Details
| Original language | English |
|---|---|
| Title of host publication | 2009 Conference for Visual Media Production, CVMP 2009 |
| Subtitle of host publication | Proceedings |
| Pages | 135-143 |
| Number of pages | 9 |
| Publication status | Published - Mar 2010 |
| Event | 6th European Conference for Visual Media Production, CVMP 2009 - London, United Kingdom (UK) Duration: 12 Nov 2009 → 13 Nov 2009 |
Publication series
| Name | CVMP 2009 - The 6th European Conference for Visual Media Production |
|---|
Abstract
The extrinsic calibration of a stereo camera system is a procedure that estimates the position and orientation of a stereo camera system relative to a calibration object. In this paper, a calibration object specified by a CAD model of known shape and arbitrary texture is used. Based on feature points located in the stereo image and using triangulation, 3D object points in the camera coordinate system are calculated. This point cloud is matched to the surface of the CAD model to estimate the position and the rotation of the stereo camera system relative to the object coordinate system. In order to improve the accuracy of known techniques for the calibration, two steps are proposed in this paper. First, a systematic error in the standard method of subpel feature point localization is eliminated by replacing the parabolic interpolation by a Gaussian regression. Second, the estimated accuracies of the 3D points are incorporated by propagating the uncertainties of the detected feature points in the images. To calculate the global minimum of the cost function, an evolutionary optimizer is combined with a two-stage strategy, refining a fast converging approximate result. The developed procedure reduces the error variance of observed points by a factor of about 80.
Keywords
- Camera calibration, Reconstruction, Registration, Stereo vision, Uncertainty propagation
ASJC Scopus subject areas
- Computer Science(all)
- Human-Computer Interaction
- Engineering(all)
- Media Technology
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2009 Conference for Visual Media Production, CVMP 2009: Proceedings. 2010. p. 135-143 5430071 (CVMP 2009 - The 6th European Conference for Visual Media Production).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Extrinsic calibration of a stereo camera system using a 3D CAD model considering the uncertainties of estimated feature points
AU - Cordes, Kai
AU - Mikulastik, Patrick
AU - Vais, Alexander
AU - Ostermann, Jörn
PY - 2010/3
Y1 - 2010/3
N2 - The extrinsic calibration of a stereo camera system is a procedure that estimates the position and orientation of a stereo camera system relative to a calibration object. In this paper, a calibration object specified by a CAD model of known shape and arbitrary texture is used. Based on feature points located in the stereo image and using triangulation, 3D object points in the camera coordinate system are calculated. This point cloud is matched to the surface of the CAD model to estimate the position and the rotation of the stereo camera system relative to the object coordinate system. In order to improve the accuracy of known techniques for the calibration, two steps are proposed in this paper. First, a systematic error in the standard method of subpel feature point localization is eliminated by replacing the parabolic interpolation by a Gaussian regression. Second, the estimated accuracies of the 3D points are incorporated by propagating the uncertainties of the detected feature points in the images. To calculate the global minimum of the cost function, an evolutionary optimizer is combined with a two-stage strategy, refining a fast converging approximate result. The developed procedure reduces the error variance of observed points by a factor of about 80.
AB - The extrinsic calibration of a stereo camera system is a procedure that estimates the position and orientation of a stereo camera system relative to a calibration object. In this paper, a calibration object specified by a CAD model of known shape and arbitrary texture is used. Based on feature points located in the stereo image and using triangulation, 3D object points in the camera coordinate system are calculated. This point cloud is matched to the surface of the CAD model to estimate the position and the rotation of the stereo camera system relative to the object coordinate system. In order to improve the accuracy of known techniques for the calibration, two steps are proposed in this paper. First, a systematic error in the standard method of subpel feature point localization is eliminated by replacing the parabolic interpolation by a Gaussian regression. Second, the estimated accuracies of the 3D points are incorporated by propagating the uncertainties of the detected feature points in the images. To calculate the global minimum of the cost function, an evolutionary optimizer is combined with a two-stage strategy, refining a fast converging approximate result. The developed procedure reduces the error variance of observed points by a factor of about 80.
KW - Camera calibration
KW - Reconstruction
KW - Registration
KW - Stereo vision
KW - Uncertainty propagation
UR - http://www.scopus.com/inward/record.url?scp=77952230352&partnerID=8YFLogxK
U2 - 10.1109/CVMP.2009.10
DO - 10.1109/CVMP.2009.10
M3 - Conference contribution
AN - SCOPUS:77952230352
SN - 9780769538938
T3 - CVMP 2009 - The 6th European Conference for Visual Media Production
SP - 135
EP - 143
BT - 2009 Conference for Visual Media Production, CVMP 2009
T2 - 6th European Conference for Visual Media Production, CVMP 2009
Y2 - 12 November 2009 through 13 November 2009
ER -