TEMPORAL SYNCHRONIZATION FROM CAMERA MOTION

This paper presents a method to recover the temporal synchronization between a pair of video sequences using the frame-to-frame motion of the sequences instead of pixelbased comparisons between the two sequences. A previous method uses the similarity between corresponding frame-to-frame homographies. It works when the transformations are extremely accurate, but is not robust in the presence of noise. To overcome these problems, we have created and tested four new measures. All of the new measures perform well with either precise or noisy data for both real and synthetic sequences.

[1]  Michal Irani,et al.  Computing occluding and transparent motions , 1994, International Journal of Computer Vision.

[2]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[3]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[4]  Yaron Caspi,et al.  Alignment of non-overlapping sequences , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Michael J. Black,et al.  Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Richard I. Hartley,et al.  In defence of the 8-point algorithm , 1995, Proceedings of IEEE International Conference on Computer Vision.