Tiling of ortho-rectified facade images

Przemyslaw Musialski, Meinrad Recheis, Stefan Maierhofer, Peter Wonka, Werner Purgathofer

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

11 Citations (Scopus)

Abstract

Typical building facades consist of regular structures such as windows arranged in a predominantly grid-like manner. We propose a method that handles precisely such facades and assumes that there must be horizontal and vertical repetitions of similar patterns. Using a Monte Carlo sampling approach, this method is able to segment repetitive patterns on orthogonal images along the axes even if the pattern is partially occluded. Additionally, it is very fast and can be used as a preprocessing step for finer segmentation stages.

Original languageEnglish (US)
Title of host publicationProceedings - SCCG 2010: 26th Spring Conference on Computer Graphics
Pages117-126
Number of pages10
DOIs
StatePublished - 2010
Event26th Spring Conference on Computer Graphics, SCCG 2010 - Budmerice, Slovakia
Duration: May 13 2010May 15 2010

Other

Other26th Spring Conference on Computer Graphics, SCCG 2010
CountrySlovakia
CityBudmerice
Period5/13/105/15/10

Fingerprint

Facades
Sampling

Keywords

  • Image processing
  • Image segmentation
  • Image-based urban reconstruction

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Musialski, P., Recheis, M., Maierhofer, S., Wonka, P., & Purgathofer, W. (2010). Tiling of ortho-rectified facade images. In Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics (pp. 117-126). [1925081] https://doi.org/10.1145/1925059.1925081

Tiling of ortho-rectified facade images. / Musialski, Przemyslaw; Recheis, Meinrad; Maierhofer, Stefan; Wonka, Peter; Purgathofer, Werner.

Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics. 2010. p. 117-126 1925081.

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

Musialski, P, Recheis, M, Maierhofer, S, Wonka, P & Purgathofer, W 2010, Tiling of ortho-rectified facade images. in Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics., 1925081, pp. 117-126, 26th Spring Conference on Computer Graphics, SCCG 2010, Budmerice, Slovakia, 5/13/10. https://doi.org/10.1145/1925059.1925081
Musialski P, Recheis M, Maierhofer S, Wonka P, Purgathofer W. Tiling of ortho-rectified facade images. In Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics. 2010. p. 117-126. 1925081 https://doi.org/10.1145/1925059.1925081
Musialski, Przemyslaw ; Recheis, Meinrad ; Maierhofer, Stefan ; Wonka, Peter ; Purgathofer, Werner. / Tiling of ortho-rectified facade images. Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics. 2010. pp. 117-126
@inproceedings{7ca30aa8045545ed9a666db7f22e53f8,
title = "Tiling of ortho-rectified facade images",
abstract = "Typical building facades consist of regular structures such as windows arranged in a predominantly grid-like manner. We propose a method that handles precisely such facades and assumes that there must be horizontal and vertical repetitions of similar patterns. Using a Monte Carlo sampling approach, this method is able to segment repetitive patterns on orthogonal images along the axes even if the pattern is partially occluded. Additionally, it is very fast and can be used as a preprocessing step for finer segmentation stages.",
keywords = "Image processing, Image segmentation, Image-based urban reconstruction",
author = "Przemyslaw Musialski and Meinrad Recheis and Stefan Maierhofer and Peter Wonka and Werner Purgathofer",
year = "2010",
doi = "10.1145/1925059.1925081",
language = "English (US)",
isbn = "9781450305587",
pages = "117--126",
booktitle = "Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics",

}

TY - GEN

T1 - Tiling of ortho-rectified facade images

AU - Musialski, Przemyslaw

AU - Recheis, Meinrad

AU - Maierhofer, Stefan

AU - Wonka, Peter

AU - Purgathofer, Werner

PY - 2010

Y1 - 2010

N2 - Typical building facades consist of regular structures such as windows arranged in a predominantly grid-like manner. We propose a method that handles precisely such facades and assumes that there must be horizontal and vertical repetitions of similar patterns. Using a Monte Carlo sampling approach, this method is able to segment repetitive patterns on orthogonal images along the axes even if the pattern is partially occluded. Additionally, it is very fast and can be used as a preprocessing step for finer segmentation stages.

AB - Typical building facades consist of regular structures such as windows arranged in a predominantly grid-like manner. We propose a method that handles precisely such facades and assumes that there must be horizontal and vertical repetitions of similar patterns. Using a Monte Carlo sampling approach, this method is able to segment repetitive patterns on orthogonal images along the axes even if the pattern is partially occluded. Additionally, it is very fast and can be used as a preprocessing step for finer segmentation stages.

KW - Image processing

KW - Image segmentation

KW - Image-based urban reconstruction

UR - http://www.scopus.com/inward/record.url?scp=79952349851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952349851&partnerID=8YFLogxK

U2 - 10.1145/1925059.1925081

DO - 10.1145/1925059.1925081

M3 - Conference contribution

SN - 9781450305587

SP - 117

EP - 126

BT - Proceedings - SCCG 2010: 26th Spring Conference on Computer Graphics

ER -