Detecting and matching repeated patterns for automatic geo-tagging in urban environments

Grant Schindler, Panchapagesan Krishnamurthy, Roberto Lublinerman, Yanxi Liu, Frank Dellaert

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

95 Citations (Scopus)

Abstract

We present a novel method for automatically geo-tagging photographs of man-made environments via detection and matching of repeated patterns. Highly repetitive environments introduce numerous correspondence ambiguities and are problematic for traditional wide-baseline matching methods. Our method exploits the highly repetitive nature of urban environments, detecting multiple perspectively distorted periodic 2D patterns in an image and matching them to a 3D database of textured facades by reasoning about the underlying canonical forms of each pattern. Multiple 2D-to-3D pattern correspondences enable robust recovery of camera orientation and location. We demonstrate the success of this method in a large urban environment.

Original languageEnglish (US)
Title of host publication26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
DOIs
StatePublished - Sep 23 2008
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR - Anchorage, AK, United States
Duration: Jun 23 2008Jun 28 2008

Publication series

Name26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Other

Other26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
CountryUnited States
CityAnchorage, AK
Period6/23/086/28/08

Fingerprint

Facades
Pattern matching
Cameras
Recovery

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering

Cite this

Schindler, G., Krishnamurthy, P., Lublinerman, R., Liu, Y., & Dellaert, F. (2008). Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR [4587461] (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR). https://doi.org/10.1109/CVPR.2008.4587461
Schindler, Grant ; Krishnamurthy, Panchapagesan ; Lublinerman, Roberto ; Liu, Yanxi ; Dellaert, Frank. / Detecting and matching repeated patterns for automatic geo-tagging in urban environments. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR).
@inproceedings{149f7565413b4c9e8f11d9abad62d7bb,
title = "Detecting and matching repeated patterns for automatic geo-tagging in urban environments",
abstract = "We present a novel method for automatically geo-tagging photographs of man-made environments via detection and matching of repeated patterns. Highly repetitive environments introduce numerous correspondence ambiguities and are problematic for traditional wide-baseline matching methods. Our method exploits the highly repetitive nature of urban environments, detecting multiple perspectively distorted periodic 2D patterns in an image and matching them to a 3D database of textured facades by reasoning about the underlying canonical forms of each pattern. Multiple 2D-to-3D pattern correspondences enable robust recovery of camera orientation and location. We demonstrate the success of this method in a large urban environment.",
author = "Grant Schindler and Panchapagesan Krishnamurthy and Roberto Lublinerman and Yanxi Liu and Frank Dellaert",
year = "2008",
month = "9",
day = "23",
doi = "10.1109/CVPR.2008.4587461",
language = "English (US)",
isbn = "9781424422432",
series = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",
booktitle = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

}

Schindler, G, Krishnamurthy, P, Lublinerman, R, Liu, Y & Dellaert, F 2008, Detecting and matching repeated patterns for automatic geo-tagging in urban environments. in 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR., 4587461, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Anchorage, AK, United States, 6/23/08. https://doi.org/10.1109/CVPR.2008.4587461

Detecting and matching repeated patterns for automatic geo-tagging in urban environments. / Schindler, Grant; Krishnamurthy, Panchapagesan; Lublinerman, Roberto; Liu, Yanxi; Dellaert, Frank.

26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. 4587461 (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR).

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

TY - GEN

T1 - Detecting and matching repeated patterns for automatic geo-tagging in urban environments

AU - Schindler, Grant

AU - Krishnamurthy, Panchapagesan

AU - Lublinerman, Roberto

AU - Liu, Yanxi

AU - Dellaert, Frank

PY - 2008/9/23

Y1 - 2008/9/23

N2 - We present a novel method for automatically geo-tagging photographs of man-made environments via detection and matching of repeated patterns. Highly repetitive environments introduce numerous correspondence ambiguities and are problematic for traditional wide-baseline matching methods. Our method exploits the highly repetitive nature of urban environments, detecting multiple perspectively distorted periodic 2D patterns in an image and matching them to a 3D database of textured facades by reasoning about the underlying canonical forms of each pattern. Multiple 2D-to-3D pattern correspondences enable robust recovery of camera orientation and location. We demonstrate the success of this method in a large urban environment.

AB - We present a novel method for automatically geo-tagging photographs of man-made environments via detection and matching of repeated patterns. Highly repetitive environments introduce numerous correspondence ambiguities and are problematic for traditional wide-baseline matching methods. Our method exploits the highly repetitive nature of urban environments, detecting multiple perspectively distorted periodic 2D patterns in an image and matching them to a 3D database of textured facades by reasoning about the underlying canonical forms of each pattern. Multiple 2D-to-3D pattern correspondences enable robust recovery of camera orientation and location. We demonstrate the success of this method in a large urban environment.

UR - http://www.scopus.com/inward/record.url?scp=51949108641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949108641&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2008.4587461

DO - 10.1109/CVPR.2008.4587461

M3 - Conference contribution

AN - SCOPUS:51949108641

SN - 9781424422432

T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

ER -

Schindler G, Krishnamurthy P, Lublinerman R, Liu Y, Dellaert F. Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. 4587461. (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR). https://doi.org/10.1109/CVPR.2008.4587461