A new optimized FME hardware structure for QFHD video

He Qian; Satoshi Goto

doi:10.1109/CSPA.2011.5759860

A new optimized FME hardware structure for QFHD video

He Qian^*, Satoshi Goto

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Motion Estimation is the most complex part in H.264 encoder which takes more than 90% time in baseline profile while making test encoding using JM15.1. In the motion estimation stage, macro block cost calculation is very important for motion vector prediction and bit stream estimation. As a new characteristic introduced in H.264, Fractional ME is an essential part for improving encoder efficiency. In this paper we tried to promote another order of progress structure, and based on the rearranged structure stages we analyzed the MB cost data. Taking the mathematical characteristics of cost distribution while calculating SATD, we can make an idea of how to reduce the complexity. Thus, further reduction of hardware cost can be estimated.

Original language	English
Title of host publication	Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
Pages	142-145
Number of pages	4
DOIs	https://doi.org/10.1109/CSPA.2011.5759860
Publication status	Published - 2011
Event	2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 - Penang Duration: 2011 Mar 4 → 2011 Mar 6

Other

Other	2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
City	Penang
Period	11/3/4 → 11/3/6

Keywords

H264/AVC encoding
Hadamard Transform
MB Cost
SATD

ASJC Scopus subject areas

Signal Processing

Access to Document

10.1109/CSPA.2011.5759860

Cite this

@inproceedings{4e870039f3d24a74a1554a0de6e0cc59,

title = "A new optimized FME hardware structure for QFHD video",

abstract = "Motion Estimation is the most complex part in H.264 encoder which takes more than 90% time in baseline profile while making test encoding using JM15.1. In the motion estimation stage, macro block cost calculation is very important for motion vector prediction and bit stream estimation. As a new characteristic introduced in H.264, Fractional ME is an essential part for improving encoder efficiency. In this paper we tried to promote another order of progress structure, and based on the rearranged structure stages we analyzed the MB cost data. Taking the mathematical characteristics of cost distribution while calculating SATD, we can make an idea of how to reduce the complexity. Thus, further reduction of hardware cost can be estimated.",

keywords = "H264/AVC encoding, Hadamard Transform, MB Cost, SATD",

author = "He Qian and Satoshi Goto",

year = "2011",

doi = "10.1109/CSPA.2011.5759860",

language = "English",

isbn = "9781612844145",

pages = "142--145",

booktitle = "Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011",

note = "2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 ; Conference date: 04-03-2011 Through 06-03-2011",

}

TY - GEN

T1 - A new optimized FME hardware structure for QFHD video

AU - Qian, He

AU - Goto, Satoshi

PY - 2011

Y1 - 2011

N2 - Motion Estimation is the most complex part in H.264 encoder which takes more than 90% time in baseline profile while making test encoding using JM15.1. In the motion estimation stage, macro block cost calculation is very important for motion vector prediction and bit stream estimation. As a new characteristic introduced in H.264, Fractional ME is an essential part for improving encoder efficiency. In this paper we tried to promote another order of progress structure, and based on the rearranged structure stages we analyzed the MB cost data. Taking the mathematical characteristics of cost distribution while calculating SATD, we can make an idea of how to reduce the complexity. Thus, further reduction of hardware cost can be estimated.

AB - Motion Estimation is the most complex part in H.264 encoder which takes more than 90% time in baseline profile while making test encoding using JM15.1. In the motion estimation stage, macro block cost calculation is very important for motion vector prediction and bit stream estimation. As a new characteristic introduced in H.264, Fractional ME is an essential part for improving encoder efficiency. In this paper we tried to promote another order of progress structure, and based on the rearranged structure stages we analyzed the MB cost data. Taking the mathematical characteristics of cost distribution while calculating SATD, we can make an idea of how to reduce the complexity. Thus, further reduction of hardware cost can be estimated.

KW - H264/AVC encoding

KW - Hadamard Transform

KW - MB Cost

KW - SATD

UR - http://www.scopus.com/inward/record.url?scp=79957481243&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957481243&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2011.5759860

DO - 10.1109/CSPA.2011.5759860

M3 - Conference contribution

AN - SCOPUS:79957481243

SN - 9781612844145

SP - 142

EP - 145

BT - Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011

T2 - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011

Y2 - 4 March 2011 through 6 March 2011

ER -

A new optimized FME hardware structure for QFHD video

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this