Low-power partial distortion sorting fast motion estimation algorithms and VLSI implementations

Yang Song, Zhenyu Liu, Takeshi Ikenaga, Satoshi Goto

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper presents two hardware-friendly low-power oriented fast motion estimation (ME) algorithms and their VLSI implementations. The basic idea of the proposed partial distortion sorting (PDS) algorithm is to disable the search points which have larger partial distortions during the ME process, and only keep those search points with smaller ones. To further reduce the computation overhead, a simplified local PDS (LPDS) algorithm is also presented. Experiments show that the PDS and LPDS algorithms can provide almost the same image quality as full search only with 36.7 computation complexity. The proposed two algorithms can be integrated into different FSBMA architectures to save power consumption. In this paper, the 1-D inter ME architecture [12] is used as an detailed example. Under the worst working conditions (1.62 V, 125°C) and 166 MHz clock frequency, the PDS algorithm can reduce 33.3 power consumption with 4.05 K gates extra hardware cost, and the LPDS can reduce 37.8 power consumption with 1.73 K gates overhead.

Original languageEnglish
Pages (from-to)108-117
Number of pages10
JournalIEICE Transactions on Information and Systems
VolumeE90-D
Issue number1
DOIs
Publication statusPublished - 2007 Jan

Fingerprint

Motion estimation
Sorting
Electric power utilization
Hardware
Image quality
Clocks
Costs
Experiments

Keywords

  • Motion estimation (ME)
  • Partial distortion sorting (PDS)
  • Systolic array architecture

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Low-power partial distortion sorting fast motion estimation algorithms and VLSI implementations. / Song, Yang; Liu, Zhenyu; Ikenaga, Takeshi; Goto, Satoshi.

In: IEICE Transactions on Information and Systems, Vol. E90-D, No. 1, 01.2007, p. 108-117.

Research output: Contribution to journalArticle

@article{bbd819f9d1ef4721a50ca49813981609,
title = "Low-power partial distortion sorting fast motion estimation algorithms and VLSI implementations",
abstract = "This paper presents two hardware-friendly low-power oriented fast motion estimation (ME) algorithms and their VLSI implementations. The basic idea of the proposed partial distortion sorting (PDS) algorithm is to disable the search points which have larger partial distortions during the ME process, and only keep those search points with smaller ones. To further reduce the computation overhead, a simplified local PDS (LPDS) algorithm is also presented. Experiments show that the PDS and LPDS algorithms can provide almost the same image quality as full search only with 36.7 computation complexity. The proposed two algorithms can be integrated into different FSBMA architectures to save power consumption. In this paper, the 1-D inter ME architecture [12] is used as an detailed example. Under the worst working conditions (1.62 V, 125°C) and 166 MHz clock frequency, the PDS algorithm can reduce 33.3 power consumption with 4.05 K gates extra hardware cost, and the LPDS can reduce 37.8 power consumption with 1.73 K gates overhead.",
keywords = "Motion estimation (ME), Partial distortion sorting (PDS), Systolic array architecture",
author = "Yang Song and Zhenyu Liu and Takeshi Ikenaga and Satoshi Goto",
year = "2007",
month = "1",
doi = "10.1093/ietisy/e90-1.1.108",
language = "English",
volume = "E90-D",
pages = "108--117",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "1",

}

TY - JOUR

T1 - Low-power partial distortion sorting fast motion estimation algorithms and VLSI implementations

AU - Song, Yang

AU - Liu, Zhenyu

AU - Ikenaga, Takeshi

AU - Goto, Satoshi

PY - 2007/1

Y1 - 2007/1

N2 - This paper presents two hardware-friendly low-power oriented fast motion estimation (ME) algorithms and their VLSI implementations. The basic idea of the proposed partial distortion sorting (PDS) algorithm is to disable the search points which have larger partial distortions during the ME process, and only keep those search points with smaller ones. To further reduce the computation overhead, a simplified local PDS (LPDS) algorithm is also presented. Experiments show that the PDS and LPDS algorithms can provide almost the same image quality as full search only with 36.7 computation complexity. The proposed two algorithms can be integrated into different FSBMA architectures to save power consumption. In this paper, the 1-D inter ME architecture [12] is used as an detailed example. Under the worst working conditions (1.62 V, 125°C) and 166 MHz clock frequency, the PDS algorithm can reduce 33.3 power consumption with 4.05 K gates extra hardware cost, and the LPDS can reduce 37.8 power consumption with 1.73 K gates overhead.

AB - This paper presents two hardware-friendly low-power oriented fast motion estimation (ME) algorithms and their VLSI implementations. The basic idea of the proposed partial distortion sorting (PDS) algorithm is to disable the search points which have larger partial distortions during the ME process, and only keep those search points with smaller ones. To further reduce the computation overhead, a simplified local PDS (LPDS) algorithm is also presented. Experiments show that the PDS and LPDS algorithms can provide almost the same image quality as full search only with 36.7 computation complexity. The proposed two algorithms can be integrated into different FSBMA architectures to save power consumption. In this paper, the 1-D inter ME architecture [12] is used as an detailed example. Under the worst working conditions (1.62 V, 125°C) and 166 MHz clock frequency, the PDS algorithm can reduce 33.3 power consumption with 4.05 K gates extra hardware cost, and the LPDS can reduce 37.8 power consumption with 1.73 K gates overhead.

KW - Motion estimation (ME)

KW - Partial distortion sorting (PDS)

KW - Systolic array architecture

UR - http://www.scopus.com/inward/record.url?scp=33846444035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846444035&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e90-1.1.108

DO - 10.1093/ietisy/e90-1.1.108

M3 - Article

AN - SCOPUS:33846444035

VL - E90-D

SP - 108

EP - 117

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 1

ER -