检索结果-内蒙古大学图书馆

International Symposium on Computational Intelligence and Design, ISCID

作者： Dan Lu Linsheng Li Qingsen Yan Institute of Digital Media & Communication Taiyuan University of Science and Technology Taiyuan China Shaanxi Key Laboratory of Speech & Image Information Processing School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781479970063

In this paper, we introduce the development of object tracking. In particular, we introduce several kinds of target tracking algorithm based on sparse coding, including a robust visual tracking method by casting tracking as a sparse approximation problem in a particle filter framework, kernel sparse tracking with compressive sensing, and real-time compressive tracking. Show the concept of sparse representation and compressed sensing, analyze the meaning of the sparse representation in the target tracking, and compare the algorithm.

关键词： Target tracking Kernel Robustness Visualization image coding Pattern recognition Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Distributed Adaptive Compressed Video Sensing Using Smoothed Projected Landweber Reconstruction

引用

China communications 2013年第11期10卷 58-69页

作者：李然干宗良崔子冠武明虎朱秀昌 Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications

A novel Compressed-Sensing-based(CS-based)Distributed Video Coding(DVC)system,called Distributed Adaptive Compressed Video Sensing(DISACOS),is proposed in this *** this system,the input frames are divided into key frames and non-key frames,which are encoded by block CS *** key frames are encoded as CS measurements at substantially higher rates than the non-key frames and decoded by the Smoothed Projected Landweber(SPL)algorithm using multi-hypothesis *** the non-key frames,a small number of CS measurements are first transmitted to detect blocks having low-quality Side Information(SI)generated by the conventional interpolation or extrapolation at the decoder;then,another group of CS measurements are sampled again upon the decoder’s *** fully utilise the CS measurements,we adaptively allocate these measurements to each block in terms of different edge ***,the residual frame is reconstructed using the SPL algorithm and the decoded non-key frame is simply determined as the sum of the residual frame and the *** results have revealed that our CS-based DVC system yields better rate-distortion performance when compared with other schemes.

关键词： distributed video coding com-pressed sensing side information smoothedprojected Landweber reconstruction edge inf-ormation

来源：评论

学校读者我要写书评

暂无评论

Action Recognition from a Different View

引用

China communications 2013年第12期10卷 139-148页

作者：陈昌红干宗良 Jiangsu Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications

In this paper,we propose a novel approach to recognise human activities from a different *** appearance-based recognition methods have been shown to be unsuitable for action recognition for varying views,there must be some regularity among the same action sequences of different *** matrices appear to be relative stable across ***,the ability to effectively realise this stability is a *** this paper,we extract the shape-flow descriptor as the low-level feature and then choose the same number of key frames from the action ***-similarity matrices are obtained by computing the similarity between any pair of the key *** diagonal features of the similarity matrices are extracted as the highlevel feature representation of the action sequence and Support Vector Machines(SVM) is employed for *** test our approach on the IXMAS multi-view data *** proposed approach is simple but effective when compared with other algorithms.

关键词： action recognition different view shape-flow descriptor self-similarity matrix diagonal feature

来源：评论

学校读者我要写书评

暂无评论

Fast coding unit depth decision for HEVC

Fast coding unit depth decision for HEVC

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Fangshun Mu Li Song Xiaokang Yang Zhenyi Luo Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China School of Electronics and Information Engineering Shanghai University of Electric Power Shanghai China

ISBN: (纸本)9781479947164

High Efficiency Video Coding (HEVC) achieves high efficiency by introducing a new coding structure in adoption of coding unit (CU), prediction unit (PU) and transform unit (TU). However, it also imposes great computation burden on the mode decision of encoders. In this paper, we propose a fast CU depth decision scheme to reduce the encoder complexity for HEVC. Firstly, the relationship between rate-distortion (R-D) cost and CU depth is explored carefully with Mean Squared Error (MSE) and Number of Encoded Bits (NEB) metrics. Then CU splitting is modeled as a binary classification problem and resolved by an offline trained Support Vector Machine (SVM) model. The experimental results show that the proposed algorithm achieves up to 59% running-time reduction with negligible loss in terms of PSNR and bit rate.

关键词： Encoding Bit rate Support vector machines Classification algorithms Video coding Prediction algorithms Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Speed up HEVC encoder by precoding with H.264

Speed up HEVC encoder by precoding with H.264

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Fangshun Mul Li Song Zhenyi Luo Xiangwen Wang Xiaokang Yang Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China School of Electronics and Information Engineering Shanghai University of Electric Power Shanghai China

ISBN: (纸本)9781479942503

The new video coding standard, High Efficiency Video Coding (HEVC), was developed to replace H264/AVC and achieves high efficiency by introducing a new coding structure in adoption of coding unit (CU), prediction unit (PU) and transform unit (TU). However, it also imposes great computation burden on the mode decision of encoders. In this paper, a conceptual HEVC encoder architecture with cascaded H264/AVC encoder is proposed to speed up the CTU splitting process of HEVC encoder. First, the input frame is precoded with an efficient H264/AVC encoder to gather the partition and prediction information of H264/AVC macroblocks (MBs). Then based on the gathered information, CU and PU modes are carefully screened during HEVC encoding. Two schemes are proposed to reduce the CU and PU candidate modes to accelerate the Coding Tree Unit (CTU) splitting process. At last, the HEVC encoder tries all combinations of candidate CU and PU mode to determine the optimal CU, PU and TU mode by computing the rate-distortion (R-D) cost. The experimental results on highly-optimized open source codecs - x264 and x265 show that the proposed framework can effectively reduce encoding time with negligible loss in terms of PSNR and bitrate.

关键词： Video coding Encoding PSNR Bit rate Decision support systems Abstracts Standards

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of H.265/MPEG-HEVC encoders for 4K video sequences

Performance evaluation of H.265/MPEG-HEVC encoders for 4K vi...

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Qingxiong Huangyuan Li Song Zhengyi Luo Xiangwen Wang Yanan Zhao Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China Instiuue of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China School of Electronics and Information Engineering Shanghai University of Electric Power Shanghai China

ISBN: (纸本)9781479942503

The H.265/MPEG-HEVC is the latest video coding standard, which achieves an increase of about 50% in coding efficiency compared to its predecessor H.264/MPEG-AVC. Ever since H.265/MPEG-HEVC was designed to replace almost all existing H.264/ MPEG-AVC codecs, high-resolution video coding beyond High Definition (4K, 8K, etc.) has drawn more attention. On the other hand, it's well known that reference implementation of HEVC codec, HM, acts an important role during standardization, particularly for evaluation of rate distortion performance of different tools. However, HM is far from a practical codec because of very slow coding speed even on modern multi-core computers. Up to now except for HM few comparisons are known about both the coding performance and the coding speed of practical HEVC encoders for high resolution video sequences. To address this issue, this paper conducts a comprehensive evaluation of latest high performance H.265/MPEG-HEVC encoders, including the open source encoder-x265 and the commercial encoder-DivX265, based on default parameters and a new open 4K video database. Furthermore, latest HM and x264 are also included for performance anchors. The experimental results show DivX265 provides average bit-rate savings of 4.79% relative to HM while x265 with default preset achieves an average reduction of 3.21% in terms of BD-BR saving. In addition, different presets of x265 make a good tradeoff between coding speed and R-D performance while DivX265 is almost as fast as x265 ultrafast preset. We believe such evaluation information could provide a more comprehensive picture of state-of-the-art H.265/MPEG-HEVC encoders.

关键词： Transform coding Encoding Decision support systems Codecs Video coding Abstracts Standards

来源：评论

学校读者我要写书评

暂无评论

Appearance model based moving object matching across disjoint camera views

引用

2nd International Conference on Opto-Electronics Engineering and Materials Research, OEMR 2013

作者： Yu, Kong Shuai Hu, Dong Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology The key lab of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecom Nanjing 210003 China

ISBN: (纸本)9783037857731

A new object tracking scheme for multi-camera surveillance with non-overlapping views is proposed in this paper. Brightness transfer function (BTF) is used to establish relative appearance correspondence between different views. Mixtures of probabilistic principal component analysis (MPPCA) is incooperated to learn the subspace of brightness transfer function with the concern to deal with multiple different brightness areas in a scene. The incremental major color spectrum histogram (IMCSH) is used as similarity measure for reliable matching. Experimental results with real world videos show the effectiveness of the proposed algorithm. © (2013) Trans Tech Publications, Switzerland.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Spectral unmixing for hyperspectral image classification with an adaptive endmember selection

Spectral unmixing for hyperspectral image classification wit...

引用

4th International Conference on Intelligence Science and Big Data Engineering, IScIDE 2013

作者： Meng, Qingjie Zhang, Yanning Wei, Wei Zhang, Lei School of Computer Science Shaanxi Province Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9783642420566

Hyperspectral classification techniques are widely used for detailed analysis of the earth surface. However, mixed pixels caused by the relatively low spatial resolution of the imaging system are the big burden for traditional pure-pixel-hypothesis based hard classification methods. To address this problem, a novel method, which jointly uses soft classification and spectral unmixing, is proposed in this paper. The confusion matrix is exploited to determine the endmember set for each class. Then the generated endmember is adopted for spectral unmixing. The fractional abundance of training samples, which is generated from spectral unmixing, is utilized to optimize soft multinomial logistic regression classifier. The result of the optimized classifier will result in a more accurate confusion matrix. Thus, this procedure is executed iteratively to achieve required performance. Experimental results on synthetic and real hyperspectral data sets demonstrate the superiority of the proposed method for hyperspectral image classification. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Super-resolution based on two dictionary-pairs

引用

Sensors and Transducers 2013年第10期157卷 289-294页

作者： Li, Xin Zhu, Xiuchang Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

For learning-based super-resolution reconstruction, the selection and training of dictionary play an important role in improving image reconstruction quality. A super-resolution algorithm based on two dictionary-pairs is proposed in this paper. This algorithm selects image's high- and mid-frequency components as the features of high- and low-resolution patches respectively, and gets the first dictionary-pair, i.e. joint-basic high/low-resolution dictionary-pair, by means of joint training. Then it calculates the difference between original high/mid-frequency components and reconstructed high/mid-frequency components with the first dictionary-pair, and composes the second dictionary-pair, i.e. residual high- and low-resolution dictionary-pair. During super-resolution reconstruction, the high-frequency component and residual high-frequency component of low-resolution image are reconstructed respectively with the above two dictionary-pairs. The experiment results show that, the subjective and objective reconstruction quality could be effectively improved by our proposed algorithm. © 2013 IFSA.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Evaluation of bodily-kinesthetic intelligence based on computer contextual method

Evaluation of bodily-kinesthetic intelligence based on compu...

引用

2013 International Conference on Sport Science and Computer Science (CCCS 2013)

作者： Qi Xia Wei Wang Jun Wang College of Education Science Nanjing Normal University Key Laboratory of Image Processing and Image Communication of Jiangsu Province Nanjing University of Posts and Telecommunications

There are two main types of tests to assess one's bodily-kinesthetic intelligence,which are writing tests and scenario ***,these two methods are subjective and time-consuming and not suitable for large-scale *** paper proposed a new assess method to assess bodily-kinesthetic intelligence based on the writing intelligence test *** method is designed with the computer virtual reality *** result shows the method can get better reliability and *** the evaluation process is easier to realize.

关键词： bodily-kinesthetic intelligence multiple intelligence computer contextual method

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：