A matching method using edges with the rigid body assumption

Shiho Tanaka, Toshio Ito, Takenao Ohkawa

Research output: Contribution to journalArticle

Abstract

In this paper, we propose the matching method using the edge image with the rigid-body assumption. We introduce the virtual intensity added to the edge image and regard it as the energy function. It is assumed that the objects to match each other are rigid. The edges are repeatedly moved to the direction which the energy function is reduced by parallel translation and rotation. The corresponding point between two images can be found when the function is minimum. Real images include the areas which have no or extreme intensity change. The proposed method is available in those cases since it uses features of the image, that is, the edges. We showed this advantage by experiments on motion estimation.

Original languageEnglish
Pages (from-to)28-33
Number of pages6
JournalElectronics and Communications in Japan
Volume92
Issue number11
DOIs
Publication statusPublished - 2009 Nov
Externally publishedYes

Fingerprint

rigid structures
Motion estimation
Experiments
energy

Keywords

  • Edge
  • Matching
  • Motion estimation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Physics and Astronomy(all)
  • Signal Processing
  • Applied Mathematics

Cite this

A matching method using edges with the rigid body assumption. / Tanaka, Shiho; Ito, Toshio; Ohkawa, Takenao.

In: Electronics and Communications in Japan, Vol. 92, No. 11, 11.2009, p. 28-33.

Research output: Contribution to journalArticle

Tanaka, Shiho ; Ito, Toshio ; Ohkawa, Takenao. / A matching method using edges with the rigid body assumption. In: Electronics and Communications in Japan. 2009 ; Vol. 92, No. 11. pp. 28-33.
@article{39ec6441f0ea438cb9210c95c53410b5,
title = "A matching method using edges with the rigid body assumption",
abstract = "In this paper, we propose the matching method using the edge image with the rigid-body assumption. We introduce the virtual intensity added to the edge image and regard it as the energy function. It is assumed that the objects to match each other are rigid. The edges are repeatedly moved to the direction which the energy function is reduced by parallel translation and rotation. The corresponding point between two images can be found when the function is minimum. Real images include the areas which have no or extreme intensity change. The proposed method is available in those cases since it uses features of the image, that is, the edges. We showed this advantage by experiments on motion estimation.",
keywords = "Edge, Matching, Motion estimation",
author = "Shiho Tanaka and Toshio Ito and Takenao Ohkawa",
year = "2009",
month = "11",
doi = "10.1002/ecj.10148",
language = "English",
volume = "92",
pages = "28--33",
journal = "Electronics and Communications in Japan",
issn = "1942-9533",
publisher = "Scripta Technica",
number = "11",

}

TY - JOUR

T1 - A matching method using edges with the rigid body assumption

AU - Tanaka, Shiho

AU - Ito, Toshio

AU - Ohkawa, Takenao

PY - 2009/11

Y1 - 2009/11

N2 - In this paper, we propose the matching method using the edge image with the rigid-body assumption. We introduce the virtual intensity added to the edge image and regard it as the energy function. It is assumed that the objects to match each other are rigid. The edges are repeatedly moved to the direction which the energy function is reduced by parallel translation and rotation. The corresponding point between two images can be found when the function is minimum. Real images include the areas which have no or extreme intensity change. The proposed method is available in those cases since it uses features of the image, that is, the edges. We showed this advantage by experiments on motion estimation.

AB - In this paper, we propose the matching method using the edge image with the rigid-body assumption. We introduce the virtual intensity added to the edge image and regard it as the energy function. It is assumed that the objects to match each other are rigid. The edges are repeatedly moved to the direction which the energy function is reduced by parallel translation and rotation. The corresponding point between two images can be found when the function is minimum. Real images include the areas which have no or extreme intensity change. The proposed method is available in those cases since it uses features of the image, that is, the edges. We showed this advantage by experiments on motion estimation.

KW - Edge

KW - Matching

KW - Motion estimation

UR - http://www.scopus.com/inward/record.url?scp=70450186952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450186952&partnerID=8YFLogxK

U2 - 10.1002/ecj.10148

DO - 10.1002/ecj.10148

M3 - Article

VL - 92

SP - 28

EP - 33

JO - Electronics and Communications in Japan

JF - Electronics and Communications in Japan

SN - 1942-9533

IS - 11

ER -