“Measurement Matrix Interpolation Based on Projective Reconstruction for Factorization Method”

Shigeharu Kamijima, Hideo Saito

Research output: Contribution to journalArticle

Abstract

The factorization method by Tomasi and Kanade simultaneously recovers camera motion and object shape from an image sequence. This method is robust because the solution is linear by assuming the orthographic camera model. However, the only feature points that are tracked throughout the image sequence can be reconstructed, it is difficult to recover whole object shape by the factorization method. In this paper, we propose a new method to interpolate feature tracking so that even the loci of unseen feature points can be used as inputs of the factorization for object shape reconstruction. In this method, we employ projective reconstruction to interpolate un-tracked feature points. All loci of all detected feature points throughout the input image sequence provide correct reconstructed shape of the object via the factorization. The results of reconstruction are evaluated by the experiment using synthetic images and real images.

Original languageEnglish
Pages (from-to)576-585
Number of pages10
JournalJournal of the Institute of Image Electronics Engineers of Japan
Volume33
Issue number3
DOIs
Publication statusPublished - 2004

Fingerprint

Factorization
Interpolation
Cameras
Experiments

Keywords

  • 3D Shape Reconstruction
  • Factorization Method
  • Projected Position Estimation
  • Projective Reconstruction

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

@article{1b1cbca8160345b088cff10849351dd4,
title = "“Measurement Matrix Interpolation Based on Projective Reconstruction for Factorization Method”",
abstract = "The factorization method by Tomasi and Kanade simultaneously recovers camera motion and object shape from an image sequence. This method is robust because the solution is linear by assuming the orthographic camera model. However, the only feature points that are tracked throughout the image sequence can be reconstructed, it is difficult to recover whole object shape by the factorization method. In this paper, we propose a new method to interpolate feature tracking so that even the loci of unseen feature points can be used as inputs of the factorization for object shape reconstruction. In this method, we employ projective reconstruction to interpolate un-tracked feature points. All loci of all detected feature points throughout the input image sequence provide correct reconstructed shape of the object via the factorization. The results of reconstruction are evaluated by the experiment using synthetic images and real images.",
keywords = "3D Shape Reconstruction, Factorization Method, Projected Position Estimation, Projective Reconstruction",
author = "Shigeharu Kamijima and Hideo Saito",
year = "2004",
doi = "10.11371/iieej.33.576",
language = "English",
volume = "33",
pages = "576--585",
journal = "Journal of the Institute of Image Electronics Engineers of Japan",
issn = "0285-9831",
publisher = "Institute of Image Electronics Engineers of Japan",
number = "3",

}

TY - JOUR

T1 - “Measurement Matrix Interpolation Based on Projective Reconstruction for Factorization Method”

AU - Kamijima, Shigeharu

AU - Saito, Hideo

PY - 2004

Y1 - 2004

N2 - The factorization method by Tomasi and Kanade simultaneously recovers camera motion and object shape from an image sequence. This method is robust because the solution is linear by assuming the orthographic camera model. However, the only feature points that are tracked throughout the image sequence can be reconstructed, it is difficult to recover whole object shape by the factorization method. In this paper, we propose a new method to interpolate feature tracking so that even the loci of unseen feature points can be used as inputs of the factorization for object shape reconstruction. In this method, we employ projective reconstruction to interpolate un-tracked feature points. All loci of all detected feature points throughout the input image sequence provide correct reconstructed shape of the object via the factorization. The results of reconstruction are evaluated by the experiment using synthetic images and real images.

AB - The factorization method by Tomasi and Kanade simultaneously recovers camera motion and object shape from an image sequence. This method is robust because the solution is linear by assuming the orthographic camera model. However, the only feature points that are tracked throughout the image sequence can be reconstructed, it is difficult to recover whole object shape by the factorization method. In this paper, we propose a new method to interpolate feature tracking so that even the loci of unseen feature points can be used as inputs of the factorization for object shape reconstruction. In this method, we employ projective reconstruction to interpolate un-tracked feature points. All loci of all detected feature points throughout the input image sequence provide correct reconstructed shape of the object via the factorization. The results of reconstruction are evaluated by the experiment using synthetic images and real images.

KW - 3D Shape Reconstruction

KW - Factorization Method

KW - Projected Position Estimation

KW - Projective Reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85024734513&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024734513&partnerID=8YFLogxK

U2 - 10.11371/iieej.33.576

DO - 10.11371/iieej.33.576

M3 - Article

VL - 33

SP - 576

EP - 585

JO - Journal of the Institute of Image Electronics Engineers of Japan

JF - Journal of the Institute of Image Electronics Engineers of Japan

SN - 0285-9831

IS - 3

ER -