Geolocating static cameras

Nathan Jacobs; Scott Satkin; Nathaniel Roman; Richard Speyer; Robert Pless

doi:10.1109/ICCV.2007.4408995

Geolocating static cameras

Nathan Jacobs, Scott Satkin, Nathaniel Roman, Richard Speyer, Robert Pless

Computer Science

Research output: Contribution to conference › Paper › peer-review

93 Scopus citations

Abstract

A key problem in widely distributed camera networks is geolocating the cameras. This paper considers three scenarios for camera localization: localizing a camera in an unknown environment, adding a new camera in a region with many other cameras, and localizing a camera by finding correlations with satellite imagery. We find that simple summary statistics (the time course of principal component coefficients) are sufficient to geolocate cameras without determining correspondences between cameras or explicitly reasoning about weather in the scene. We present results from a database of images from 538 cameras collected over the course of a year. We find that for cameras that remain stationary and for which we have accurate image times-tamps, we can localize most cameras to within 50 miles of the known location. In addition, we demonstrate the use of a distributed camera network in the construction a map of weather conditions.

Original language	English
DOIs	https://doi.org/10.1109/ICCV.2007.4408995
State	Published - 2007
Event	2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil Duration: Oct 14 2007 → Oct 21 2007

Conference

Conference	2007 IEEE 11th International Conference on Computer Vision, ICCV
Country/Territory	Brazil
City	Rio de Janeiro
Period	10/14/07 → 10/21/07

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2007.4408995

Cite this

@conference{d431530a98b0421888a316b95a5cd1a0,

title = "Geolocating static cameras",

abstract = "A key problem in widely distributed camera networks is geolocating the cameras. This paper considers three scenarios for camera localization: localizing a camera in an unknown environment, adding a new camera in a region with many other cameras, and localizing a camera by finding correlations with satellite imagery. We find that simple summary statistics (the time course of principal component coefficients) are sufficient to geolocate cameras without determining correspondences between cameras or explicitly reasoning about weather in the scene. We present results from a database of images from 538 cameras collected over the course of a year. We find that for cameras that remain stationary and for which we have accurate image times-tamps, we can localize most cameras to within 50 miles of the known location. In addition, we demonstrate the use of a distributed camera network in the construction a map of weather conditions.",

author = "Nathan Jacobs and Scott Satkin and Nathaniel Roman and Richard Speyer and Robert Pless",

year = "2007",

doi = "10.1109/ICCV.2007.4408995",

language = "English",

note = "2007 IEEE 11th International Conference on Computer Vision, ICCV ; Conference date: 14-10-2007 Through 21-10-2007",

}

TY - CONF

T1 - Geolocating static cameras

AU - Jacobs, Nathan

AU - Satkin, Scott

AU - Roman, Nathaniel

AU - Speyer, Richard

AU - Pless, Robert

PY - 2007

Y1 - 2007

N2 - A key problem in widely distributed camera networks is geolocating the cameras. This paper considers three scenarios for camera localization: localizing a camera in an unknown environment, adding a new camera in a region with many other cameras, and localizing a camera by finding correlations with satellite imagery. We find that simple summary statistics (the time course of principal component coefficients) are sufficient to geolocate cameras without determining correspondences between cameras or explicitly reasoning about weather in the scene. We present results from a database of images from 538 cameras collected over the course of a year. We find that for cameras that remain stationary and for which we have accurate image times-tamps, we can localize most cameras to within 50 miles of the known location. In addition, we demonstrate the use of a distributed camera network in the construction a map of weather conditions.

AB - A key problem in widely distributed camera networks is geolocating the cameras. This paper considers three scenarios for camera localization: localizing a camera in an unknown environment, adding a new camera in a region with many other cameras, and localizing a camera by finding correlations with satellite imagery. We find that simple summary statistics (the time course of principal component coefficients) are sufficient to geolocate cameras without determining correspondences between cameras or explicitly reasoning about weather in the scene. We present results from a database of images from 538 cameras collected over the course of a year. We find that for cameras that remain stationary and for which we have accurate image times-tamps, we can localize most cameras to within 50 miles of the known location. In addition, we demonstrate the use of a distributed camera network in the construction a map of weather conditions.

UR - http://www.scopus.com/inward/record.url?scp=50649092843&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50649092843&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2007.4408995

DO - 10.1109/ICCV.2007.4408995

M3 - Paper

AN - SCOPUS:50649092843

T2 - 2007 IEEE 11th International Conference on Computer Vision, ICCV

Y2 - 14 October 2007 through 21 October 2007

ER -

Geolocating static cameras

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this