检索结果-内蒙古大学图书馆

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Qi Xu Guangtao Zhai Min Liu Ke Gu Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China

Owing to the thriving market of stereoscopic image based applications, efficient and effective 3D image quality assessment (IQA) techniques become colossally required these days. Consequently, we introduce a new reduced-reference (RR) stereoscopic image quality metric to meet this demand, through measuring Structural degradation and Saliency based Parallax compensation Model (SSPM). Experimental results on the LIVE 3D image Quality Database, including both symmetrically and asymmetrically distorted stereoscopic images in different categories and quality levels, are provided to justify the effectiveness of the proposed SSPM model as compared to some existing progressive and popular stereoscopic IQA approaches. Meanwhile, it deserves broad attentions that only four number pairs, extracted from original image, are required as the key feature to be sent to the receiver terminal, thus making this procedure also efficient.

关键词： Three-dimensional displays Stereo image processing Measurement image quality Databases Degradation Nonlinear distortion

来源：评论

学校读者我要写书评

暂无评论

Blind image quality assessment for noise

Blind image quality assessment for noise

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Min Liu Guangtao Zhai Zhenyu Zhang Yuntao Sun Ke Gu Xiaokang Yang Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China

image denoising has been fanatically researched for a very long time in that it is a commonplace yet important subject. The task to testify the performance of different image de-noising methods always resorts to PSNR in the past, until the emergence of SSIM, a landmark image quality assessment (IQA) metric. Since then, a vast majority of IQA methods were introduced in terms of various kinds of models. But unfortunately, those IQA metrics are along with more or less deficiencies such as the requirement of original images, making them far less than the ideal approaches. To address this problem, in this paper we propose an effective and blind image quality assessment for noise (dubbed BIQAN) to approximate the human visual perception to noise. The BIQAN is realized with three important portions, namely the free energy based brain principle, image gradient extraction, and texture masking. We conduct and compare the proposed BIQAN and a large amount of existing IQA metrics on three largest and most popular image quality databases (LIVE, TID2013, CSIQ). Results of experiments prove that the BIQAN has acquired very encouraging performance, outperforming those competitors stated above.

关键词： Measurement image quality Quality assessment Indexes PSNR

来源：评论

学校读者我要写书评

暂无评论

Simultaneous triple subtitles exhibition via Temporal Psychovisual Modulation

Simultaneous triple subtitles exhibition via Temporal Psycho...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Chunjia Hu Guangtao Zhai Zhongpai Gao Xiongkuo Min Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China

ISBN: (纸本)9781479943142

With the quick acceleration of cultural exchange and globalization, multi-language annotation for in-theatre movie exhibition is gaining more attention. The existing solution overlays a stack of subtitles in different languages over the movie, for example, the familiar combination of English + local tongue as seen in the cinema today. However, a major drawback of this straightforward piling-up type of solution is that as the required number of languages increases, the subtitle area grows and it may eventually span over the movie contents. An effective multi-language subtitling system without compromising the movie watching experience is therefore highly desired. In this paper, we propose a new Temporal Psychovisual Modulation (TPVM) based solution to the multi-language subtitling problem. TPVM is a new paradigm of information display exploiting the mismatch between high refresh rate of the modern optoelectronic displays and limited temporal resolution of the human visual system (HVS). In this work, we design a simultaneous triple subtitle exhibition system using 2 120 Hz stereoscopic DLP projectors with linear polarization filters and LCD shutter glasses. Wearing different pairs of glasses, the audience can enjoy the movie with 3 optional subtitles without interfering with the audience without the glasses and see the movie directly. Extended experimental results will be given in this paper to justify the effectiveness and robustness of the proposed multiple subtitling system.

关键词： Glass Motion pictures Modulation Stereo image processing Synchronization Visual systems Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Visual Attention Data for image Quality Assessment Databases

Visual Attention Data for Image Quality Assessment Databases

引用

IEEE International Symposium on Circuits and Systems

作者： Xiongkuo Min Guangtao Zhai Zhongpai Gao Ke Gu Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmissions

ISBN: (纸本)9781479934331

images usually contain areas that particularly attract people's attention and visual attention is an important feature of human visual system (HVS). Visual attention had been shown to be effective in improving performance of existing image quality assessment (IQA) metrics. However, with the quick advancement of IQA research, the booming of open IQA databases calls for associated comprehensive and accurate visual attention dataset. Despite of the large number of existing computational attention/saliency models, the most accurate measure of human attention is still human based. In this research, we first conduct extensive eye tracking experiments for all the pristine images from the seven widely used IQA databases (LIVE, TID2008, CSIQ, Toyama, LIVE Multiply Distortion, IVC and A57 databases). Then we propose a gaze-duration adaptive weighting approach to generate saliency maps from the eye tracking data. When applied on the IQA databases, experimental results suggest that accuracy of benchmark quality metrics, e.g. PSNR and SSIM can be systematically improved, outperforming existing saliency datasets. Both the eye tracking data and the saliency maps in this research will be made publicly available at ***.

关键词： important HVS IQA

来源：评论

学校读者我要写书评

暂无评论

A QoE friendly rate adaptation method for DASH

A QoE friendly rate adaptation method for DASH

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Yuming Cao Xiaoquan You Jia Wang Li Song Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Multi Media Processing and Transmissions Shanghai

MPEG-DASH introduced open standards into HTTP streaming, which was a huge step forward. The scope of the MPEG-DASH standard was limited to the Media Presentation Description (MPD) format of the manifest files as well as the segmentation standards for the server, but did not include the client application as part of their standards. Particularly a good representation switching algorithm at DASH client should adapt to time varying bandwidth with better QoE (Quality of Experience). In this paper, we propose a QoE friendly rate adaptation method which can achieve less switching times and more gradual quality change. To achieve these purposes, we propose a fixed-interval buffer model, which keeps the representation level unchanged whenever the media buffer size is within the preset interval. We also design a step-wise switch-up method to prevent buffer overflow and a switch-down method based on intermediate quality level to prevent buffer underflow. A quick boot algorithm is introduced to fully improve the performance of the proposed scheme. Experimental results show that the proposed algorithm can achieve more satisfactory results compared with existing ones.

关键词： Bandwidth Bit rate Switches Heuristic algorithms Streaming media Standards Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Multilevel DCT-based zerotree image coding

Multilevel DCT-based zerotree image coding

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Kankan Zheng Liang Zhang Rong Xie Institute of Image Communication and Network Engineering & Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China

image and video coding is fundamental to data storage and transmission. JPEG 2000 is the latest international image coding standard which exploits wavelet transform for image compression. Zerotree coding structure is an efficient algorithm for coding of wavelet transform coefficients. However, implementation complexity of wavelet transform and long coding process of zerotree structure may limit the application in some cases. In this paper, an idea of multilevel DCT-based zerotree image coding is proposed, in which Wavelet Transform (WT) is replaced by Discrete Cosine Transform (DCT) and DCT coefficients are regrouped into subbands of different frequencies. Furthermore, a new zerotree coding structure is proposed to reduce the complexity of zerotree coding process. A conventional zerotree with a parent-child relation of 2×2 offspring is expanded to the one of 4×4 offspring. Coefficients reorder and inverse DCT are needed when DCT transform size is not a power of 4. This expansion makes each parent node of zerotree coding structure have more child nodes and, therefore, reduce the complexity of encoding process. Simulation results of images with different spatial resolutions are presented to show the advantage of the proposed algorithm. The proposed multi-level DCT-based zerotree image coding algorithm performs similar coding performance as the SPIHT method. The zerotree coding structure with a parent-child relation of 4×4 pixels can significantly reduce the complexity of high-bitrate coding process without sacrificing image subjective quality.

关键词： Discrete cosine transforms image coding Encoding Spatial resolution Wavelet transforms Bit rate

来源：评论

学校读者我要写书评

暂无评论

Spatial Error Concealment with Adaptive Linear Predictor

Spatial Error Concealment with Adaptive Linear Predictor

引用

IEEE International Symposium on Circuits and Systems

作者： Jing Liu Guangtao Zhai Xiaokang Yang Bing Yang Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai 200240 China

ISBN: (纸本)9781479934331

In this paper, we propose a novel spatial error concealment algorithm based on adaptive linear predictor. The predictor automatically tunes its order and support shape according to local contexts. The optimal order is determined using Bayesian Index Criterion (BIC). The order-adaptive predictor is able to recover more important features or structures. Simulation results show that compared to the state-of-the-art error concealment algorithms, the proposed method gives better reconstruction performance in terms of objective and subjective evaluations.

关键词： Data Security linear predictor Self tuning subjective evaluation Simulation results

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

A Survey: Target Tracking Algorithm Based on Sparse Representation

A Survey: Target Tracking Algorithm Based on Sparse Represen...

引用

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

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：