Feature matching for building extraction from multiple views

Michel Roux; David M. Mckeown

doi:10.1109/cvpr.1994.323809

Feature matching for building extraction from multiple views

Michel Roux, David M. Mckeown

Carnegie Mellon University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper we present a method to generate three-dimensional building hypotheses starting from sparse features, hypothesized building corners, extracted from multiple views of the scene. This technique relies on knowledge about the imaging geometry and acquisition parameters to provide rigorous geometric constraints for the matching process. The effectiveness of this approach is demonstrated using complex aerial imagery taken with highly oblique views containing buildings with flat or peaked roofs.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	Publ by IEEE
Pages	46-53
Number of pages	8
ISBN (Print)	0818658274, 9780818658273
DOIs	https://doi.org/10.1109/cvpr.1994.323809
Publication status	Published - 1 Jan 1994
Externally published	Yes
Event	Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Seattle, WA, USA Duration: 21 Jun 1994 → 23 Jun 1994

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Conference

Conference	Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
City	Seattle, WA, USA
Period	21/06/94 → 23/06/94

Access to Document

10.1109/cvpr.1994.323809

Cite this

@inproceedings{e4fd415234894eae9fd4c4569e55d809,

title = "Feature matching for building extraction from multiple views",

abstract = "In this paper we present a method to generate three-dimensional building hypotheses starting from sparse features, hypothesized building corners, extracted from multiple views of the scene. This technique relies on knowledge about the imaging geometry and acquisition parameters to provide rigorous geometric constraints for the matching process. The effectiveness of this approach is demonstrated using complex aerial imagery taken with highly oblique views containing buildings with flat or peaked roofs.",

author = "Michel Roux and Mckeown, \{David M.\}",

year = "1994",

month = jan,

day = "1",

doi = "10.1109/cvpr.1994.323809",

language = "English",

isbn = "0818658274",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "Publ by IEEE",

pages = "46--53",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

note = "Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 21-06-1994 Through 23-06-1994",

}

Roux, M & Mckeown, DM 1994, Feature matching for building extraction from multiple views. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Publ by IEEE, pp. 46-53, Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 21/06/94. https://doi.org/10.1109/cvpr.1994.323809

Feature matching for building extraction from multiple views. / Roux, Michel; Mckeown, David M.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Publ by IEEE, 1994. p. 46-53 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature matching for building extraction from multiple views

AU - Roux, Michel

AU - Mckeown, David M.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - In this paper we present a method to generate three-dimensional building hypotheses starting from sparse features, hypothesized building corners, extracted from multiple views of the scene. This technique relies on knowledge about the imaging geometry and acquisition parameters to provide rigorous geometric constraints for the matching process. The effectiveness of this approach is demonstrated using complex aerial imagery taken with highly oblique views containing buildings with flat or peaked roofs.

AB - In this paper we present a method to generate three-dimensional building hypotheses starting from sparse features, hypothesized building corners, extracted from multiple views of the scene. This technique relies on knowledge about the imaging geometry and acquisition parameters to provide rigorous geometric constraints for the matching process. The effectiveness of this approach is demonstrated using complex aerial imagery taken with highly oblique views containing buildings with flat or peaked roofs.

U2 - 10.1109/cvpr.1994.323809

DO - 10.1109/cvpr.1994.323809

M3 - Conference contribution

AN - SCOPUS:0028054623

SN - 0818658274

SN - 9780818658273

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 46

EP - 53

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - Publ by IEEE

T2 - Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 21 June 1994 through 23 June 1994

ER -

Feature matching for building extraction from multiple views

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this