检索结果-内蒙古大学图书馆

作者： Hu, D. Hu, J. Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications China Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications China

ISBN: (纸本)9781845648282

Nonparametric model is one of the popular ones for background modeling for its ability to adapt to changes quickly in dynamic environment and enable very sensitive detection of moving objects. However, the method is too complex and computationally inefficient to real-time application. In this paper, a fast and efficient scheme for moving object detection by nonparametric background modeling was proposed, whereas the background was modeled combining clustering theory to eliminate the large amount of redundant information and noise pixels in background modeling stage. Moreover, adaptive background and temporal differencing was used to filter out unchanged background pixels, thus enabling an additional reduction in computational requirements and improving the detection results. Besides, RGB color components were substituted by chromaticity coordinates to suppress shadow effects. Experimental results demonstrated the effectiveness of the proposed algorithm. © 2014 WIT Press.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on moving object detection based on the Bayesian theory

Research on moving object detection based on the Bayesian th...

引用

作者： Hu, D. Liu, X. Education Ministry's Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications China Jiangsu Province's Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications China

ISBN: (纸本)9781845648282

For effective and efficient detection of moving objects from complex surveillance scenarios, a novel integrated object detection scheme based on clustering and Bayesian theory is proposed in this paper. The algorithm conducts clustering analysis in the time domain as the pre-segmentation step for later Bayesian judgment processing. Furthermore, temporal differential image was used to classify dynamical and static pixels, which were then used to direct the Bayesian judgment with proper models. The clustering processing reduced the number of the mixture models, which in turn, reduced the computational complexity while ensuring accurate moving object detection. Simulation results show that the proposed scheme well exploited the temporal correlation of the video sequences and the accuracy of the detected objects can be improved by nearly 20% compared to the typical Gaussian mixture modeling algorithm. © 2014 WIT Press.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Efficient Rate Control Algorithm for Multi-view Video Coding

引用

China communications 2011年第3期8卷 83-89页

作者：刘峰熊婕范晶晶林琼洁 Image Processing & Image Communication Key Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology(Nanjing University of Posts and Telecommunications) Ministry of Education

Rate control is one of the key factors influencing the multi-view video ***,there is not a rate control algorithm in the existing Joint Multi-view Video Coding *** this paper,an efficient rate control algorithm and a bit allocation strategy for multi-view video coding are *** order to obtain the consistent view quality,a bit allocation model based on the Lagrange optimum algorithm is firstly ***,considering the encoding statistical characteristics of different view types,a view weighting factor is introduced,and it will help improve the precision of bit allocation among *** with the fixed QP control strategy,experiment results show that the proposed algorithm can efficiently control the bit rate and obtain more consistent views,with video visual quality improved.

关键词： rate control rate distortion bit allocation view weighting factor

来源：评论

学校读者我要写书评

暂无评论

Improved SAI Method using Non-local Spatial Constraint for image Interpolation

Improved SAI Method using Non-local Spatial Constraint for I...

引用

2011年无线通信与信号处理国际会议(WCSP 2011)

作者： Jueping Bian Zongliang Gan Mengcheng Zhang Xiuchang Zhu Jiangsu province key lab on image processing & image communication NUPT Nanjing China

This paper proposes an improved image interpolation method based on the soft-decision adaptive interpolation (SAI) algorithm. Natural images often contain repeatable patterns and structures throughout the image, which is called non-local property. We can use this non-local strategy to improve the interpolation quality by better estimating the model parameters and Lagrangian multiplier. There are two steps in our method. In the first step, similar patches of the given block are found in the initialized high resolution image, and the model parameters can be determined properly using the expanded piecewise auto regression (PAR) model and non-local spatial constraint. In the second step, the self-similarity of patches across the high and low resolution images is exploited to solve the Lagrangian multiplier λ, thus to make the data estimation robust. Experiments indicate that the improved method can achieve good results both subjectively and objectively.

关键词： image interpolation the SAI algorithm non-local self-similarity

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

Partical swarm optimization based unequal loss protection of embedded video streams

Partical swarm optimization based unequal loss protection of...

引用

International Conference on Communication Technology (ICCT)

作者： Jiajing Hu Dong Hu The key Laboratory of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China

This paper presents a new scheme for optimal packetization of scalab.e multimedia data over lossy network. By assigning an unequal amount of forward error correction (FEC) bits to each segment of transmission packets, the proposed algorithm protects a progressive bitstream generated by a three-dimensional set partitioning in hierarchical trees (3-D SPIHT) algorithm. The partical swarm optimization (PSO) algorithm is used to reasonably allocate bits between source coding and channel coding across packets. Experimental results show that the proposed algorithm provides close to optimal average peak signal-to-noise ratio performance and that its' running time is significantly lower than that of previously known solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Fast Inter Mode Decision Algorithm for H.264/AVC

An Efficient Fast Inter Mode Decision Algorithm for H.264/AV...

引用

WRI International Conference on communications and Mobile Computing, CMC

作者： Huaibin Huang Dong Hu key Laboratory of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China

An efficient fast inter mode decision algorithm for the baseline H.264/AVC video coding is proposed in this paper. The main idea of the algorithm is to reduce the number of candidate modes for rate distortion optimization (RDO) by using early mode detection in four different levels, viz. SKIP mode detection, type detection at macroblock-level, type detection at submacroblock-level and intra modes detection. In addition, the correlation of cost of current MB and the one of previous frame, as well as the cost's monotonous property are both used to help the mode decision. Compared to JM8.6 reference software, our algorithm can save encoding time 71.743% on average with negligible PSNR loss, which is very helpful for H.264/AVC inter frame. encoding.

关键词： Automatic voltage control Costs image coding Encoding Video coding Rate-distortion Video sequences Mobile communication Mobile computing Telecommunication computing

来源：评论

学校读者我要写书评

暂无评论

A Novel Representation for Video-based Person Reidentification with Attribute-constraints

A Novel Representation for Video-based Person Reidentificati...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Wanru Song Jieying Zheng Yahong Wu Qingqing Zhao Changhong Chen Feng Liu Jiangsu Key Lab of Image Processing and Image Communications Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781538646748;9781538646731

Person re-identification is an important task in the field of intelligent video surveillance, which has become one of the research focus spots in the field of computer vision. Video-based person re-identification aims to verify a pedestrian identity of the video sequences which captured from non-overlapping cameras at different time. In this paper, we propose a novel feature extractor based on LSTM networks. These LSTM networks are used to extract the effective space-time feature representation named the attribute-constraints space-time feature (ASTF). Different from other methods, we manually annotate pedestrians in videos with three attributes. In the meantime, the attributes with the IDs of pedestrians are regarded as lab.ls to train the feature extractor. The ASTF representation for a testing video is extracted by this feature extractor, which is an effective space-time feature representation for video-based re-identification. Extensive experiments on two public datasets demonstrate that our approach outperforms the state-of-the-art video-based re-identification methods.

关键词： Feature extraction Task analysis Training Cameras Testing Measurement Video sequences

来源：评论

学校读者我要写书评

暂无评论

A novel spatial information recovery algorithm based on fuzzy clustering in H.264

A novel spatial information recovery algorithm based on fuzz...

引用

IEEE International Symposium on Intelligent Signal processing and Communication Systems (ISPACS)

作者： Han Shen Xiu-chang Zhu Jiangsu Province Key Lab on Image Processing & Image Communication Nanjing University of Posts and Telecommunications China

As no reference frame can be obtained in Intra-frame error concealment, reducing the degradation of spatial reconstructed image is one of the key techniques in error concealment. In this paper, a novel spatial error concealment algorithm based on fuzzy clustering for Intra-frame in H.264 is proposed. This proposed algorithm gives a new selection of eigenvectors and similarity measurement for fuzzy clustering. The experimental results show that the proposed algorithm can improve the edge details, achieve a better subjective quality of the recovered image and increase PSNR (Peak Signal-to-Noise Ratio) as well.

关键词： Clustering algorithms Signal processing algorithms image reconstruction Degradation PSNR Resilience Video sequences Frequency Discrete cosine transforms Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Pixel classified colourisation method based on neighbourhood similarity priori

Pixel classified colourisation method based on neighbourhood...

引用

作者： Chen, Jie Gan, Zongliang Zhu, Xiuchang Wang, Jin Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Post and Telecommunications P.O. Box 166 No. 66 Xin Mofan Road Nanjing Jiangsu China College of Information Engineering Yangzhou University No. 88 South University Ave Yangzhou Jiangsu China

Colourisation is a kind of computer-aided technology which automatically adds colours to greyscale images. This paper presents a scribble-based colourisation method which treats the flat and edge pixels differently. First, we classify the pixels to flat or edge pixel categories using the neighbourhood similarity pixels searching algorithm. Then, we compute the weighted coefficients of the edge pixels by solving a constraint quadratic programming problem and compute the weighted coefficients of the flat pixels based on their luminance distances. Finally, we transmit the weighted coefficients to the chrominance images according to the joint correlation property between luminance and chrominance channels, and combine with the colours scribbled on by the user to compute all the unknown colours. The experimental results show that our method is effective especially on reducing colour bleeding in the boundary parts and can give better results when only a few colours are scribbled on. © 2018 Inderscience Enterprises Ltd.

关键词： Quadratic programming

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：