A hardware implementation of a content-based motion estimation algorithm for real-time MPEG-4 video coding

Shen Li, Takeshi Ikenaga, Hideki Takeda, Masataka Matsui, Satoshi Goto

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Power efficiency and real-time processing capability are two major issues in today's mobile video applications. We proposed a novel Motion Estimation (ME) engine for power-efficient real-time MPEG-4 video coding based on our previously proposed content-based ME algorithm [8], [13]. By adopting Full Search (FS) and Three Step Search (TSS) alternatively according to the nature of video contents, this algorithm keeps the visual quality very close to that of FS with only 3% of its computational power. We designed a flexible Block Matching (BM) Unit with 16-PE SIMD data path so that the adaptive ME can be performed at a much lower clock frequency and hardware cost as compared with previous FS based work. To reduce the energy cost caused by excessive external memory access, on-chip SRAM is also utilized and optimized for parallel processing in the BM Unit. The ME engine is fabricated with TSMC 0.18 μm technology. When processing QCIF (15 fps) video, the estimated power is 2.88 mW@4.16 MHz (supply voltage: 1.62 V). It is believed to be a favorable contribution to the video encoder LSI design for mobile applications.

Original languageEnglish
Pages (from-to)932-939
Number of pages8
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE89-A
Issue number4
DOIs
Publication statusPublished - 2006 Apr

Fingerprint

MPEG-4
Video Coding
Motion Estimation
Hardware Implementation
Motion estimation
Estimation Algorithms
Image coding
Real-time
Hardware
Block Matching
Engine
Processing
Engines
External Memory
Adaptive Estimation
Unit
Mobile Applications
Static random access storage
Costs
Encoder

Keywords

  • Content-based
  • Motion estimation
  • MPEG-4
  • Power-efficient
  • Real-time

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Information Systems

Cite this

A hardware implementation of a content-based motion estimation algorithm for real-time MPEG-4 video coding. / Li, Shen; Ikenaga, Takeshi; Takeda, Hideki; Matsui, Masataka; Goto, Satoshi.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E89-A, No. 4, 04.2006, p. 932-939.

Research output: Contribution to journalArticle

@article{9ea964e7a7d04893afd5790bc092f36f,
title = "A hardware implementation of a content-based motion estimation algorithm for real-time MPEG-4 video coding",
abstract = "Power efficiency and real-time processing capability are two major issues in today's mobile video applications. We proposed a novel Motion Estimation (ME) engine for power-efficient real-time MPEG-4 video coding based on our previously proposed content-based ME algorithm [8], [13]. By adopting Full Search (FS) and Three Step Search (TSS) alternatively according to the nature of video contents, this algorithm keeps the visual quality very close to that of FS with only 3{\%} of its computational power. We designed a flexible Block Matching (BM) Unit with 16-PE SIMD data path so that the adaptive ME can be performed at a much lower clock frequency and hardware cost as compared with previous FS based work. To reduce the energy cost caused by excessive external memory access, on-chip SRAM is also utilized and optimized for parallel processing in the BM Unit. The ME engine is fabricated with TSMC 0.18 μm technology. When processing QCIF (15 fps) video, the estimated power is 2.88 mW@4.16 MHz (supply voltage: 1.62 V). It is believed to be a favorable contribution to the video encoder LSI design for mobile applications.",
keywords = "Content-based, Motion estimation, MPEG-4, Power-efficient, Real-time",
author = "Shen Li and Takeshi Ikenaga and Hideki Takeda and Masataka Matsui and Satoshi Goto",
year = "2006",
month = "4",
doi = "10.1093/ietfec/e89-a.4.932",
language = "English",
volume = "E89-A",
pages = "932--939",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "4",

}

TY - JOUR

T1 - A hardware implementation of a content-based motion estimation algorithm for real-time MPEG-4 video coding

AU - Li, Shen

AU - Ikenaga, Takeshi

AU - Takeda, Hideki

AU - Matsui, Masataka

AU - Goto, Satoshi

PY - 2006/4

Y1 - 2006/4

N2 - Power efficiency and real-time processing capability are two major issues in today's mobile video applications. We proposed a novel Motion Estimation (ME) engine for power-efficient real-time MPEG-4 video coding based on our previously proposed content-based ME algorithm [8], [13]. By adopting Full Search (FS) and Three Step Search (TSS) alternatively according to the nature of video contents, this algorithm keeps the visual quality very close to that of FS with only 3% of its computational power. We designed a flexible Block Matching (BM) Unit with 16-PE SIMD data path so that the adaptive ME can be performed at a much lower clock frequency and hardware cost as compared with previous FS based work. To reduce the energy cost caused by excessive external memory access, on-chip SRAM is also utilized and optimized for parallel processing in the BM Unit. The ME engine is fabricated with TSMC 0.18 μm technology. When processing QCIF (15 fps) video, the estimated power is 2.88 mW@4.16 MHz (supply voltage: 1.62 V). It is believed to be a favorable contribution to the video encoder LSI design for mobile applications.

AB - Power efficiency and real-time processing capability are two major issues in today's mobile video applications. We proposed a novel Motion Estimation (ME) engine for power-efficient real-time MPEG-4 video coding based on our previously proposed content-based ME algorithm [8], [13]. By adopting Full Search (FS) and Three Step Search (TSS) alternatively according to the nature of video contents, this algorithm keeps the visual quality very close to that of FS with only 3% of its computational power. We designed a flexible Block Matching (BM) Unit with 16-PE SIMD data path so that the adaptive ME can be performed at a much lower clock frequency and hardware cost as compared with previous FS based work. To reduce the energy cost caused by excessive external memory access, on-chip SRAM is also utilized and optimized for parallel processing in the BM Unit. The ME engine is fabricated with TSMC 0.18 μm technology. When processing QCIF (15 fps) video, the estimated power is 2.88 mW@4.16 MHz (supply voltage: 1.62 V). It is believed to be a favorable contribution to the video encoder LSI design for mobile applications.

KW - Content-based

KW - Motion estimation

KW - MPEG-4

KW - Power-efficient

KW - Real-time

UR - http://www.scopus.com/inward/record.url?scp=33646257053&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646257053&partnerID=8YFLogxK

U2 - 10.1093/ietfec/e89-a.4.932

DO - 10.1093/ietfec/e89-a.4.932

M3 - Article

AN - SCOPUS:33646257053

VL - E89-A

SP - 932

EP - 939

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 4

ER -