Abstract | ||
---|---|---|
We present a novel approach for temporally aligning N unsynchronized sequences of a dynamic 3D scene, captured from distinct viewpoints. Unlike existing methods, which work for N = 2 and rely on a computationally-intensive search in the space of temporal alignments, we reduce the problem for general N to the robust estimation of a single line in RN. This line captures all temporal relations between the sequences and can be computed without any prior knowledge of these relations. Experimental results show that our method can accurately align sequences even when they have large mis-alignments (e.g., hundreds of frames), when the problem is seemingly ambiguous (e.g., scenes with roughly periodic motion), and when accurate manual alignment is difficult (e.g., due to slow-moving objects). |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/CVPR.2004.1315106 | Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference |
Keywords | Field | DocType |
estimation theory,geometry,image reconstruction,image sequences,spatiotemporal phenomena,video signal processing,dynamic 3D scene,geometry,manual alignment,periodic motion,prior knowledge,robust estimation,search problems,sequence alignment,temporal alignments,temporal relations,timeline reconstruction,unsynchronized sequences,video sequences | Iterative reconstruction,Sequence alignment,Computer vision,Periodic function,Pattern recognition,Viewpoints,Computer science,Artificial intelligence,Estimation theory | Conference |
Volume | Issue | ISSN |
1 | 2 | 1063-6919 |
ISBN | Citations | PageRank |
0-7695-2158-4 | 24 | 1.12 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carceroni, R.L. | 1 | 87 | 5.93 |
Flávio L. C. Pádua | 2 | 102 | 10.88 |
Geraldo A. M. R. Santos | 3 | 24 | 1.12 |
Kiriakos N. Kutulakos | 4 | 173 | 8.38 |