Registration of an uncalibrated image pair to a 3D surface model

Zsolt Jankó, D. Chetverikov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

The following data fusion problem is considered: Given a 3D geometric model of an object and two uncalibrated images of the same object, and assuming that the object surface is textured and Lambertian, precisely register the images to the model. Solving this problem is necessary for building a geometrically accurate, photorealistic model from laser-scanned 3D data and high quality images. We generalise the photo-consistency approach by Clarkson et al. to the case of uncalibrated cameras, when both intrinsic and extrinsic parameters are unknown. This gives a user the freedom of taking the pictures by a conventional digital camera, from arbitrary positions and with varying zoom. We discuss a number of possible approaches to the problem and propose a method based on manual pre-registration followed by a genetic optimisation algorithm. The issues of speed and robustness are addressed. Results for real data are shown.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages208-211
Number of pages4
Volume2
Publication statusPublished - 2004
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: Aug 23 2004Aug 26 2004

Other

OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
CountryUnited Kingdom
CityCambridge
Period8/23/048/26/04

Fingerprint

Digital cameras
Data fusion
Image quality
Cameras
Lasers

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Jankó, Z., & Chetverikov, D. (2004). Registration of an uncalibrated image pair to a 3D surface model. In J. Kittler, M. Petrou, & M. Nixon (Eds.), Proceedings - International Conference on Pattern Recognition (Vol. 2, pp. 208-211)

Registration of an uncalibrated image pair to a 3D surface model. / Jankó, Zsolt; Chetverikov, D.

Proceedings - International Conference on Pattern Recognition. ed. / J. Kittler; M. Petrou; M. Nixon. Vol. 2 2004. p. 208-211.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jankó, Z & Chetverikov, D 2004, Registration of an uncalibrated image pair to a 3D surface model. in J Kittler, M Petrou & M Nixon (eds), Proceedings - International Conference on Pattern Recognition. vol. 2, pp. 208-211, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, United Kingdom, 8/23/04.
Jankó Z, Chetverikov D. Registration of an uncalibrated image pair to a 3D surface model. In Kittler J, Petrou M, Nixon M, editors, Proceedings - International Conference on Pattern Recognition. Vol. 2. 2004. p. 208-211
Jankó, Zsolt ; Chetverikov, D. / Registration of an uncalibrated image pair to a 3D surface model. Proceedings - International Conference on Pattern Recognition. editor / J. Kittler ; M. Petrou ; M. Nixon. Vol. 2 2004. pp. 208-211
@inproceedings{a202252ab61f436699657e9123a84a05,
title = "Registration of an uncalibrated image pair to a 3D surface model",
abstract = "The following data fusion problem is considered: Given a 3D geometric model of an object and two uncalibrated images of the same object, and assuming that the object surface is textured and Lambertian, precisely register the images to the model. Solving this problem is necessary for building a geometrically accurate, photorealistic model from laser-scanned 3D data and high quality images. We generalise the photo-consistency approach by Clarkson et al. to the case of uncalibrated cameras, when both intrinsic and extrinsic parameters are unknown. This gives a user the freedom of taking the pictures by a conventional digital camera, from arbitrary positions and with varying zoom. We discuss a number of possible approaches to the problem and propose a method based on manual pre-registration followed by a genetic optimisation algorithm. The issues of speed and robustness are addressed. Results for real data are shown.",
author = "Zsolt Jank{\'o} and D. Chetverikov",
year = "2004",
language = "English",
volume = "2",
pages = "208--211",
editor = "J. Kittler and M. Petrou and M. Nixon",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Registration of an uncalibrated image pair to a 3D surface model

AU - Jankó, Zsolt

AU - Chetverikov, D.

PY - 2004

Y1 - 2004

N2 - The following data fusion problem is considered: Given a 3D geometric model of an object and two uncalibrated images of the same object, and assuming that the object surface is textured and Lambertian, precisely register the images to the model. Solving this problem is necessary for building a geometrically accurate, photorealistic model from laser-scanned 3D data and high quality images. We generalise the photo-consistency approach by Clarkson et al. to the case of uncalibrated cameras, when both intrinsic and extrinsic parameters are unknown. This gives a user the freedom of taking the pictures by a conventional digital camera, from arbitrary positions and with varying zoom. We discuss a number of possible approaches to the problem and propose a method based on manual pre-registration followed by a genetic optimisation algorithm. The issues of speed and robustness are addressed. Results for real data are shown.

AB - The following data fusion problem is considered: Given a 3D geometric model of an object and two uncalibrated images of the same object, and assuming that the object surface is textured and Lambertian, precisely register the images to the model. Solving this problem is necessary for building a geometrically accurate, photorealistic model from laser-scanned 3D data and high quality images. We generalise the photo-consistency approach by Clarkson et al. to the case of uncalibrated cameras, when both intrinsic and extrinsic parameters are unknown. This gives a user the freedom of taking the pictures by a conventional digital camera, from arbitrary positions and with varying zoom. We discuss a number of possible approaches to the problem and propose a method based on manual pre-registration followed by a genetic optimisation algorithm. The issues of speed and robustness are addressed. Results for real data are shown.

UR - http://www.scopus.com/inward/record.url?scp=10044271949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10044271949&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 208

EP - 211

BT - Proceedings - International Conference on Pattern Recognition

A2 - Kittler, J.

A2 - Petrou, M.

A2 - Nixon, M.

ER -