Region extraction from multiple images

Hiroshi Ishikawa, I. H. Jermyn

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

14 Citations (Scopus)

Abstract

We present a method for region identification in multiple images. A set of regions in different images and the correspondences on their boundaries can be thought of as a boundary in the multi-dimensional space formed by the product of the individual image domains. We minimize an energy functional on the space of such boundaries, thereby identifying simultaneously both the optimal regions in each image and the optimal correspondences on their boundaries. We use a ratio form for the energy functional, thus enabling the global minimization of the energy functional using a polynomial time graph algorithm, among other desirable properties. We choose a simple form for this energy that favours boundaries that lie on high intensity gradients in each image, while encouraging correspondences between boundaries in different images that match intensity values. The latter tendency is weighted by a novel heuristic energy that encourages the boundaries to lie on disparity or optical flow discontinuities, although no dense optical flow or disparity map is computed.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Pages509-516
Number of pages8
Volume1
Publication statusPublished - 2001
Externally publishedYes
Event8th International Conference on Computer Vision - Vancouver, BC
Duration: 2001 Jul 92001 Jul 12

Other

Other8th International Conference on Computer Vision
CityVancouver, BC
Period01/7/901/7/12

Fingerprint

Optical flows
Polynomials

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Ishikawa, H., & Jermyn, I. H. (2001). Region extraction from multiple images. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 1, pp. 509-516)

Region extraction from multiple images. / Ishikawa, Hiroshi; Jermyn, I. H.

Proceedings of the IEEE International Conference on Computer Vision. Vol. 1 2001. p. 509-516.

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

Ishikawa, H & Jermyn, IH 2001, Region extraction from multiple images. in Proceedings of the IEEE International Conference on Computer Vision. vol. 1, pp. 509-516, 8th International Conference on Computer Vision, Vancouver, BC, 01/7/9.
Ishikawa H, Jermyn IH. Region extraction from multiple images. In Proceedings of the IEEE International Conference on Computer Vision. Vol. 1. 2001. p. 509-516
Ishikawa, Hiroshi ; Jermyn, I. H. / Region extraction from multiple images. Proceedings of the IEEE International Conference on Computer Vision. Vol. 1 2001. pp. 509-516
@inproceedings{8dd21b18579d4e48ae1dc9d2a6400769,
title = "Region extraction from multiple images",
abstract = "We present a method for region identification in multiple images. A set of regions in different images and the correspondences on their boundaries can be thought of as a boundary in the multi-dimensional space formed by the product of the individual image domains. We minimize an energy functional on the space of such boundaries, thereby identifying simultaneously both the optimal regions in each image and the optimal correspondences on their boundaries. We use a ratio form for the energy functional, thus enabling the global minimization of the energy functional using a polynomial time graph algorithm, among other desirable properties. We choose a simple form for this energy that favours boundaries that lie on high intensity gradients in each image, while encouraging correspondences between boundaries in different images that match intensity values. The latter tendency is weighted by a novel heuristic energy that encourages the boundaries to lie on disparity or optical flow discontinuities, although no dense optical flow or disparity map is computed.",
author = "Hiroshi Ishikawa and Jermyn, {I. H.}",
year = "2001",
language = "English",
volume = "1",
pages = "509--516",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",

}

TY - GEN

T1 - Region extraction from multiple images

AU - Ishikawa, Hiroshi

AU - Jermyn, I. H.

PY - 2001

Y1 - 2001

N2 - We present a method for region identification in multiple images. A set of regions in different images and the correspondences on their boundaries can be thought of as a boundary in the multi-dimensional space formed by the product of the individual image domains. We minimize an energy functional on the space of such boundaries, thereby identifying simultaneously both the optimal regions in each image and the optimal correspondences on their boundaries. We use a ratio form for the energy functional, thus enabling the global minimization of the energy functional using a polynomial time graph algorithm, among other desirable properties. We choose a simple form for this energy that favours boundaries that lie on high intensity gradients in each image, while encouraging correspondences between boundaries in different images that match intensity values. The latter tendency is weighted by a novel heuristic energy that encourages the boundaries to lie on disparity or optical flow discontinuities, although no dense optical flow or disparity map is computed.

AB - We present a method for region identification in multiple images. A set of regions in different images and the correspondences on their boundaries can be thought of as a boundary in the multi-dimensional space formed by the product of the individual image domains. We minimize an energy functional on the space of such boundaries, thereby identifying simultaneously both the optimal regions in each image and the optimal correspondences on their boundaries. We use a ratio form for the energy functional, thus enabling the global minimization of the energy functional using a polynomial time graph algorithm, among other desirable properties. We choose a simple form for this energy that favours boundaries that lie on high intensity gradients in each image, while encouraging correspondences between boundaries in different images that match intensity values. The latter tendency is weighted by a novel heuristic energy that encourages the boundaries to lie on disparity or optical flow discontinuities, although no dense optical flow or disparity map is computed.

UR - http://www.scopus.com/inward/record.url?scp=0034850750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034850750&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034850750

VL - 1

SP - 509

EP - 516

BT - Proceedings of the IEEE International Conference on Computer Vision

ER -