimum problem for a quadruped robot which is about seeking a foot contact point prevents itself from falling *** ensure the stability of the intelligent robot control system,the intelligent optimization method is *** proposed chaotic artificial bee colony(CABC)algorithm is based on basic ABC,and a chaotic mechanism is used to help the algorithm to jump out of the local optimum as well as finding the optimal *** implementation procedure of our proposed chaotic ABC approach is described in ***–The proposed CABC method is applied to a quadruped robot in ADAMS *** the CABC to implement,the quadruped robot can work smoothly under the interference.A comparison among the basic ABC and CABC is *** results verify a better trajectory tracking response can be achieved by the proposed CABC method after control parameters *** implications–The proposed CABC algorithm can be easily applied to practice and can steer the robot during walking,which will considerably increase the autonomy of the ***/value–The proposed CABC approach is interesting for the optimization of a control scheme for quadruped robot.A parameter training methodology,using the presented intelligent algorithm is proposed to increase the learning *** experimental results verify the system stabilization,favorable performance and no chattering phenomena can be

关键词： Optimal control robotics Chaotic Step planning Artificial bee colony(ABC) Quadruped robot

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：