Title
Temporal synchronization of non-overlapping videos using known object motion
Abstract
This paper presents a robust technique for temporally aligning multiple video sequences that have no spatial overlap between their fields of view. It is assumed that (i) a moving target with known trajectory is viewed by all cameras at non-overlapping periods in time, (ii) the target trajectory is estimated with a limited error at a constant sampling rate, and (iii) the sequences are recorded by stationary cameras with constant frame rates and fixed intrinsic and extrinsic parameters. The proposed approach reduces the problem of synchronizing N non-overlapping sequences to the problem of robustly estimating a single line from a set of appropriately-generated points in R^N^+^1. This line describes all temporal relations between the N sequences and the moving target. Our technique can handle arbitrarily-large misalignments between the sequences and does not require any a priori information about their temporal relations. Experimental results with real-world and synthetic sequences demonstrate that our method can accurately align the videos.
Year
DOI
Venue
2011
10.1016/j.patrec.2010.02.011
Pattern Recognition Letters
Keywords
Field
DocType
non-overlapping period,temporal relation,synchronizing n non-overlapping sequence,object motion,target trajectory,robust technique,single line,temporal alignment,constant frame rate,n sequence,constant sampling rate,non-overlapping video,video synchronization,temporal synchronization,known trajectory,non-overlapping fields of view,field of view,generic point
Computer vision,Synchronization,Sampling (signal processing),A priori and a posteriori,Synchronizing,Artificial intelligence,Frame rate,Image sequence,Trajectory,Mathematics
Journal
Volume
Issue
ISSN
32
1
Pattern Recognition Letters
Citations 
PageRank 
References 
5
0.42
29
Authors
4
Name
Order
Citations
PageRank
Darlan N. Brito181.15
Flávio L. C. Pádua210210.88
Guilherme A. S. Pereira344533.51
Rodrigo L. Carceroni418218.67