Precision of Global Motion Parameter Detection in Interactive Semantic/Model-Based Image Coding

Kazuo Ohzeki

Research output: Contribution to journalArticle

Abstract

Video network is beginning to have various kinds of applications such as using a vertical blanking interval. Model-based coding is suitable for the narrow band network. Interactive model-based image coding, which had been developed for non-realtime environment, needs to be specified by the number and the precision of interactive operations. This paper first analyzes the noise in input feature points during the global motion parameter detection. Then a new structure filter for reducing the noise in the feature points on a facial wireframe model is developed. The structure filter keeps original facial shape composed of feature points and reduces variation in the mutual distance between the feature points. In evaluating the precision for applying the least-squares method for detecting depth and global motion parameters, the number of conditions of input data is considered from the point of variance of error of the estimated values. Based on the structure filter with the precision evaluation, the allowance error in the interactive operation for the encoding process is specified by the pixel accuracy for feature point position.

Original languageEnglish
Pages (from-to)871-880
Number of pages10
JournalKyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
Volume52
Issue number6
Publication statusPublished - 1998
Externally publishedYes

Fingerprint

Image coding
Semantics
Pixels

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition

Cite this

@article{7787624870f0416eb82eae982ca80d19,
title = "Precision of Global Motion Parameter Detection in Interactive Semantic/Model-Based Image Coding",
abstract = "Video network is beginning to have various kinds of applications such as using a vertical blanking interval. Model-based coding is suitable for the narrow band network. Interactive model-based image coding, which had been developed for non-realtime environment, needs to be specified by the number and the precision of interactive operations. This paper first analyzes the noise in input feature points during the global motion parameter detection. Then a new structure filter for reducing the noise in the feature points on a facial wireframe model is developed. The structure filter keeps original facial shape composed of feature points and reduces variation in the mutual distance between the feature points. In evaluating the precision for applying the least-squares method for detecting depth and global motion parameters, the number of conditions of input data is considered from the point of variance of error of the estimated values. Based on the structure filter with the precision evaluation, the allowance error in the interactive operation for the encoding process is specified by the pixel accuracy for feature point position.",
author = "Kazuo Ohzeki",
year = "1998",
language = "English",
volume = "52",
pages = "871--880",
journal = "Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers",
issn = "1342-6907",
publisher = "Institute of Image Information and Television Engineers",
number = "6",

}

TY - JOUR

T1 - Precision of Global Motion Parameter Detection in Interactive Semantic/Model-Based Image Coding

AU - Ohzeki, Kazuo

PY - 1998

Y1 - 1998

N2 - Video network is beginning to have various kinds of applications such as using a vertical blanking interval. Model-based coding is suitable for the narrow band network. Interactive model-based image coding, which had been developed for non-realtime environment, needs to be specified by the number and the precision of interactive operations. This paper first analyzes the noise in input feature points during the global motion parameter detection. Then a new structure filter for reducing the noise in the feature points on a facial wireframe model is developed. The structure filter keeps original facial shape composed of feature points and reduces variation in the mutual distance between the feature points. In evaluating the precision for applying the least-squares method for detecting depth and global motion parameters, the number of conditions of input data is considered from the point of variance of error of the estimated values. Based on the structure filter with the precision evaluation, the allowance error in the interactive operation for the encoding process is specified by the pixel accuracy for feature point position.

AB - Video network is beginning to have various kinds of applications such as using a vertical blanking interval. Model-based coding is suitable for the narrow band network. Interactive model-based image coding, which had been developed for non-realtime environment, needs to be specified by the number and the precision of interactive operations. This paper first analyzes the noise in input feature points during the global motion parameter detection. Then a new structure filter for reducing the noise in the feature points on a facial wireframe model is developed. The structure filter keeps original facial shape composed of feature points and reduces variation in the mutual distance between the feature points. In evaluating the precision for applying the least-squares method for detecting depth and global motion parameters, the number of conditions of input data is considered from the point of variance of error of the estimated values. Based on the structure filter with the precision evaluation, the allowance error in the interactive operation for the encoding process is specified by the pixel accuracy for feature point position.

UR - http://www.scopus.com/inward/record.url?scp=0032091716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032091716&partnerID=8YFLogxK

M3 - Article

VL - 52

SP - 871

EP - 880

JO - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

JF - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

SN - 1342-6907

IS - 6

ER -