Dense Lagrangian motion estimation with occlusions
Publication
, Journal Article
Ricco, S; Tomasi, C
Published in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
October 1, 2012
We couple occlusion modeling and multi-frame motion estimation to compute dense, temporally extended point trajectories in video with significant occlusions. Our approach combines robust spatial regularization with spatially and temporally global occlusion labeling in a variational, Lagrangian framework with subspace constraints. We track points even through ephemeral occlusions. Experiments demonstrate accuracy superior to the state of the art while tracking more points through more frames. © 2012 IEEE.
Duke Scholars
Published In
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOI
ISSN
1063-6919
Publication Date
October 1, 2012
Start / End Page
1800 / 1807
Citation
APA
Chicago
ICMJE
MLA
NLM
Ricco, S., & Tomasi, C. (2012). Dense Lagrangian motion estimation with occlusions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1800–1807. https://doi.org/10.1109/CVPR.2012.6247877
Ricco, S., and C. Tomasi. “Dense Lagrangian motion estimation with occlusions.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, October 1, 2012, 1800–1807. https://doi.org/10.1109/CVPR.2012.6247877.
Ricco S, Tomasi C. Dense Lagrangian motion estimation with occlusions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012 Oct 1;1800–7.
Ricco, S., and C. Tomasi. “Dense Lagrangian motion estimation with occlusions.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Oct. 2012, pp. 1800–07. Scopus, doi:10.1109/CVPR.2012.6247877.
Ricco S, Tomasi C. Dense Lagrangian motion estimation with occlusions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012 Oct 1;1800–1807.
Published In
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOI
ISSN
1063-6919
Publication Date
October 1, 2012
Start / End Page
1800 / 1807