Superresolved image synthesis for multiple-plane scenes captured with an uncalibrated moving camera

Shinichiro Sei, Hideo Saito

Research output: Contribution to journalArticle

Abstract

In this paper, the authors propose a method to take a video sequence photographed with an uncalihrated moving camera and use the projected relationship between each frame in the sequence to merge all the frames together and generate a superresolved image, that is, one with higher resolution than the source images. By assuming that the scene can he approximated with multiple plane patches, the images are merged using a homography derived from a fundamental matrix estimated across each frame for each plane patch. In this method, blurring occurs in the generated image as a result of positional errors in the images being synthesizd: this is turned to advantage in an optimization process that maximizes the energy of the high-frequency components in the generated image; the correspondence among plane-patch vertex frames, needed to derive the homography, is used to estimate subpixel precision. To prove the effectiveness of this method, the authors conducted experiments with actual images and were able to improve resolution beyond the level of the original image.

Original languageEnglish
Pages (from-to)62-71
Number of pages10
JournalSystems and Computers in Japan
Volume36
Issue number10
DOIs
Publication statusPublished - 2005 Sep

Fingerprint

Camera
Cameras
Synthesis
Experiments
Patch
Homography
Fundamental Matrix
Sub-pixel
Process Optimization
High Resolution
Correspondence
Maximise
Vertex of a graph
Energy
Estimate
Experiment

Keywords

  • Fundamental matrix
  • Homography
  • Projection geometry
  • Superresolved image synthesis
  • Uncalibrated camera

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Superresolved image synthesis for multiple-plane scenes captured with an uncalibrated moving camera. / Sei, Shinichiro; Saito, Hideo.

In: Systems and Computers in Japan, Vol. 36, No. 10, 09.2005, p. 62-71.

Research output: Contribution to journalArticle

@article{d510ff7502384f1697a532b729ceb1d2,
title = "Superresolved image synthesis for multiple-plane scenes captured with an uncalibrated moving camera",
abstract = "In this paper, the authors propose a method to take a video sequence photographed with an uncalihrated moving camera and use the projected relationship between each frame in the sequence to merge all the frames together and generate a superresolved image, that is, one with higher resolution than the source images. By assuming that the scene can he approximated with multiple plane patches, the images are merged using a homography derived from a fundamental matrix estimated across each frame for each plane patch. In this method, blurring occurs in the generated image as a result of positional errors in the images being synthesizd: this is turned to advantage in an optimization process that maximizes the energy of the high-frequency components in the generated image; the correspondence among plane-patch vertex frames, needed to derive the homography, is used to estimate subpixel precision. To prove the effectiveness of this method, the authors conducted experiments with actual images and were able to improve resolution beyond the level of the original image.",
keywords = "Fundamental matrix, Homography, Projection geometry, Superresolved image synthesis, Uncalibrated camera",
author = "Shinichiro Sei and Hideo Saito",
year = "2005",
month = "9",
doi = "10.1002/scj.10597",
language = "English",
volume = "36",
pages = "62--71",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "10",

}

TY - JOUR

T1 - Superresolved image synthesis for multiple-plane scenes captured with an uncalibrated moving camera

AU - Sei, Shinichiro

AU - Saito, Hideo

PY - 2005/9

Y1 - 2005/9

N2 - In this paper, the authors propose a method to take a video sequence photographed with an uncalihrated moving camera and use the projected relationship between each frame in the sequence to merge all the frames together and generate a superresolved image, that is, one with higher resolution than the source images. By assuming that the scene can he approximated with multiple plane patches, the images are merged using a homography derived from a fundamental matrix estimated across each frame for each plane patch. In this method, blurring occurs in the generated image as a result of positional errors in the images being synthesizd: this is turned to advantage in an optimization process that maximizes the energy of the high-frequency components in the generated image; the correspondence among plane-patch vertex frames, needed to derive the homography, is used to estimate subpixel precision. To prove the effectiveness of this method, the authors conducted experiments with actual images and were able to improve resolution beyond the level of the original image.

AB - In this paper, the authors propose a method to take a video sequence photographed with an uncalihrated moving camera and use the projected relationship between each frame in the sequence to merge all the frames together and generate a superresolved image, that is, one with higher resolution than the source images. By assuming that the scene can he approximated with multiple plane patches, the images are merged using a homography derived from a fundamental matrix estimated across each frame for each plane patch. In this method, blurring occurs in the generated image as a result of positional errors in the images being synthesizd: this is turned to advantage in an optimization process that maximizes the energy of the high-frequency components in the generated image; the correspondence among plane-patch vertex frames, needed to derive the homography, is used to estimate subpixel precision. To prove the effectiveness of this method, the authors conducted experiments with actual images and were able to improve resolution beyond the level of the original image.

KW - Fundamental matrix

KW - Homography

KW - Projection geometry

KW - Superresolved image synthesis

KW - Uncalibrated camera

UR - http://www.scopus.com/inward/record.url?scp=30544432473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30544432473&partnerID=8YFLogxK

U2 - 10.1002/scj.10597

DO - 10.1002/scj.10597

M3 - Article

AN - SCOPUS:30544432473

VL - 36

SP - 62

EP - 71

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 10

ER -