A New IDCT and Motion Compensation Algorithm Based on VLIW OU-YANG Wan-li,XIAO Chuang-Bai,LIU Guang

OU-YANG Wan-li; XIAO Chuang-Bai; LIU Guang

您当前的位置：

首页 >

文章列表页 >

A New IDCT and Motion Compensation Algorithm Based on VLIW OU-YANG Wan-li,XIAO Chuang-Bai,LIU Guang

更新时间：2025-07-16

- A New IDCT and Motion Compensation Algorithm Based on VLIW OU-YANG Wan-li,XIAO Chuang-Bai,LIU Guang
- Acta Electronica Sinica Vol. 33, Issue 11, Pages: 2074-2079(2005)
- 作者机构：
  
  北京工业大学计算机学院,北京,100022
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.41
- Published：2005
- 稿件说明：
移动端阅览
OU-YANG Wan-li, XIAO Chuang-Bai, LIU Guang. A New IDCT and Motion Compensation Algorithm Based on VLIW OU-YANG Wan-li,XIAO Chuang-Bai,LIU Guang[J]. Acta Electronica Sinica, 2005, 33(11): 2074-2079.
DOI：

OU-YANG Wan-li, XIAO Chuang-Bai, LIU Guang. A New IDCT and Motion Compensation Algorithm Based on VLIW OU-YANG Wan-li,XIAO Chuang-Bai,LIU Guang[J]. Acta Electronica Sinica, 2005, 33(11): 2074-2079. DOI：

摘要

本文使用矩阵形式在超长指令字(VLIW)的观点下将几种经典算法与已有的适合于VLIW的算法进行了比较.然后利用VLIW结构的特性

提出了一种快速IDCT算法.与现有算法相比

新算法进一步减少了所需的指令周期.并利用VLIW结构的寄存器特性

将视频编解码过程中的运动补偿(预测)和IDCT(DCT)组合

使运动补偿所需时间降低为原来的约50%

这种思想能应用于MPEG1/2/4

H.263和H.264.

Abstract

In this paper

using a very long instruction word (VLIW) architecture view

the existing state of the art algorithms were compared with an algorithm that is tailored for VLIW architecture in the form of matrix.The architecture's character is further exploited to design a new fast inverse discrete cosine transform (IDCT) algorithm.Compared with existing algorithms

the new algorithm reduces the number of instruction cycles needed.Further

the register character of VLIW is used for merging motion compensation with IDCT (DCT) in the video codec process.This achieves 50% speed improvement.The concept is applicable for MPEG1/2/4 and H.264/AVC.

关键词

Keywords

references

Views

752

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Motion Compensation Optimization Method for 3D Multi-Object Tracking

Video Compressed Sensing Reconstruction Network Based on Temporal-Attention Feature Alignment

Via-Aware Parallel Layer Assignment Algorithm for VLSI Physical Design

Error Concealment for Frame Losses in MVD Video Using Saliency

Fast Antenna Selection Algorithm in Amplify-and-Forward MIMO Relay Systems

Related Author

WANG Shun-hong

ZHANG Yu

SHEN Jiang-nan

JI Jian-min

ZHANG Yan-yong

WEI Zhi-chao

YANG Chun-ling

LIU Geng-geng

Related Institution

School of Computer Science and Technology， University of Science and Technology of China

School of Electronic and Information Engineering, South China University of Technology

College of Computer and Data Science, Fuzhou University

School of Information Engineering, Wuhan University of Technology

School of Telecommunication Engineering, Hangzhou Dianzi University

⁰