Fast, robust, and consistent camera motion estimation
Publication
, Journal Article
Zhang, T; Tomasi, C
Published in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
January 1, 1999
Previous algorithms that recover camera motion from image velocities suffer from both bias and excessive variance in the results. We propose a robust estimator of camera motion that is statistically consistent when image noise is isotropic. Consistency means that the estimated motion converges in probability to the true value as the number of image points increases. An algorithm based on reweighted Gauss-Newton iterations handles 100 velocity measurements in about 50 milliseconds on a workstation.
Duke Scholars
Published In
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN
1063-6919
Publication Date
January 1, 1999
Volume
1
Start / End Page
164 / 170
Citation
APA
Chicago
ICMJE
MLA
NLM
Zhang, T., & Tomasi, C. (1999). Fast, robust, and consistent camera motion estimation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, 164–170.
Zhang, T., and C. Tomasi. “Fast, robust, and consistent camera motion estimation.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1 (January 1, 1999): 164–70.
Zhang T, Tomasi C. Fast, robust, and consistent camera motion estimation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999 Jan 1;1:164–70.
Zhang, T., and C. Tomasi. “Fast, robust, and consistent camera motion estimation.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, Jan. 1999, pp. 164–70.
Zhang T, Tomasi C. Fast, robust, and consistent camera motion estimation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999 Jan 1;1:164–170.
Published In
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN
1063-6919
Publication Date
January 1, 1999
Volume
1
Start / End Page
164 / 170