检索结果-内蒙古大学图书馆

Parallel full search algorithm for Motion Estimation on Graphic Processing Unit

RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING 2019年第4期12卷 317-323页

作者： Sayadi, Fatma Ezzahra Chouchene, Marwa Bahri, Haithem Khemiri, Randa Atri, Mohamed Monastir Univ Fac Sci Lab Elect & Microelect EE Environm St Monastir 5019 Tunisia

Background: Advances in video compression technology have been driven by ever-increasing processing power available in software and hardware. Methods: The emerging High-Efficiency Video Coding (HEVC) standard aims to provide a doubling in coding efficiency with respect to the H.264/AVC high profile, delivering the same video quality at half the bit rate. Results: Thus, the results show high computational complexity. In both standards, the motion estimation block presents a significant challenge in clock latency since it consumes more than 40% of the total encoding time. For these reasons, we proposed an optimized implementation of this algorithm on a low-cost NVIDIA GPU developed with CUDA language. Conclusion: This optimized implementation can provide high-performance video encoder where the speed reaches about 85.

关键词： Compute Unified Device Architecture (CUDA) full search algorithm GPU HEVC motion estimation Nvidia optimization method

来源：评论

学校读者我要写书评

暂无评论

Implementation of parallel full search algorithm for motion estimation on multi-core processors

Implementation of parallel full search algorithm for motion ...

引用

2nd International Conference on Next Generation Information Technology, ICNIT 2011

作者： Zhou, Jing Jiao, Liangbao Cao, Xuehong College of Communication and Information System Nanjing University of Post and Telecommunications Nanjing China School of Communications Engineering Nanjing Institute of Technology Nanjing China

In order to speed up H.264/AVC coding efficiency, this paper proposed a parallelization approach of full search (FS) algorithm for motion estimation on Graphic Processor Unit (GPU) using computing unified device architecture (CUDA). According to the independence among different macro-blocks (MBs), we mapped the traditional sequential FS algorithm for motion estimation to CUDA parallel computing model with optimizing memory usage, taking full advantage of the powerful parallel computing capability to speed up FS motion estimation. Experimental results show that our implementation on CUDA demonstrates substantial improvement up to 50 times than CPU counterpart available and can effectively speed up the FS for motion estimation. © 2011 AICIT.

关键词： CUDA full search algorithm Motion estimation parallel computing

来源：评论

学校读者我要写书评

暂无评论

Hardware - software co-design framework for sum of absolute difference based block matching in motion estimation

引用

MICROPROCESSORS AND MICROSYSTEMS 2020年 74卷 103012-103012页

作者： Chandran, K. R. Sarath Chandramani, Premanand Venkatesh Sri Sivasubramaniya Nadar Coll Engn Dept Comp Sci & Engn Chennai 603110 Tamil Nadu India Sri Sivasubramaniya Nadar Coll Engn Dept Elect & Commun Engn Chennai 603110 Tamil Nadu India

Motion estimation is the computationally intensive part of video encoding. This paper presents a processing element based architecture for accelerating the calculation of Sum of Absolute Differences (SAD) which is the most widely used block matching criteria in motion estimation. A clock gating method is anlysed to enable or disable the required processing elements for a particular time of use. The selection of processing elements is performed based on motion analysis of the input video. The level of motion is estimated from initial frames to configure the hardware for SAD evaluation. A System-on-Chip approach, implemented in Xilinx Zynq SoC is proposed that will be efficient in terms of power and resource utilization as the hardware is configured based on the property of input video. This hardware-software co-design is able to achieve approximately 4.6x speed up compared to the the original software implementation of the framework running on ARM processor. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Processing element Hardware-software co-design Sum of absolute difference Motion estimation full search algorithm System-on-chip

来源：评论

学校读者我要写书评

暂无评论

A new predictive search area approach for fast block motion estimation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2003年第6期12卷 648-652页

作者： Chung, KL Chang, LC Natl Taiwan Univ Sci & Technol Dept Comp Sci & Informat Engn Taipei 10672 Taiwan Natl Taiwan Univ Sci & Technol Dept Informat Management Taipei 10672 Taiwan

According to the observation on the distribution of motion differentials among the motion vector of any block and those of its four neighboring blocks from six real video sequences, this paper presents a new predictive search area approach for fast block motion estimation. Employing our proposed simple predictive search area approach into the full search (FS) algorithm, our improved FS algorithm leads to 93.83% average execution-time improvement ratio, but only has a small estimation accuracy degradation. We also investigate the advantages of computation and estimation accuracy of our improved FS algorithm when compared to the edge-based search algorithm currently published by Chan and Sin;experimental results reveal that our improved FS algorithm has 74.33% average execution-time improvement ratio and has a higher estimation accuracy. Finally, we further compare the performance among our improved FS algorithm, the three-step search algorithm, and the block-based gradient descent search algorithm.

关键词： block matching estimation accuracy full search algorithm motion estimation search area determination search window

来源：评论

学校读者我要写书评

暂无评论

Histogram ordering model-based fast motion estimation

引用

IET IMAGE PROCESSING 2012年第3期6卷 238-250页

作者： Park, S. -J. Hong, S. -M. Lee, H. Jin, S. Jeong, J. Hanyang Univ Dept Elect & Comp Engn Seoul 133791 South Korea Hanyang Univ Dept Intelligent Robot Seoul 133791 South Korea LG Elect Inc SIC Ctr DTVSoC Dept SAT Gr Seoul South Korea

This study proposes two efficient block matching algorithms for fast motion estimation using a histogram ordering model in order to reduce the computational cost of video coding. Since the representative pixels that consist of edge or texture mainly contribute to the block matching criterion, it is important to analyse the details of the current block. To analyse the characteristics of the block with low complexity, the pixel histogram is used for the observation of the block. Based on this pixel histogram for the current block, an optimal block matching order is determined for the lossless fast matching algorithm. In addition, adaptive partial block matching algorithm for lossy fast motion estimation using histogram-based block matching ordering is also presented to further reduce the complexity of block matching. By capturing the representative pixels, block matching distortion is maximised soon enough during the block matching. For this reason, partial block matching is available instead of full block matching, which is also known as a full search algorithm. Our experimental results show that the proposed algorithm not only reduces the computational complexity of block matching criterion, but also tends to maintain the image quality when compared to the conventional fast matching algorithms.

关键词： search problems image quality fast motion estimation Optimisation techniques partial block matching histogram-based block matching ordering model Image and video coding motion estimation pixel histogram full search algorithm block matching algorithms image matching video coding representative pixels block matching criterion image texture Computational complexity Video signal processing block matching distortion computational complexity optimal block matching order computational cost reduction Combinatorial mathematics block matching complexity

来源：评论

学校读者我要写书评

暂无评论

A novel fast sampling predictive block match algorithm

A novel fast sampling predictive block match algorithm

引用

International Conference on Neural Networks and Signal Processing

作者： Su, R Liu, GZ Zhou, GF Xian Jiaotong Univ Sch Elect & Informat Engn Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)0780377028

Block-based motion estimation is essential in video coding applications, which can diminish the temporal redundancy of sequences effectively. Though full search algorithm (FSA) can undoubtedly get global optimum estimation, it is computationally intensive. In this paper a novel algorithm named as the Sampling Predictive Block Match algorithm (SPBMA) is presented, which combine the ideas of motion vector mean predictor sampling match and adaptive diamond search. Our experiments verify the superiority of the proposed algorithm in precision and rapidity (for the Mother & daughter sequence, SPBMA is 108 times as fast as FSA with only 0.75% lower in PSNR). It is suitable for the wireless video communication with the rigorous demand for ultra low power.

关键词： motion estimation image sampling image matching prediction theory sampling predictive block match algorithm motion estimation video coding temporal redundancy full search algorithm global optimum estimation motion vector mean predictor sampling match adaptive diamond search wireless video communication

来源：评论

学校读者我要写书评

暂无评论

A fast motion estimation using a three-dimensional reference motion vector

A fast motion estimation using a three-dimensional reference...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Lai, KC Wong, SC Hong Kong Polytech Univ Ctr Multimedia Signal Proc Dept Elect & Informat Engn Hong Kong Hong Kong Peoples R China

ISBN: (纸本)0780374029

Based on a study of the motion vector (MV) obtained by the full search algorithm among several test sequences, we found that the prediction process for motion estimation in many existing algorithms are not optimal. We optimize the prediction process by classifying the blocks into four different classes based on a newly proposed three-dimensional reference MV. Different search patterns and strategies are used for each class. The proposed algorithm can improve computation requirement as high as 43.9% than the diamond search algorithm.

关键词： motion estimation video coding search problems image sequences fast motion estimation three-dimensional reference motion vector 3D reference motion vector full search algorithm test sequences prediction process diamond search algorithm video compression standard computational complexity reduction

来源：评论

学校读者我要写书评

暂无评论

A novel Orthogonal Logarithmic search algorithm for low bit rate video coding

A novel Orthogonal Logarithmic search algorithm for low bit ...

引用

Conference on Image and Video Communications and Processing

作者： Soongsathitanon, S Dlay, SS Univ Newcastle Upon Tyne Sch Elect Elect & Comp Engn Newcastle Upon Tyne NE1 7RU Tyne & Wear England

ISBN: (纸本)0819448222

The paper presents a novel Orthogonal Logarithmic search (OLS) method for block base motion compensation. The performance of the algorithm is evaluated, by using standard QCIF benchmark video sequences and the results are compared to a traditional well-known full search algorithm (FSA) and a sub-optimal method called the Three Step search (3SS). The evaluation considers the three important metrics, time, entropy and PSNR (Peak Signal to Noise Ratio). The paper also shows that the strength of the algorithm lies in its speed of operation as it is 95% faster than the FSA and over 60% faster than the 3SS. Investigation into-motion estimation algorithms is one of the important issues in the video coding standards such as ISO MPEG-1/2 and ITU-T H.263. These international standard's regularly use a conventional FSA to estimate the motion of pixels between pairs of image block matching algorithms. Since a full search requires intensive computations and the distortion function needs to be evaluated many times for each target block to be matched, the process is very time consuming. Therefore, the main aim of this investigation has been to alleviate this acute problem of search speed and accuracy.

关键词： Orthogonal Logarithmic search Motion Estimation block matching algorithms Three-Step search full search algorithm low bit rate Video Coding

来源：评论

学校读者我要写书评

暂无评论

A Fast VQ Codeword search algorithm for AMR Wideband Speech Codec

A Fast VQ Codeword Search Algorithm for AMR Wideband Speech ...

引用

2nd International Conference on Computer and Automation Engineering (ICCAE)

作者： Li, Feng-lian Zhang, Xue-ying Liu, Xing-wang Du, Xiao-lin Taiyuan Univ Technol Coll Informat Engn Taiyuan Shanxi Peoples R China

ISBN: (纸本)9781424455690

This paper presents a fast efficient codeword search algorithm for vector quantization (VQ) based on the Adaptive Multi-Rate Wideband (AMR-WB) speech codec. AMR-WB is the speech codec standardized by the 3GPP for the GSM and WCDMA 3G system. It is also selected as the ITU-T G. 722.2 standards. In AMR-WB speech codec VQ codeword search section, full search algorithm is used to find matching codeword. This requires a huge amount of computation. For large-size codebooks and high-dimensional vector of AMR-WB, computational complexity is significantly higher. The proposed fast codeword search method selects the codeword, which has the least absolute error component in VQ codebook, as the initial matching codeword. It can help to reduce computational complexity, whereas the reconstructed speech quality almost has no dropping. The article introduces the basic principle of the fast codeword search algorithm in detail. Simulation results show that the algorithm based on AMR-WB speech codec, can reduce the time of vector quantization codebook search and the w-PESQ of nine modes is no significant dropping.

关键词： Adaptive Multi-Rate Wideband (AMR-WB) speech codec full search algorithm Initial matching codeword least absolute error component fast codeword search algorithm

来源：评论

学校读者我要写书评

暂无评论

Motion estimation based on spatio-temporal correlations and pixel decimation

Motion estimation based on spatio-temporal correlations and ...

引用

Conference on Image and Video Communications and Processing 2005

作者： Sheinin, V IBM TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)0819456586

Based on motion estimation using spatio-temporal correlations, an enhanced search algorithm is proposed to further improve the performance in terms of reducing total amount of computations while preserving the video quality. Our experimental results show that the proposed algorithm has substantially smaller computational complexity having some quality reduction. For sequences with low motion PSNR reduction is around 0.1 dB and computational complexity is around 1700 times less than that of a full search.

关键词： block matching full search algorithm motion estimation search area determination

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：