Camera geo-calibration using an MCMC approach

Menghua Zhai; Scott Workman; Nathan Jacobs

doi:10.1109/ICIP.2016.7532905

Camera geo-calibration using an MCMC approach

Menghua Zhai
, Scott Workman
, Nathan Jacobs

Computer Science

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

Abstract

We address the problem of single-image geo-calibration, in which an estimate of the geographic location, viewing direction and field of view is sought for the camera that captured an image. The dominant approach to this problem is to match features of the query image, using color and texture, against a reference database of nearby ground imagery. However, this fails when such imagery is not available. We propose to overcome this limitation by matching against a geographic database that contains the locations of known objects, such as houses, roads and bodies of water. Since we are unable to find one-to-one correspondences between image locations and objects in our database, we model the problem probabilistically based on the geometric configuration of multiple such weak correspondences. We propose a Markov Chain Monte Carlo (MCMC) sampling approach to approximate the underlying probability distribution over the full geo-calibration of the camera.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
Pages	2976-2980
Number of pages	5
ISBN (Electronic)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7532905
State	Published - Aug 3 2016
Event	23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: Sep 25 2016 → Sep 28 2016

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2016-August
ISSN (Print)	1522-4880

Conference

Conference	23rd IEEE International Conference on Image Processing, ICIP 2016
Country/Territory	United States
City	Phoenix
Period	9/25/16 → 9/28/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Geo-calibration
Monte Carlo

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2016.7532905

Cite this

@inproceedings{3769534a931545ecb204b39d066d1814,

title = "Camera geo-calibration using an MCMC approach",

abstract = "We address the problem of single-image geo-calibration, in which an estimate of the geographic location, viewing direction and field of view is sought for the camera that captured an image. The dominant approach to this problem is to match features of the query image, using color and texture, against a reference database of nearby ground imagery. However, this fails when such imagery is not available. We propose to overcome this limitation by matching against a geographic database that contains the locations of known objects, such as houses, roads and bodies of water. Since we are unable to find one-to-one correspondences between image locations and objects in our database, we model the problem probabilistically based on the geometric configuration of multiple such weak correspondences. We propose a Markov Chain Monte Carlo (MCMC) sampling approach to approximate the underlying probability distribution over the full geo-calibration of the camera.",

keywords = "Geo-calibration, Monte Carlo",

author = "Menghua Zhai and Scott Workman and Nathan Jacobs",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

month = aug,

day = "3",

doi = "10.1109/ICIP.2016.7532905",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "2976--2980",

booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",

}

Zhai, M, Workman, S & Jacobs, N 2016, Camera geo-calibration using an MCMC approach. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings., 7532905, Proceedings - International Conference on Image Processing, ICIP, vol. 2016-August, pp. 2976-2980, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7532905

Camera geo-calibration using an MCMC approach. / Zhai, Menghua; Workman, Scott; Jacobs, Nathan.
2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. 2016. p. 2976-2980 7532905 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August).

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

TY - GEN

T1 - Camera geo-calibration using an MCMC approach

AU - Zhai, Menghua

AU - Workman, Scott

AU - Jacobs, Nathan

PY - 2016/8/3

Y1 - 2016/8/3

N2 - We address the problem of single-image geo-calibration, in which an estimate of the geographic location, viewing direction and field of view is sought for the camera that captured an image. The dominant approach to this problem is to match features of the query image, using color and texture, against a reference database of nearby ground imagery. However, this fails when such imagery is not available. We propose to overcome this limitation by matching against a geographic database that contains the locations of known objects, such as houses, roads and bodies of water. Since we are unable to find one-to-one correspondences between image locations and objects in our database, we model the problem probabilistically based on the geometric configuration of multiple such weak correspondences. We propose a Markov Chain Monte Carlo (MCMC) sampling approach to approximate the underlying probability distribution over the full geo-calibration of the camera.

AB - We address the problem of single-image geo-calibration, in which an estimate of the geographic location, viewing direction and field of view is sought for the camera that captured an image. The dominant approach to this problem is to match features of the query image, using color and texture, against a reference database of nearby ground imagery. However, this fails when such imagery is not available. We propose to overcome this limitation by matching against a geographic database that contains the locations of known objects, such as houses, roads and bodies of water. Since we are unable to find one-to-one correspondences between image locations and objects in our database, we model the problem probabilistically based on the geometric configuration of multiple such weak correspondences. We propose a Markov Chain Monte Carlo (MCMC) sampling approach to approximate the underlying probability distribution over the full geo-calibration of the camera.

KW - Geo-calibration

KW - Monte Carlo

UR - https://www.scopus.com/pages/publications/85006836396

UR - https://www.scopus.com/pages/publications/85006836396#tab=citedBy

U2 - 10.1109/ICIP.2016.7532905

DO - 10.1109/ICIP.2016.7532905

M3 - Conference contribution

AN - SCOPUS:85006836396

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2976

EP - 2980

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016

Y2 - 25 September 2016 through 28 September 2016

ER -

Camera geo-calibration using an MCMC approach

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this