Stochastic view registration of overlapping cameras based on arbitrary motion

Zoltán Szlávik, T. Szirányi, László Havasi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A new motion-based method is presented for automatic registration of images in multicamera systems, to permit synthesis of wide-baseline composite views. Unlike existing static-image and motion-based methods, our approach does not need any a priori information about the scene, the appearance of objects in the scene, or their motion. We introduce an entropy-based preselection of motion histories and an iterative Bayesian assignment of corresponding image areas. Finally, correlated point-histories and data-set optimization lead to the matching of the different views. The method is validated by demonstrating its successful use on several real-life indoor and outdoor stereo video image-sequence pairs.

Original languageEnglish
Pages (from-to)710-720
Number of pages11
JournalIEEE Transactions on Image Processing
Volume16
Issue number3
DOIs
Publication statusPublished - Mar 2007

Fingerprint

Registration
Overlapping
Entropy
Camera
Cameras
Motion
Composite materials
Arbitrary
Image Sequence
Baseline
Assignment
Composite
Synthesis
Optimization
History

Keywords

  • Image registration
  • Stereo image processing
  • Video surveillance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Stochastic view registration of overlapping cameras based on arbitrary motion. / Szlávik, Zoltán; Szirányi, T.; Havasi, László.

In: IEEE Transactions on Image Processing, Vol. 16, No. 3, 03.2007, p. 710-720.

Research output: Contribution to journalArticle

@article{0e9358ee41c74f8989e40dde1051ffc4,
title = "Stochastic view registration of overlapping cameras based on arbitrary motion",
abstract = "A new motion-based method is presented for automatic registration of images in multicamera systems, to permit synthesis of wide-baseline composite views. Unlike existing static-image and motion-based methods, our approach does not need any a priori information about the scene, the appearance of objects in the scene, or their motion. We introduce an entropy-based preselection of motion histories and an iterative Bayesian assignment of corresponding image areas. Finally, correlated point-histories and data-set optimization lead to the matching of the different views. The method is validated by demonstrating its successful use on several real-life indoor and outdoor stereo video image-sequence pairs.",
keywords = "Image registration, Stereo image processing, Video surveillance",
author = "Zolt{\'a}n Szl{\'a}vik and T. Szir{\'a}nyi and L{\'a}szl{\'o} Havasi",
year = "2007",
month = "3",
doi = "10.1109/TIP.2007.891158",
language = "English",
volume = "16",
pages = "710--720",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Stochastic view registration of overlapping cameras based on arbitrary motion

AU - Szlávik, Zoltán

AU - Szirányi, T.

AU - Havasi, László

PY - 2007/3

Y1 - 2007/3

N2 - A new motion-based method is presented for automatic registration of images in multicamera systems, to permit synthesis of wide-baseline composite views. Unlike existing static-image and motion-based methods, our approach does not need any a priori information about the scene, the appearance of objects in the scene, or their motion. We introduce an entropy-based preselection of motion histories and an iterative Bayesian assignment of corresponding image areas. Finally, correlated point-histories and data-set optimization lead to the matching of the different views. The method is validated by demonstrating its successful use on several real-life indoor and outdoor stereo video image-sequence pairs.

AB - A new motion-based method is presented for automatic registration of images in multicamera systems, to permit synthesis of wide-baseline composite views. Unlike existing static-image and motion-based methods, our approach does not need any a priori information about the scene, the appearance of objects in the scene, or their motion. We introduce an entropy-based preselection of motion histories and an iterative Bayesian assignment of corresponding image areas. Finally, correlated point-histories and data-set optimization lead to the matching of the different views. The method is validated by demonstrating its successful use on several real-life indoor and outdoor stereo video image-sequence pairs.

KW - Image registration

KW - Stereo image processing

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=33947234235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947234235&partnerID=8YFLogxK

U2 - 10.1109/TIP.2007.891158

DO - 10.1109/TIP.2007.891158

M3 - Article

C2 - 17357731

AN - SCOPUS:33947234235

VL - 16

SP - 710

EP - 720

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 3

ER -