Estimating Motion Information Using Multiple Features

SeokWoo Jang

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2005, 10(2), pp.1-10
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

SeokWoo Jang ¹

¹한국건설기술연구원

ABSTRACT

In this paper, we propose a new block matching algorithm that extracts motion vectors from consecutive range data. The proposed method defines a matching metric that integrates intensity, hue, and range. Our algorithm begins matching with a small matching template. If the matching degree is not good enough, we slightly expand the size of a matching template and then repeat the matching process until our matching criterion is satisfied or the predetermined maximum size has been reached. As the iteration proceeds, we adaptively adjust weights of the matching metric by considering the importance of each feature. In the experiments, we show that our block matching approach can work as a promising solution by comparing the proposed method with previously known method in terms of performance.
KEYWORDS

range data, block matching, matching metric, weight adjustment, motion vector
REFERENCES (10)

[journal] / 2005. / 組細 단계를 이용한 光流검출 알고리즘 10(1) : 223~229

[journal] / 1994. / New Fast Algorithms for the Estimation of Block Motion Vectors 3(2) : 438~441

[journal] / 1994. / A New Three-Step Search Algorithm for Block Motion Estimation 4(4) : 438~441

[journal] / 1996. / A Novel Four-Step Algorithm for Fast Block Motion Estimation 6(3) : 313~317

[journal] / 2000. / Accurate Estimation of Motion Vectors Using Active Block Matching : 527~531

[journal] / 2001. / Improving Quality and Speed of Range Data for Communication : 348~353

[journal] / 2004. / Gesture Recognition Using Bezier Curves for Visualization Navigation from Registered 3-D Data 37(5) : 1011~1024

[journal] / 2004. / Emerging Topics in Computer Vision / Prentice Hall : 122~145

[journal] / 2005. / 인터넷상의 동영상에서의 물체 특징 점 탐지 및 추적 10(1) : 149~156

[journal] / 2004 / A Thresholding Method Based on Two-Dimensional Renyi's Entropy 2004.저 자 소 개장 석 우2000년 8월 숭실대학교 대학원 컴퓨터학과 졸업 2003년 10월 - 현재 한국건설기술연구원 선임연구원 비디오 색인 및 검색 37 : 1149~1161
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools